Models
What builders use, how models score, and what they cost. Usage comes from public Tokscale submissions. Scores come from Epoch AI, LMArena and Terminal-Bench, each with its own unit, date and run conditions. Prices are list prices from models.dev.
Oct 18 – Nov 16, 2026 (UTC)951 accounts100% of tokens from an identified modelData through Nov 16, 2026, 01:05 UTCHow we count
| Model | Top agent | |||||
|---|---|---|---|---|---|---|
Claude Opus 5.51. Anthropic | 711Down 103 from 814 active users in the previous 30 days. | 168.5 Epoch Capabilities Index: 168.5
Source · Epoch AI, ‘Capabilities & benchmarking’, epoch.ai/benchmarks (CC BY 4.0) | 65.8%Max · Claude Code Terminal-Bench 4.1: 65.8%
Source · Terminal-Bench 4.1 official leaderboard, tbench.ai | 1,807Max WebDev Arena: 1,807
Source · LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset on Hugging Face), CC BY 4.0 | $0.42 Estimate at list prices
The list price of each token type, weighted by its share of the mix. Reasoning tokens are priced as output. Discounts, batch prices and long-context tiers are not applied. Not what anyone paid. | |
GPT-6.1 Sol2. OpenAI | 671Down 55 from 726 active users in the previous 30 days. | 168.5 Epoch Capabilities Index: 168.5
Source · Epoch AI, ‘Capabilities & benchmarking’, epoch.ai/benchmarks (CC BY 4.0) | 60.9%Max · Codex Terminal-Bench 4.1: 60.9%
Source · Terminal-Bench 4.1 official leaderboard, tbench.ai | 1,753Max WebDev Arena: 1,753
Source · LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset on Hugging Face), CC BY 4.0 | $0.21 Estimate at list prices
The list price of each token type, weighted by its share of the mix. Reasoning tokens are priced as output. Discounts, batch prices and long-context tiers are not applied. Not what anyone paid. | |
GPT-6 Astra3. OpenAI | 562Down 248 from 810 active users in the previous 30 days. | 169.0 Epoch Capabilities Index: 169.0
Source · Epoch AI, ‘Capabilities & benchmarking’, epoch.ai/benchmarks (CC BY 4.0) | 60.3%Max · Codex Terminal-Bench 4.1: 60.3%
Best of 5 reported results for this model. Source · Terminal-Bench 4.1 official leaderboard, tbench.ai | 1,774Max WebDev Arena: 1,774
Source · LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset on Hugging Face), CC BY 4.0 | $1.53 Estimate at list prices
The list price of each token type, weighted by its share of the mix. Reasoning tokens are priced as output. Discounts, batch prices and long-context tiers are not applied. Not what anyone paid. | |
Claude Sonnet 5.54. Anthropic | 554No change from 554 active users in the previous 30 days. | 166.6 Epoch Capabilities Index: 166.6
Source · Epoch AI, ‘Capabilities & benchmarking’, epoch.ai/benchmarks (CC BY 4.0) | 63.9%Max · Claude Code Terminal-Bench 4.1: 63.9%
Source · Terminal-Bench 4.1 official leaderboard, tbench.ai | 1,768XHigh WebDev Arena: 1,768
Best of 2 reported results for this model. Source · LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset on Hugging Face), CC BY 4.0 | $0.21 Estimate at list prices
The list price of each token type, weighted by its share of the mix. Reasoning tokens are priced as output. Discounts, batch prices and long-context tiers are not applied. Not what anyone paid. | |
Claude Haiku 5.55. Anthropic | 498Up 171 from 327 active users in the previous 30 days. | 160.4 Epoch Capabilities Index: 160.4
Source · Epoch AI, ‘Capabilities & benchmarking’, epoch.ai/benchmarks (CC BY 4.0) | Not evaluated on Terminal-Bench 4.1 | 1,586High WebDev Arena: 1,586
Source · LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset on Hugging Face), CC BY 4.0 | $0.02 Estimate at list prices
The list price of each token type, weighted by its share of the mix. Reasoning tokens are priced as output. Discounts, batch prices and long-context tiers are not applied. Not what anyone paid. | |
GPT-6 Luna6. OpenAI | 425Down 150 from 575 active users in the previous 30 days. | 156.4 Epoch Capabilities Index: 156.4
Source · Epoch AI, ‘Capabilities & benchmarking’, epoch.ai/benchmarks (CC BY 4.0) | 15.2%Max · Codex Terminal-Bench 4.1: 15.2%
Source · Terminal-Bench 4.1 official leaderboard, tbench.ai | 1,578Max WebDev Arena: 1,578
Source · LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset on Hugging Face), CC BY 4.0 | $0.02 Estimate at list prices
The list price of each token type, weighted by its share of the mix. Reasoning tokens are priced as output. Discounts, batch prices and long-context tiers are not applied. Not what anyone paid. | |
Claude Fable 5.17. Anthropic | 353Down 167 from 520 active users in the previous 30 days. | 167.0 Epoch Capabilities Index: 167.0
Source · Epoch AI, ‘Capabilities & benchmarking’, epoch.ai/benchmarks (CC BY 4.0) | 57.6%XHigh · Claude Code Terminal-Bench 4.1: 57.6%
Best of 5 reported results for this model. Source · Terminal-Bench 4.1 official leaderboard, tbench.ai | 1,743Max WebDev Arena: 1,743
Source · LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset on Hugging Face), CC BY 4.0 | $0.81 Estimate at list prices
The list price of each token type, weighted by its share of the mix. Reasoning tokens are priced as output. Discounts, batch prices and long-context tiers are not applied. Not what anyone paid. | |
Claude Fable 5.28. Anthropic | 326Up 325 from 1 active users in the previous 30 days. | 173.4 Epoch Capabilities Index: 173.4
Source · Epoch AI, ‘Capabilities & benchmarking’, epoch.ai/benchmarks (CC BY 4.0) | Not evaluated on Terminal-Bench 4.1 | Not evaluated on WebDev Arena | $0.65 Estimate at list prices
The list price of each token type, weighted by its share of the mix. Reasoning tokens are priced as output. Discounts, batch prices and long-context tiers are not applied. Not what anyone paid. | |
GPT-6.1 Terra9. OpenAI | 304Up 300 from 4 active users in the previous 30 days. | 167.7 Epoch Capabilities Index: 167.7
Source · Epoch AI, ‘Capabilities & benchmarking’, epoch.ai/benchmarks (CC BY 4.0) | Not evaluated on Terminal-Bench 4.1 | Not evaluated on WebDev Arena | $0.11 Estimate at list prices
The list price of each token type, weighted by its share of the mix. Reasoning tokens are priced as output. Discounts, batch prices and long-context tiers are not applied. Not what anyone paid. | |
Codex Auto Review10. OpenAI | 281Down 113 from 394 active users in the previous 30 days. | Not evaluated on Epoch Capabilities Index | Not evaluated on Terminal-Bench 4.1 | Not evaluated on WebDev Arena | No list price on models.dev | |
DeepSeek V4.1 Flash11. DeepSeek | 223Down 44 from 267 active users in the previous 30 days. | 156.7 Epoch Capabilities Index: 156.7
Source · Epoch AI, ‘Capabilities & benchmarking’, epoch.ai/benchmarks (CC BY 4.0) | Not evaluated on Terminal-Bench 4.1 | 1,664Max WebDev Arena: 1,664
Best of 2 reported results for this model. Source · LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset on Hugging Face), CC BY 4.0 | $0.02 Estimate at list prices
The list price of each token type, weighted by its share of the mix. Reasoning tokens are priced as output. Discounts, batch prices and long-context tiers are not applied. Not what anyone paid. No cache-write price is listed, so cache writes are priced as input. | |
Claude Opus 4.812. Anthropic | 221Down 83 from 304 active users in the previous 30 days. | 159.9 Epoch Capabilities Index: 159.9
Source · Epoch AI, ‘Capabilities & benchmarking’, epoch.ai/benchmarks (CC BY 4.0) | 23.6%Max · Claude Code Terminal-Bench 4.1: 23.6%
Source · Terminal-Bench 4.1 official leaderboard, tbench.ai | 1,556High WebDev Arena: 1,556
Best of 2 reported results for this model. Source · LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset on Hugging Face), CC BY 4.0 | $0.77 Estimate at list prices
The list price of each token type, weighted by its share of the mix. Reasoning tokens are priced as output. Discounts, batch prices and long-context tiers are not applied. Not what anyone paid. | |
GPT-6 Sol13. OpenAI | 213Down 412 from 625 active users in the previous 30 days. | 163.8 Epoch Capabilities Index: 163.8
Source · Epoch AI, ‘Capabilities & benchmarking’, epoch.ai/benchmarks (CC BY 4.0) | 50.3%Max · Codex Terminal-Bench 4.1: 50.3%
Source · Terminal-Bench 4.1 official leaderboard, tbench.ai | 1,683Max WebDev Arena: 1,683
Source · LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset on Hugging Face), CC BY 4.0 | $0.31 Estimate at list prices
The list price of each token type, weighted by its share of the mix. Reasoning tokens are priced as output. Discounts, batch prices and long-context tiers are not applied. Not what anyone paid. | |
GPT-5.6 Sol14. OpenAI | 208Down 458 from 666 active users in the previous 30 days. | 163.0 Epoch Capabilities Index: 163.0
Source · Epoch AI, ‘Capabilities & benchmarking’, epoch.ai/benchmarks (CC BY 4.0) | 38.5%Max · Codex Terminal-Bench 4.1: 38.5%
Source · Terminal-Bench 4.1 official leaderboard, tbench.ai | 1,616XHigh · Codex WebDev Arena: 1,616
Source · LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset on Hugging Face), CC BY 4.0 | $0.61 Estimate at list prices
The list price of each token type, weighted by its share of the mix. Reasoning tokens are priced as output. Discounts, batch prices and long-context tiers are not applied. Not what anyone paid. | |
Claude Opus 515. Anthropic | 168Down 453 from 621 active users in the previous 30 days. | 164.7 Epoch Capabilities Index: 164.7
Source · Epoch AI, ‘Capabilities & benchmarking’, epoch.ai/benchmarks (CC BY 4.0) | 53.3%XHigh · Claude Code Terminal-Bench 4.1: 53.3%
Best of 5 reported results for this model. Source · Terminal-Bench 4.1 official leaderboard, tbench.ai | 1,689Max WebDev Arena: 1,689
Best of 2 reported results for this model. Source · LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset on Hugging Face), CC BY 4.0 | $0.77 Estimate at list prices
The list price of each token type, weighted by its share of the mix. Reasoning tokens are priced as output. Discounts, batch prices and long-context tiers are not applied. Not what anyone paid. | |
GLM-5.3 Flash16. Z.ai | 158Down 87 from 245 active users in the previous 30 days. | 153.8 Epoch Capabilities Index: 153.8
Source · Epoch AI, ‘Capabilities & benchmarking’, epoch.ai/benchmarks (CC BY 4.0) | 35.4%No reasoning · Claude Code Terminal-Bench 4.1: 35.4%
Source · Terminal-Bench 4.1 official leaderboard, tbench.ai | 1,607 WebDev Arena: 1,607
Source · LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset on Hugging Face), CC BY 4.0 | $0.03 Estimate at list prices
The list price of each token type, weighted by its share of the mix. Reasoning tokens are priced as output. Discounts, batch prices and long-context tiers are not applied. Not what anyone paid. | |
DeepSeek V4.1 Flash Free17. DeepSeek | 152Up 85 from 67 active users in the previous 30 days. | Not evaluated on Epoch Capabilities Index | Not evaluated on Terminal-Bench 4.1 | Not evaluated on WebDev Arena | No list price on models.dev | |
GPT-5.6 Luna18. OpenAI | 144Down 354 from 498 active users in the previous 30 days. | 156.7 Epoch Capabilities Index: 156.7
Source · Epoch AI, ‘Capabilities & benchmarking’, epoch.ai/benchmarks (CC BY 4.0) | 17.6%Max · Codex Terminal-Bench 4.1: 17.6%
Source · Terminal-Bench 4.1 official leaderboard, tbench.ai | 1,518XHigh · Codex WebDev Arena: 1,518
Source · LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset on Hugging Face), CC BY 4.0 | $0.03 Estimate at list prices
The list price of each token type, weighted by its share of the mix. Reasoning tokens are priced as output. Discounts, batch prices and long-context tiers are not applied. Not what anyone paid. | |
Claude Sonnet 519. Anthropic | 130Down 364 from 494 active users in the previous 30 days. | 156.9 Epoch Capabilities Index: 156.9
Source · Epoch AI, ‘Capabilities & benchmarking’, epoch.ai/benchmarks (CC BY 4.0) | 12.1%Max · Claude Code Terminal-Bench 4.1: 12.1%
Source · Terminal-Bench 4.1 official leaderboard, tbench.ai | 1,540High WebDev Arena: 1,540
Source · LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset on Hugging Face), CC BY 4.0 | $0.31 Estimate at list prices
The list price of each token type, weighted by its share of the mix. Reasoning tokens are priced as output. Discounts, batch prices and long-context tiers are not applied. Not what anyone paid. | |
GLM-5.320. Z.ai | 128Down 55 from 183 active users in the previous 30 days. | 157.1 Epoch Capabilities Index: 157.1
Source · Epoch AI, ‘Capabilities & benchmarking’, epoch.ai/benchmarks (CC BY 4.0) | 41.2%Max · Claude Code Terminal-Bench 4.1: 41.2%
Source · Terminal-Bench 4.1 official leaderboard, tbench.ai | 1,621Max WebDev Arena: 1,621
Source · LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset on Hugging Face), CC BY 4.0 | $0.29 Estimate at list prices
The list price of each token type, weighted by its share of the mix. Reasoning tokens are priced as output. Discounts, batch prices and long-context tiers are not applied. Not what anyone paid. | |
Gemini 3.8 Flash N21. Google | 123Up 8 from 115 active users in the previous 30 days. | Not evaluated on Epoch Capabilities Index | Not evaluated on Terminal-Bench 4.1 | Not evaluated on WebDev Arena | No list price on models.dev | |
Grok 4.722. xAI | 119Down 69 from 188 active users in the previous 30 days. | 156.2 Epoch Capabilities Index: 156.2
Source · Epoch AI, ‘Capabilities & benchmarking’, epoch.ai/benchmarks (CC BY 4.0) | 38.8%XHigh · Grok Build Terminal-Bench 4.1: 38.8%
Source · Terminal-Bench 4.1 official leaderboard, tbench.ai | 1,637XHigh WebDev Arena: 1,637
Source · LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset on Hugging Face), CC BY 4.0 | $0.57 Estimate at list prices
The list price of each token type, weighted by its share of the mix. Reasoning tokens are priced as output. Discounts, batch prices and long-context tiers are not applied. Not what anyone paid. No cache-write price is listed, so cache writes are priced as input. | |
GPT-5.6 Terra23. OpenAI | 114Down 250 from 364 active users in the previous 30 days. | 160.7 Epoch Capabilities Index: 160.7
Source · Epoch AI, ‘Capabilities & benchmarking’, epoch.ai/benchmarks (CC BY 4.0) | 21.5%Max · Codex Terminal-Bench 4.1: 21.5%
Source · Terminal-Bench 4.1 official leaderboard, tbench.ai | 1,522XHigh · Codex WebDev Arena: 1,522
Source · LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset on Hugging Face), CC BY 4.0 | $0.31 Estimate at list prices
The list price of each token type, weighted by its share of the mix. Reasoning tokens are priced as output. Discounts, batch prices and long-context tiers are not applied. Not what anyone paid. | |
DeepSeek Flash24. DeepSeek | 111Down 27 from 138 active users in the previous 30 days. | Not evaluated on Epoch Capabilities Index | Not evaluated on Terminal-Bench 4.1 | Not evaluated on WebDev Arena | No list price on models.dev | |
Claude Haiku 4.525. Anthropic | 93Down 321 from 414 active users in the previous 30 days. | 142.8 Epoch Capabilities Index: 142.8
Source · Epoch AI, ‘Capabilities & benchmarking’, epoch.ai/benchmarks (CC BY 4.0) | Not evaluated on Terminal-Bench 4.1 | 1,330 WebDev Arena: 1,330
Source · LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset on Hugging Face), CC BY 4.0 | $0.15 Estimate at list prices
The list price of each token type, weighted by its share of the mix. Reasoning tokens are priced as output. Discounts, batch prices and long-context tiers are not applied. Not what anyone paid. | |
DeepSeek V4.1 Flash 101726. DeepSeek | 83Up 80 from 3 active users in the previous 30 days. | 159.4 Epoch Capabilities Index: 159.4
Source · Epoch AI, ‘Capabilities & benchmarking’, epoch.ai/benchmarks (CC BY 4.0) | Not evaluated on Terminal-Bench 4.1 | Not evaluated on WebDev Arena | $0.01 Estimate at list prices
The list price of each token type, weighted by its share of the mix. Reasoning tokens are priced as output. Discounts, batch prices and long-context tiers are not applied. Not what anyone paid. No cache-write price is listed, so cache writes are priced as input. | |
Gemini 4 Argon27. Google | 79Up 34 from 45 active users in the previous 30 days. | 166.5 Epoch Capabilities Index: 166.5
Source · Epoch AI, ‘Capabilities & benchmarking’, epoch.ai/benchmarks (CC BY 4.0) | Not evaluated on Terminal-Bench 4.1 | 1,678High WebDev Arena: 1,678
Source · LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset on Hugging Face), CC BY 4.0 | $0.20 Estimate at list prices
The list price of each token type, weighted by its share of the mix. Reasoning tokens are priced as output. Discounts, batch prices and long-context tiers are not applied. Not what anyone paid. No cache-write price is listed, so cache writes are priced as input. | |
GLM-5.3 Flash Free28. Z.ai | 78Up 47 from 31 active users in the previous 30 days. | Not evaluated on Epoch Capabilities Index | Not evaluated on Terminal-Bench 4.1 | Not evaluated on WebDev Arena | No list price on models.dev | |
Gemini 3.8 Flash29. Google | 73Down 137 from 210 active users in the previous 30 days. | 158.8 Epoch Capabilities Index: 158.8
Source · Epoch AI, ‘Capabilities & benchmarking’, epoch.ai/benchmarks (CC BY 4.0) | 18.2%High · mini-SWE-agent Terminal-Bench 4.1: 18.2%
Source · Terminal-Bench 4.1 official leaderboard, tbench.ai | 1,585High WebDev Arena: 1,585
Source · LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset on Hugging Face), CC BY 4.0 | $0.11 Estimate at list prices
The list price of each token type, weighted by its share of the mix. Reasoning tokens are priced as output. Discounts, batch prices and long-context tiers are not applied. Not what anyone paid. No cache-write price is listed, so cache writes are priced as input. | |
Gemini 4 Argon Trial30. Google | 70Up 42 from 28 active users in the previous 30 days. | Not evaluated on Epoch Capabilities Index | Not evaluated on Terminal-Bench 4.1 | Not evaluated on WebDev Arena | No list price on models.dev | |
MiniMax M3.1 Flash Free31. MiniMax | 58NewNew: no active users in the previous 30 days, 58 now. | Not evaluated on Epoch Capabilities Index | Not evaluated on Terminal-Bench 4.1 | Not evaluated on WebDev Arena | No list price on models.dev | |
Kimi K332. Moonshot AI | 54Down 45 from 99 active users in the previous 30 days. | 158.6 Epoch Capabilities Index: 158.6
Source · Epoch AI, ‘Capabilities & benchmarking’, epoch.ai/benchmarks (CC BY 4.0) | Not evaluated on Terminal-Bench 4.1 | 1,655Max WebDev Arena: 1,655
Source · LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset on Hugging Face), CC BY 4.0 | $0.45 Estimate at list prices
The list price of each token type, weighted by its share of the mix. Reasoning tokens are priced as output. Discounts, batch prices and long-context tiers are not applied. Not what anyone paid. | |
Claude Opus 4.633. Anthropic | 52Down 61 from 113 active users in the previous 30 days. | 156.3 Epoch Capabilities Index: 156.3
Source · Epoch AI, ‘Capabilities & benchmarking’, epoch.ai/benchmarks (CC BY 4.0) | Not evaluated on Terminal-Bench 4.1 | 1,547High WebDev Arena: 1,547
Best of 2 reported results for this model. Source · LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset on Hugging Face), CC BY 4.0 | $0.77 Estimate at list prices
The list price of each token type, weighted by its share of the mix. Reasoning tokens are priced as output. Discounts, batch prices and long-context tiers are not applied. Not what anyone paid. | |
Claude Sonnet 4.634. Anthropic | 52Down 47 from 99 active users in the previous 30 days. | 152.9 Epoch Capabilities Index: 152.9
Source · Epoch AI, ‘Capabilities & benchmarking’, epoch.ai/benchmarks (CC BY 4.0) | Not evaluated on Terminal-Bench 4.1 | 1,523 WebDev Arena: 1,523
Source · LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset on Hugging Face), CC BY 4.0 | $0.46 Estimate at list prices
The list price of each token type, weighted by its share of the mix. Reasoning tokens are priced as output. Discounts, batch prices and long-context tiers are not applied. Not what anyone paid. | |
Beam Free35. Lab unknown | 49Up 36 from 13 active users in the previous 30 days. | Not evaluated on Epoch Capabilities Index | Not evaluated on Terminal-Bench 4.1 | Not evaluated on WebDev Arena | No list price on models.dev | |
DeepSeek V4 Pro36. DeepSeek | 48Down 27 from 75 active users in the previous 30 days. | 150.2 Epoch Capabilities Index: 150.2
Source · Epoch AI, ‘Capabilities & benchmarking’, epoch.ai/benchmarks (CC BY 4.0) | Not evaluated on Terminal-Bench 4.1 | 1,582High WebDev Arena: 1,582
Best of 2 reported results for this model. Source · LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset on Hugging Face), CC BY 4.0 | $1.75 Estimate at list prices
The list price of each token type, weighted by its share of the mix. Reasoning tokens are priced as output. Discounts, batch prices and long-context tiers are not applied. Not what anyone paid. No cache-read price is listed, so cache reads are priced as input. No cache-write price is listed, so cache writes are priced as input. | |
Kimi K3.1 Pro37. Moonshot AI | 47Up 46 from 1 active users in the previous 30 days. | 161.4 Epoch Capabilities Index: 161.4
Source · Epoch AI, ‘Capabilities & benchmarking’, epoch.ai/benchmarks (CC BY 4.0) | Not evaluated on Terminal-Bench 4.1 | Not evaluated on WebDev Arena | $0.30 Estimate at list prices
The list price of each token type, weighted by its share of the mix. Reasoning tokens are priced as output. Discounts, batch prices and long-context tiers are not applied. Not what anyone paid. | |
Muse Spark 1.3 Contributor38. Meta | 44Down 50 from 94 active users in the previous 30 days. | Not evaluated on Epoch Capabilities Index | Not evaluated on Terminal-Bench 4.1 | Not evaluated on WebDev Arena | No list price on models.dev | |
MiniMax M3.1 Flash39. MiniMax | 44NewNew: no active users in the previous 30 days, 44 now. | Not evaluated on Epoch Capabilities Index | Not evaluated on Terminal-Bench 4.1 | 1,587 WebDev Arena: 1,587
Source · LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset on Hugging Face), CC BY 4.0 | $0.02 Estimate at list prices
The list price of each token type, weighted by its share of the mix. Reasoning tokens are priced as output. Discounts, batch prices and long-context tiers are not applied. Not what anyone paid. No cache-write price is listed, so cache writes are priced as input. | |
Summaries40. Lab unknown | 42Down 8 from 50 active users in the previous 30 days. | Not evaluated on Epoch Capabilities Index | Not evaluated on Terminal-Bench 4.1 | Not evaluated on WebDev Arena | No list price on models.dev | |
DeepSeek V4 Flash41. DeepSeek | 41Down 73 from 114 active users in the previous 30 days. | 146.8 Epoch Capabilities Index: 146.8
Source · Epoch AI, ‘Capabilities & benchmarking’, epoch.ai/benchmarks (CC BY 4.0) | Not evaluated on Terminal-Bench 4.1 | 1,582High WebDev Arena: 1,582
Source · LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset on Hugging Face), CC BY 4.0 | $0.19 Estimate at list prices
The list price of each token type, weighted by its share of the mix. Reasoning tokens are priced as output. Discounts, batch prices and long-context tiers are not applied. Not what anyone paid. No cache-read price is listed, so cache reads are priced as input. No cache-write price is listed, so cache writes are priced as input. | |
Grok 4.642. xAI | 41Down 99 from 140 active users in the previous 30 days. | 157.8 Epoch Capabilities Index: 157.8
Source · Epoch AI, ‘Capabilities & benchmarking’, epoch.ai/benchmarks (CC BY 4.0) | 19.7%High · Grok Build Terminal-Bench 4.1: 19.7%
Source · Terminal-Bench 4.1 official leaderboard, tbench.ai | 1,617High WebDev Arena: 1,617
Source · LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset on Hugging Face), CC BY 4.0 | $0.57 Estimate at list prices
The list price of each token type, weighted by its share of the mix. Reasoning tokens are priced as output. Discounts, batch prices and long-context tiers are not applied. Not what anyone paid. No cache-write price is listed, so cache writes are priced as input. | |
Big Pickle43. Lab unknown | 41Down 18 from 59 active users in the previous 30 days. | Not evaluated on Epoch Capabilities Index | Not evaluated on Terminal-Bench 4.1 | Not evaluated on WebDev Arena | No list price on models.dev | |
Gemini 3.8 Flash Tiered44. Google | 38No change from 38 active users in the previous 30 days. | Not evaluated on Epoch Capabilities Index | Not evaluated on Terminal-Bench 4.1 | Not evaluated on WebDev Arena | No list price on models.dev | |
Claude Fable 545. Anthropic | 38Down 48 from 86 active users in the previous 30 days. | 164.1 Epoch Capabilities Index: 164.1
Source · Epoch AI, ‘Capabilities & benchmarking’, epoch.ai/benchmarks (CC BY 4.0) | 44.9%Max · Claude Code Terminal-Bench 4.1: 44.9%
Source · Terminal-Bench 4.1 official leaderboard, tbench.ai | 1,624High WebDev Arena: 1,624
Source · LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset on Hugging Face), CC BY 4.0 | $1.53 Estimate at list prices
The list price of each token type, weighted by its share of the mix. Reasoning tokens are priced as output. Discounts, batch prices and long-context tiers are not applied. Not what anyone paid. | |
MiMo V2.6 Flash Free46. Xiaomi | 38Down 51 from 89 active users in the previous 30 days. | Not evaluated on Epoch Capabilities Index | Not evaluated on Terminal-Bench 4.1 | Not evaluated on WebDev Arena | No list price on models.dev | |
K3.1 Pro47. Lab unknown | 32NewNew: no active users in the previous 30 days, 32 now. | Not evaluated on Epoch Capabilities Index | Not evaluated on Terminal-Bench 4.1 | Not evaluated on WebDev Arena | No list price on models.dev | |
MiMo V2.6 Pro48. Xiaomi | 28Down 33 from 61 active users in the previous 30 days. | Not evaluated on Epoch Capabilities Index | Not evaluated on Terminal-Bench 4.1 | 1,625 WebDev Arena: 1,625
Source · LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset on Hugging Face), CC BY 4.0 | $0.02 Estimate at list prices
The list price of each token type, weighted by its share of the mix. Reasoning tokens are priced as output. Discounts, batch prices and long-context tiers are not applied. Not what anyone paid. No cache-write price is listed, so cache writes are priced as input. | |
Grok 4.7 Build Fast49. xAI | 28Up 4 from 24 active users in the previous 30 days. | Not evaluated on Epoch Capabilities Index | Not evaluated on Terminal-Bench 4.1 | Not evaluated on WebDev Arena | No list price on models.dev | |
Nemotron 3.5 Super VL Free50. NVIDIA | 26Up 18 from 8 active users in the previous 30 days. | Not evaluated on Epoch Capabilities Index | Not evaluated on Terminal-Bench 4.1 | Not evaluated on WebDev Arena | No list price on models.dev | |
GPT Daybreak Blue Latest51. OpenAI | 23Down 12 from 35 active users in the previous 30 days. | Not evaluated on Epoch Capabilities Index | Not evaluated on Terminal-Bench 4.1 | Not evaluated on WebDev Arena | No list price on models.dev | |
Grok Bot Default52. xAI | 23Down 32 from 55 active users in the previous 30 days. | Not evaluated on Epoch Capabilities Index | Not evaluated on Terminal-Bench 4.1 | Not evaluated on WebDev Arena | No list price on models.dev | |
Muse Spark 1.353. Meta | 22Down 7 from 29 active users in the previous 30 days. | 158.2 Epoch Capabilities Index: 158.2
Source · Epoch AI, ‘Capabilities & benchmarking’, epoch.ai/benchmarks (CC BY 4.0) | 14.8%XHigh · Muse Code Terminal-Bench 4.1: 14.8%
Source · Terminal-Bench 4.1 official leaderboard, tbench.ai | 1,659Max WebDev Arena: 1,659
Best of 2 reported results for this model. Source · LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset on Hugging Face), CC BY 4.0 | $0.20 Estimate at list prices
The list price of each token type, weighted by its share of the mix. Reasoning tokens are priced as output. Discounts, batch prices and long-context tiers are not applied. Not what anyone paid. No cache-write price is listed, so cache writes are priced as input. | |
Gemini 4 Carbon54. Google | 21NewNew: no active users in the previous 30 days, 21 now. | 169.8 Epoch Capabilities Index: 169.8
Source · Epoch AI, ‘Capabilities & benchmarking’, epoch.ai/benchmarks (CC BY 4.0) | Not evaluated on Terminal-Bench 4.1 | Not evaluated on WebDev Arena | $0.20 Estimate at list prices
The list price of each token type, weighted by its share of the mix. Reasoning tokens are priced as output. Discounts, batch prices and long-context tiers are not applied. Not what anyone paid. No cache-write price is listed, so cache writes are priced as input. | |
MiniMax M355. MiniMax | 21Down 26 from 47 active users in the previous 30 days. | 147.7 Epoch Capabilities Index: 147.7
Source · Epoch AI, ‘Capabilities & benchmarking’, epoch.ai/benchmarks (CC BY 4.0) | Not evaluated on Terminal-Bench 4.1 | 1,482 WebDev Arena: 1,482
Source · LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset on Hugging Face), CC BY 4.0 | $0.07 Estimate at list prices
The list price of each token type, weighted by its share of the mix. Reasoning tokens are priced as output. Discounts, batch prices and long-context tiers are not applied. Not what anyone paid. No cache-write price is listed, so cache writes are priced as input. | |
Claude Opus 4.756. Anthropic | 21Down 49 from 70 active users in the previous 30 days. | 157.4 Epoch Capabilities Index: 157.4
Source · Epoch AI, ‘Capabilities & benchmarking’, epoch.ai/benchmarks (CC BY 4.0) | Not evaluated on Terminal-Bench 4.1 | 1,558High WebDev Arena: 1,558
Best of 2 reported results for this model. Source · LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset on Hugging Face), CC BY 4.0 | $0.77 Estimate at list prices
The list price of each token type, weighted by its share of the mix. Reasoning tokens are priced as output. Discounts, batch prices and long-context tiers are not applied. Not what anyone paid. | |
Claude Sonnet 4.557. Anthropic | 20Down 14 from 34 active users in the previous 30 days. | 147.6 Epoch Capabilities Index: 147.6
Source · Epoch AI, ‘Capabilities & benchmarking’, epoch.ai/benchmarks (CC BY 4.0) | Not evaluated on Terminal-Bench 4.1 | 1,394High WebDev Arena: 1,394
Best of 2 reported results for this model. Source · LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset on Hugging Face), CC BY 4.0 | $0.46 Estimate at list prices
The list price of each token type, weighted by its share of the mix. Reasoning tokens are priced as output. Discounts, batch prices and long-context tiers are not applied. Not what anyone paid. | |
Step 5 Preview58. StepFun | 20Down 7 from 27 active users in the previous 30 days. | Not evaluated on Epoch Capabilities Index | Not evaluated on Terminal-Bench 4.1 | 1,567High WebDev Arena: 1,567
Source · LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset on Hugging Face), CC BY 4.0 | $0.15 Estimate at list prices
The list price of each token type, weighted by its share of the mix. Reasoning tokens are priced as output. Discounts, batch prices and long-context tiers are not applied. Not what anyone paid. No cache-write price is listed, so cache writes are priced as input. | |
MiMo V2.6 Flash59. Xiaomi | 19Down 43 from 62 active users in the previous 30 days. | Not evaluated on Epoch Capabilities Index | Not evaluated on Terminal-Bench 4.1 | 1,634 WebDev Arena: 1,634
Source · LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset on Hugging Face), CC BY 4.0 | $0.009 Estimate at list prices
The list price of each token type, weighted by its share of the mix. Reasoning tokens are priced as output. Discounts, batch prices and long-context tiers are not applied. Not what anyone paid. No cache-write price is listed, so cache writes are priced as input. | |
Gemini 4 Hydrogen60. Google | 19NewNew: no active users in the previous 30 days, 19 now. | Not evaluated on Epoch Capabilities Index | Not evaluated on Terminal-Bench 4.1 | Not evaluated on WebDev Arena | No list price on models.dev |
- 1Claude Opus 5.5Anthropic
- Active users
- 711Down 103 from 814 active users in the previous 30 days.
- Top agent
Claude Code79%
- ECI
- 168.5
Epoch Capabilities Index: 168.5
- Model
- Claude Opus 5.5
- Listed as
- Claude Opus 5.5
- Conditions
- Not reported
- Interval
- 165.6–171.8
- Unit
- ECI
- Model released
- Sep 22, 2026
- Retrieved
- Nov 12, 2026
Source · Epoch AI, ‘Capabilities & benchmarking’, epoch.ai/benchmarks (CC BY 4.0)
- Terminal-Bench 4
- 65.8%Max · Claude Code
Terminal-Bench 4.1: 65.8%
- Model
- Claude Opus 5.5
- Listed as
- Opus 5.5
- Conditions
- Max · Claude Code
- Interval
- 62.6–68.9%
- Unit
- % resolved
- Published
- Nov 3, 2026
- Retrieved
- Nov 12, 2026
Source · Terminal-Bench 4.1 official leaderboard, tbench.ai
- WebDev Arena
- 1,807Max
WebDev Arena: 1,807
- Model
- Claude Opus 5.5
- Listed as
- Claude Opus 5.5 (Max)
- Conditions
- Max
- Interval
- 1793–1821
- Unit
- Arena score
- Published
- Oct 19, 2026
- Retrieved
- Oct 21, 2026
Source · LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset on Hugging Face), CC BY 4.0
- $/1M at agent mix
- $0.42
Estimate at list prices
- Estimate
- $0.42 per 1M tokens
- Mix
- the community token mix: Cache read 96%, Input 1.9%, Cache write 1.6%, Output 0.3%, Reasoning <0.1%
- List price
- Anthropic: input $4, output $20, cache read $0.20, cache write $5 per 1M
The list price of each token type, weighted by its share of the mix. Reasoning tokens are priced as output. Discounts, batch prices and long-context tiers are not applied. Not what anyone paid.
- 2GPT-6.1 SolOpenAI
- Active users
- 671Down 55 from 726 active users in the previous 30 days.
- Top agent
Codex CLI79%
- ECI
- 168.5
Epoch Capabilities Index: 168.5
- Model
- GPT-6.1 Sol
- Listed as
- GPT-6.1 Sol
- Conditions
- Not reported
- Interval
- 165.5–171.8
- Unit
- ECI
- Model released
- Sep 29, 2026
- Retrieved
- Nov 12, 2026
Source · Epoch AI, ‘Capabilities & benchmarking’, epoch.ai/benchmarks (CC BY 4.0)
- Terminal-Bench 4
- 60.9%Max · Codex
Terminal-Bench 4.1: 60.9%
- Model
- GPT-6.1 Sol
- Listed as
- GPT-6.1 Sol
- Conditions
- Max · Codex
- Interval
- 57.9–63.9%
- Unit
- % resolved
- Published
- Nov 3, 2026
- Retrieved
- Nov 12, 2026
Source · Terminal-Bench 4.1 official leaderboard, tbench.ai
- WebDev Arena
- 1,753Max
WebDev Arena: 1,753
- Model
- GPT-6.1 Sol
- Listed as
- GPT-6.1 Sol (Max)
- Conditions
- Max
- Interval
- 1740–1766
- Unit
- Arena score
- Published
- Oct 19, 2026
- Retrieved
- Oct 21, 2026
Source · LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset on Hugging Face), CC BY 4.0
- $/1M at agent mix
- $0.21
Estimate at list prices
- Estimate
- $0.21 per 1M tokens
- Mix
- the community token mix: Cache read 96%, Input 1.9%, Cache write 1.6%, Output 0.3%, Reasoning <0.1%
- List price
- OpenAI: input $2, output $10, cache read $0.10, cache write $2.50 per 1M
The list price of each token type, weighted by its share of the mix. Reasoning tokens are priced as output. Discounts, batch prices and long-context tiers are not applied. Not what anyone paid.
- 3GPT-6 AstraOpenAI
- Active users
- 562Down 248 from 810 active users in the previous 30 days.
- Top agent
Codex CLI85%
- ECI
- 169.0
Epoch Capabilities Index: 169.0
- Model
- GPT-6 Astra
- Listed as
- GPT-6 Astra
- Conditions
- Not reported
- Interval
- 166.1–172.3
- Unit
- ECI
- Model released
- Sep 3, 2026
- Retrieved
- Nov 12, 2026
Source · Epoch AI, ‘Capabilities & benchmarking’, epoch.ai/benchmarks (CC BY 4.0)
- Terminal-Bench 4
- 60.3%Max · Codex
Terminal-Bench 4.1: 60.3%
- Model
- GPT-6 Astra
- Listed as
- GPT-6 Astra
- Conditions
- Max · Codex
- Interval
- 57.5–63.1%
- Unit
- % resolved
- Published
- Nov 3, 2026
- Retrieved
- Nov 12, 2026
Best of 5 reported results for this model.
Source · Terminal-Bench 4.1 official leaderboard, tbench.ai
- WebDev Arena
- 1,774Max
WebDev Arena: 1,774
- Model
- GPT-6 Astra
- Listed as
- GPT-6 Astra (Max)
- Conditions
- Max
- Interval
- 1764–1784
- Unit
- Arena score
- Published
- Oct 19, 2026
- Retrieved
- Oct 21, 2026
Source · LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset on Hugging Face), CC BY 4.0
- $/1M at agent mix
- $1.53
Estimate at list prices
- Estimate
- $1.53 per 1M tokens
- Mix
- the community token mix: Cache read 96%, Input 1.9%, Cache write 1.6%, Output 0.3%, Reasoning <0.1%
- List price
- OpenAI: input $10, output $50, cache read $1, cache write $12.50 per 1M
The list price of each token type, weighted by its share of the mix. Reasoning tokens are priced as output. Discounts, batch prices and long-context tiers are not applied. Not what anyone paid.
- 4Claude Sonnet 5.5Anthropic
- Active users
- 554No change from 554 active users in the previous 30 days.
- Top agent
Claude Code72%
- ECI
- 166.6
Epoch Capabilities Index: 166.6
- Model
- Claude Sonnet 5.5
- Listed as
- Claude Sonnet 5.5
- Conditions
- Not reported
- Interval
- 163.8–169.6
- Unit
- ECI
- Model released
- Sep 28, 2026
- Retrieved
- Nov 12, 2026
Source · Epoch AI, ‘Capabilities & benchmarking’, epoch.ai/benchmarks (CC BY 4.0)
- Terminal-Bench 4
- 63.9%Max · Claude Code
Terminal-Bench 4.1: 63.9%
- Model
- Claude Sonnet 5.5
- Listed as
- Sonnet 5.5
- Conditions
- Max · Claude Code
- Interval
- 60.9–66.9%
- Unit
- % resolved
- Published
- Nov 3, 2026
- Retrieved
- Nov 12, 2026
Source · Terminal-Bench 4.1 official leaderboard, tbench.ai
- WebDev Arena
- 1,768XHigh
WebDev Arena: 1,768
- Model
- Claude Sonnet 5.5
- Listed as
- Claude Sonnet 5.5 (xHigh)
- Conditions
- XHigh
- Interval
- 1756–1781
- Unit
- Arena score
- Published
- Oct 19, 2026
- Retrieved
- Oct 21, 2026
Best of 2 reported results for this model.
Source · LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset on Hugging Face), CC BY 4.0
- $/1M at agent mix
- $0.21
Estimate at list prices
- Estimate
- $0.21 per 1M tokens
- Mix
- the community token mix: Cache read 96%, Input 1.9%, Cache write 1.6%, Output 0.3%, Reasoning <0.1%
- List price
- Anthropic: input $2, output $10, cache read $0.10, cache write $2.50 per 1M
The list price of each token type, weighted by its share of the mix. Reasoning tokens are priced as output. Discounts, batch prices and long-context tiers are not applied. Not what anyone paid.
- 5Claude Haiku 5.5Anthropic
- Active users
- 498Up 171 from 327 active users in the previous 30 days.
- Top agent
Claude Code80%
- ECI
- 160.4
Epoch Capabilities Index: 160.4
- Model
- Claude Haiku 5.5
- Listed as
- Claude Haiku 5.5
- Conditions
- Not reported
- Interval
- 158.3–162.9
- Unit
- ECI
- Model released
- Oct 7, 2026
- Retrieved
- Nov 12, 2026
Source · Epoch AI, ‘Capabilities & benchmarking’, epoch.ai/benchmarks (CC BY 4.0)
- Terminal-Bench 4
- Not evaluated on Terminal-Bench 4.1
- WebDev Arena
- 1,586High
WebDev Arena: 1,586
- Model
- Claude Haiku 5.5
- Listed as
- Claude Haiku 5.5 (High)
- Conditions
- High
- Interval
- 1575–1597
- Unit
- Arena score
- Published
- Oct 19, 2026
- Retrieved
- Oct 21, 2026
Source · LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset on Hugging Face), CC BY 4.0
- $/1M at agent mix
- $0.02
Estimate at list prices
- Estimate
- $0.02 per 1M tokens
- Mix
- the community token mix: Cache read 96%, Input 1.9%, Cache write 1.6%, Output 0.3%, Reasoning <0.1%
- List price
- Anthropic: input $0.10, output $0.50, cache read $0.01, cache write $0.13 per 1M
The list price of each token type, weighted by its share of the mix. Reasoning tokens are priced as output. Discounts, batch prices and long-context tiers are not applied. Not what anyone paid.
- 6GPT-6 LunaOpenAI
- Active users
- 425Down 150 from 575 active users in the previous 30 days.
- Top agent
Codex CLI83%
- ECI
- 156.4
Epoch Capabilities Index: 156.4
- Model
- GPT-6 Luna
- Listed as
- GPT-6 Luna
- Conditions
- Not reported
- Interval
- 154.4–158.5
- Unit
- ECI
- Model released
- Sep 22, 2026
- Retrieved
- Nov 12, 2026
Source · Epoch AI, ‘Capabilities & benchmarking’, epoch.ai/benchmarks (CC BY 4.0)
- Terminal-Bench 4
- 15.2%Max · Codex
Terminal-Bench 4.1: 15.2%
- Model
- GPT-6 Luna
- Listed as
- GPT-6 Luna
- Conditions
- Max · Codex
- Interval
- 12.5–17.8%
- Unit
- % resolved
- Published
- Nov 3, 2026
- Retrieved
- Nov 12, 2026
Source · Terminal-Bench 4.1 official leaderboard, tbench.ai
- WebDev Arena
- 1,578Max
WebDev Arena: 1,578
- Model
- GPT-6 Luna
- Listed as
- GPT-6 Luna (Max)
- Conditions
- Max
- Interval
- 1572–1584
- Unit
- Arena score
- Published
- Oct 19, 2026
- Retrieved
- Oct 21, 2026
Source · LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset on Hugging Face), CC BY 4.0
- $/1M at agent mix
- $0.02
Estimate at list prices
- Estimate
- $0.02 per 1M tokens
- Mix
- the community token mix: Cache read 96%, Input 1.9%, Cache write 1.6%, Output 0.3%, Reasoning <0.1%
- List price
- OpenAI: input $0.10, output $0.50, cache read $0.01, cache write $0.13 per 1M
The list price of each token type, weighted by its share of the mix. Reasoning tokens are priced as output. Discounts, batch prices and long-context tiers are not applied. Not what anyone paid.
- 7Claude Fable 5.1Anthropic
- Active users
- 353Down 167 from 520 active users in the previous 30 days.
- Top agent
Claude Code69%
- ECI
- 167.0
Epoch Capabilities Index: 167.0
- Model
- Claude Fable 5.1
- Listed as
- Claude Fable 5.1
- Conditions
- Not reported
- Interval
- 164.2–170.1
- Unit
- ECI
- Model released
- Sep 1, 2026
- Retrieved
- Nov 12, 2026
Source · Epoch AI, ‘Capabilities & benchmarking’, epoch.ai/benchmarks (CC BY 4.0)
- Terminal-Bench 4
- 57.6%XHigh · Claude Code
Terminal-Bench 4.1: 57.6%
- Model
- Claude Fable 5.1
- Listed as
- Fable 5.1
- Conditions
- XHigh · Claude Code
- Interval
- 54.3–60.9%
- Unit
- % resolved
- Published
- Nov 3, 2026
- Retrieved
- Nov 12, 2026
Best of 5 reported results for this model.
Source · Terminal-Bench 4.1 official leaderboard, tbench.ai
- WebDev Arena
- 1,743Max
WebDev Arena: 1,743
- Model
- Claude Fable 5.1
- Listed as
- Claude Fable 5.1 (Max)
- Conditions
- Max
- Interval
- 1734–1752
- Unit
- Arena score
- Published
- Oct 19, 2026
- Retrieved
- Oct 21, 2026
Source · LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset on Hugging Face), CC BY 4.0
- $/1M at agent mix
- $0.81
Estimate at list prices
- Estimate
- $0.81 per 1M tokens
- Mix
- the community token mix: Cache read 96%, Input 1.9%, Cache write 1.6%, Output 0.3%, Reasoning <0.1%
- List price
- Anthropic: input $10, output $50, cache read $0.25, cache write $12.50 per 1M
The list price of each token type, weighted by its share of the mix. Reasoning tokens are priced as output. Discounts, batch prices and long-context tiers are not applied. Not what anyone paid.
- 8Claude Fable 5.2Anthropic
- Active users
- 326Up 325 from 1 active users in the previous 30 days.
- Top agent
Claude Code72%
- ECI
- 173.4
Epoch Capabilities Index: 173.4
- Model
- Claude Fable 5.2
- Listed as
- Claude Fable 5.2
- Conditions
- Not reported
- Interval
- 169.9–177.5
- Unit
- ECI
- Model released
- Nov 9, 2026
- Retrieved
- Nov 12, 2026
Source · Epoch AI, ‘Capabilities & benchmarking’, epoch.ai/benchmarks (CC BY 4.0)
- Terminal-Bench 4
- Not evaluated on Terminal-Bench 4.1
- WebDev Arena
- Not evaluated on WebDev Arena
- $/1M at agent mix
- $0.65
Estimate at list prices
- Estimate
- $0.65 per 1M tokens
- Mix
- the community token mix: Cache read 96%, Input 1.9%, Cache write 1.6%, Output 0.3%, Reasoning <0.1%
- List price
- Anthropic: input $8, output $40, cache read $0.20, cache write $10 per 1M
The list price of each token type, weighted by its share of the mix. Reasoning tokens are priced as output. Discounts, batch prices and long-context tiers are not applied. Not what anyone paid.
- 9GPT-6.1 TerraOpenAI
- Active users
- 304Up 300 from 4 active users in the previous 30 days.
- Top agent
Codex CLI88%
- ECI
- 167.7
Epoch Capabilities Index: 167.7
- Model
- GPT-6.1 Terra
- Listed as
- GPT-6.1 Terra
- Conditions
- Not reported
- Interval
- 164.7–171.0
- Unit
- ECI
- Model released
- Oct 26, 2026
- Retrieved
- Nov 12, 2026
Source · Epoch AI, ‘Capabilities & benchmarking’, epoch.ai/benchmarks (CC BY 4.0)
- Terminal-Bench 4
- Not evaluated on Terminal-Bench 4.1
- WebDev Arena
- Not evaluated on WebDev Arena
- $/1M at agent mix
- $0.11
Estimate at list prices
- Estimate
- $0.11 per 1M tokens
- Mix
- the community token mix: Cache read 96%, Input 1.9%, Cache write 1.6%, Output 0.3%, Reasoning <0.1%
- List price
- OpenAI: input $1, output $5, cache read $0.05, cache write $1.25 per 1M
The list price of each token type, weighted by its share of the mix. Reasoning tokens are priced as output. Discounts, batch prices and long-context tiers are not applied. Not what anyone paid.
- 10Codex Auto ReviewOpenAI
- Active users
- 281Down 113 from 394 active users in the previous 30 days.
- Top agent
Codex CLI100%
- ECI
- Not evaluated on Epoch Capabilities Index
- Terminal-Bench 4
- Not evaluated on Terminal-Bench 4.1
- WebDev Arena
- Not evaluated on WebDev Arena
- $/1M at agent mix
- No list price on models.dev
- 11DeepSeek V4.1 FlashDeepSeek
- Active users
- 223Down 44 from 267 active users in the previous 30 days.
- Top agent
OpenCode31%
- ECI
- 156.7
Epoch Capabilities Index: 156.7
- Model
- DeepSeek V4.1 Flash
- Listed as
- DeepSeek V4.1 Flash
- Conditions
- Not reported
- Interval
- 154.8–158.8
- Unit
- ECI
- Model released
- Sep 9, 2026
- Retrieved
- Nov 12, 2026
Source · Epoch AI, ‘Capabilities & benchmarking’, epoch.ai/benchmarks (CC BY 4.0)
- Terminal-Bench 4
- Not evaluated on Terminal-Bench 4.1
- WebDev Arena
- 1,664Max
WebDev Arena: 1,664
- Model
- DeepSeek V4.1 Flash
- Listed as
- DeepSeek-V4.1-Flash-20261017 (Max)
- Conditions
- Max
- Interval
- 1650–1679
- Unit
- Arena score
- Published
- Oct 19, 2026
- Retrieved
- Oct 21, 2026
Best of 2 reported results for this model.
Source · LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset on Hugging Face), CC BY 4.0
- $/1M at agent mix
- $0.02
Estimate at list prices
- Estimate
- $0.02 per 1M tokens
- Mix
- the community token mix: Cache read 96%, Input 1.9%, Cache write 1.6%, Output 0.3%, Reasoning <0.1%
- List price
- Azure: input $0.30, output $1.20, cache read $0.006, cache write — per 1M
The list price of each token type, weighted by its share of the mix. Reasoning tokens are priced as output. Discounts, batch prices and long-context tiers are not applied. Not what anyone paid.
No cache-write price is listed, so cache writes are priced as input.
- 12Claude Opus 4.8Anthropic
- Active users
- 221Down 83 from 304 active users in the previous 30 days.
- Top agent
Claude Code99%
- ECI
- 159.9
Epoch Capabilities Index: 159.9
- Model
- Claude Opus 4.8
- Listed as
- Claude Opus 4.8
- Conditions
- Not reported
- Interval
- 157.9–162.2
- Unit
- ECI
- Model released
- May 28, 2026
- Retrieved
- Nov 12, 2026
Source · Epoch AI, ‘Capabilities & benchmarking’, epoch.ai/benchmarks (CC BY 4.0)
- Terminal-Bench 4
- 23.6%Max · Claude Code
Terminal-Bench 4.1: 23.6%
- Model
- Claude Opus 4.8
- Listed as
- Opus 4.8
- Conditions
- Max · Claude Code
- Interval
- 20.1–27.2%
- Unit
- % resolved
- Published
- Nov 3, 2026
- Retrieved
- Nov 12, 2026
Source · Terminal-Bench 4.1 official leaderboard, tbench.ai
- WebDev Arena
- 1,556High
WebDev Arena: 1,556
- Model
- Claude Opus 4.8
- Listed as
- Claude Opus 4.8 (High)
- Conditions
- High
- Interval
- 1550–1562
- Unit
- Arena score
- Published
- Oct 19, 2026
- Retrieved
- Oct 21, 2026
Best of 2 reported results for this model.
Source · LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset on Hugging Face), CC BY 4.0
- $/1M at agent mix
- $0.77
Estimate at list prices
- Estimate
- $0.77 per 1M tokens
- Mix
- the community token mix: Cache read 96%, Input 1.9%, Cache write 1.6%, Output 0.3%, Reasoning <0.1%
- List price
- Anthropic: input $5, output $25, cache read $0.50, cache write $6.25 per 1M
The list price of each token type, weighted by its share of the mix. Reasoning tokens are priced as output. Discounts, batch prices and long-context tiers are not applied. Not what anyone paid.
- 13GPT-6 SolOpenAI
- Active users
- 213Down 412 from 625 active users in the previous 30 days.
- Top agent
Codex CLI94%
- ECI
- 163.8
Epoch Capabilities Index: 163.8
- Model
- GPT-6 Sol
- Listed as
- GPT-6 Sol
- Conditions
- Not reported
- Interval
- 161.3–166.4
- Unit
- ECI
- Model released
- Sep 22, 2026
- Retrieved
- Nov 12, 2026
Source · Epoch AI, ‘Capabilities & benchmarking’, epoch.ai/benchmarks (CC BY 4.0)
- Terminal-Bench 4
- 50.3%Max · Codex
Terminal-Bench 4.1: 50.3%
- Model
- GPT-6 Sol
- Listed as
- GPT-6 Sol
- Conditions
- Max · Codex
- Interval
- 47.1–53.5%
- Unit
- % resolved
- Published
- Nov 3, 2026
- Retrieved
- Nov 12, 2026
Source · Terminal-Bench 4.1 official leaderboard, tbench.ai
- WebDev Arena
- 1,683Max
WebDev Arena: 1,683
- Model
- GPT-6 Sol
- Listed as
- GPT-6 Sol (Max)
- Conditions
- Max
- Interval
- 1673–1693
- Unit
- Arena score
- Published
- Oct 19, 2026
- Retrieved
- Oct 21, 2026
Source · LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset on Hugging Face), CC BY 4.0
- $/1M at agent mix
- $0.31
Estimate at list prices
- Estimate
- $0.31 per 1M tokens
- Mix
- the community token mix: Cache read 96%, Input 1.9%, Cache write 1.6%, Output 0.3%, Reasoning <0.1%
- List price
- OpenAI: input $2, output $10, cache read $0.20, cache write $2.50 per 1M
The list price of each token type, weighted by its share of the mix. Reasoning tokens are priced as output. Discounts, batch prices and long-context tiers are not applied. Not what anyone paid.
- 14GPT-5.6 SolOpenAI
- Active users
- 208Down 458 from 666 active users in the previous 30 days.
- Top agent
Codex CLI56%
- ECI
- 163.0
Epoch Capabilities Index: 163.0
- Model
- GPT-5.6 Sol
- Listed as
- GPT-5.6 Sol
- Conditions
- Not reported
- Interval
- 160.7–165.5
- Unit
- ECI
- Model released
- Jul 9, 2026
- Retrieved
- Nov 12, 2026
Source · Epoch AI, ‘Capabilities & benchmarking’, epoch.ai/benchmarks (CC BY 4.0)
- Terminal-Bench 4
- 38.5%Max · Codex
Terminal-Bench 4.1: 38.5%
- Model
- GPT-5.6 Sol
- Listed as
- GPT-5.6 Sol
- Conditions
- Max · Codex
- Interval
- 34.6–42.3%
- Unit
- % resolved
- Published
- Nov 3, 2026
- Retrieved
- Nov 12, 2026
Source · Terminal-Bench 4.1 official leaderboard, tbench.ai
- WebDev Arena
- 1,616XHigh · Codex
WebDev Arena: 1,616
- Model
- GPT-5.6 Sol
- Listed as
- GPT-5.6 Sol (xHigh, Codex Harness)
- Conditions
- XHigh · Codex
- Interval
- 1610–1622
- Unit
- Arena score
- Published
- Oct 19, 2026
- Retrieved
- Oct 21, 2026
Source · LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset on Hugging Face), CC BY 4.0
- $/1M at agent mix
- $0.61
Estimate at list prices
- Estimate
- $0.61 per 1M tokens
- Mix
- the community token mix: Cache read 96%, Input 1.9%, Cache write 1.6%, Output 0.3%, Reasoning <0.1%
- List price
- OpenAI: input $4, output $20, cache read $0.40, cache write $5 per 1M
The list price of each token type, weighted by its share of the mix. Reasoning tokens are priced as output. Discounts, batch prices and long-context tiers are not applied. Not what anyone paid.
- 15Claude Opus 5Anthropic
- Active users
- 168Down 453 from 621 active users in the previous 30 days.
- Top agent
Claude Code80%
- ECI
- 164.7
Epoch Capabilities Index: 164.7
- Model
- Claude Opus 5
- Listed as
- Claude Opus 5
- Conditions
- Not reported
- Interval
- 162.1–167.5
- Unit
- ECI
- Model released
- Jul 24, 2026
- Retrieved
- Nov 12, 2026
Source · Epoch AI, ‘Capabilities & benchmarking’, epoch.ai/benchmarks (CC BY 4.0)
- Terminal-Bench 4
- 53.3%XHigh · Claude Code
Terminal-Bench 4.1: 53.3%
- Model
- Claude Opus 5
- Listed as
- Opus 5
- Conditions
- XHigh · Claude Code
- Interval
- 50.2–56.4%
- Unit
- % resolved
- Published
- Nov 3, 2026
- Retrieved
- Nov 12, 2026
Best of 5 reported results for this model.
Source · Terminal-Bench 4.1 official leaderboard, tbench.ai
- WebDev Arena
- 1,689Max
WebDev Arena: 1,689
- Model
- Claude Opus 5
- Listed as
- Claude Opus 5 (Max)
- Conditions
- Max
- Interval
- 1683–1695
- Unit
- Arena score
- Published
- Oct 19, 2026
- Retrieved
- Oct 21, 2026
Best of 2 reported results for this model.
Source · LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset on Hugging Face), CC BY 4.0
- $/1M at agent mix
- $0.77
Estimate at list prices
- Estimate
- $0.77 per 1M tokens
- Mix
- the community token mix: Cache read 96%, Input 1.9%, Cache write 1.6%, Output 0.3%, Reasoning <0.1%
- List price
- Anthropic: input $5, output $25, cache read $0.50, cache write $6.25 per 1M
The list price of each token type, weighted by its share of the mix. Reasoning tokens are priced as output. Discounts, batch prices and long-context tiers are not applied. Not what anyone paid.
- 16GLM-5.3 FlashZ.ai
- Active users
- 158Down 87 from 245 active users in the previous 30 days.
- Top agent
Hermes Agent48%
- ECI
- 153.8
Epoch Capabilities Index: 153.8
- Model
- GLM-5.3 Flash
- Listed as
- GLM-5.3-Flash
- Conditions
- Not reported
- Interval
- 152.0–155.8
- Unit
- ECI
- Model released
- Aug 20, 2026
- Retrieved
- Nov 12, 2026
Source · Epoch AI, ‘Capabilities & benchmarking’, epoch.ai/benchmarks (CC BY 4.0)
- Terminal-Bench 4
- 35.4%No reasoning · Claude Code
Terminal-Bench 4.1: 35.4%
- Model
- GLM-5.3 Flash
- Listed as
- GLM-5.3-Flash
- Conditions
- No reasoning · Claude Code
- Interval
- 31.9–39.0%
- Unit
- % resolved
- Published
- Nov 3, 2026
- Retrieved
- Nov 12, 2026
Source · Terminal-Bench 4.1 official leaderboard, tbench.ai
- WebDev Arena
- 1,607
WebDev Arena: 1,607
- Model
- GLM-5.3 Flash
- Listed as
- GLM-5.3-Flash
- Conditions
- Not reported
- Interval
- 1600–1613
- Unit
- Arena score
- Published
- Oct 19, 2026
- Retrieved
- Oct 21, 2026
Source · LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset on Hugging Face), CC BY 4.0
- $/1M at agent mix
- $0.03
Estimate at list prices
- Estimate
- $0.03 per 1M tokens
- Mix
- the community token mix: Cache read 96%, Input 1.9%, Cache write 1.6%, Output 0.3%, Reasoning <0.1%
- List price
- Z.AI: input $0.15, output $0.50, cache read $0.03, cache write $0 per 1M
The list price of each token type, weighted by its share of the mix. Reasoning tokens are priced as output. Discounts, batch prices and long-context tiers are not applied. Not what anyone paid.
- 17DeepSeek V4.1 Flash FreeDeepSeek
- Active users
- 152Up 85 from 67 active users in the previous 30 days.
- Top agent
OpenCode40%
- ECI
- Not evaluated on Epoch Capabilities Index
- Terminal-Bench 4
- Not evaluated on Terminal-Bench 4.1
- WebDev Arena
- Not evaluated on WebDev Arena
- $/1M at agent mix
- No list price on models.dev
- 18GPT-5.6 LunaOpenAI
- Active users
- 144Down 354 from 498 active users in the previous 30 days.
- Top agent
Codex CLI83%
- ECI
- 156.7
Epoch Capabilities Index: 156.7
- Model
- GPT-5.6 Luna
- Listed as
- GPT-5.6 Luna
- Conditions
- Not reported
- Interval
- 154.8–158.7
- Unit
- ECI
- Model released
- Jul 9, 2026
- Retrieved
- Nov 12, 2026
Source · Epoch AI, ‘Capabilities & benchmarking’, epoch.ai/benchmarks (CC BY 4.0)
- Terminal-Bench 4
- 17.6%Max · Codex
Terminal-Bench 4.1: 17.6%
- Model
- GPT-5.6 Luna
- Listed as
- GPT-5.6 Luna
- Conditions
- Max · Codex
- Interval
- 14.7–20.5%
- Unit
- % resolved
- Published
- Nov 3, 2026
- Retrieved
- Nov 12, 2026
Source · Terminal-Bench 4.1 official leaderboard, tbench.ai
- WebDev Arena
- 1,518XHigh · Codex
WebDev Arena: 1,518
- Model
- GPT-5.6 Luna
- Listed as
- GPT-5.6 Luna (xHigh, Codex Harness)
- Conditions
- XHigh · Codex
- Interval
- 1512–1525
- Unit
- Arena score
- Published
- Oct 19, 2026
- Retrieved
- Oct 21, 2026
Source · LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset on Hugging Face), CC BY 4.0
- $/1M at agent mix
- $0.03
Estimate at list prices
- Estimate
- $0.03 per 1M tokens
- Mix
- the community token mix: Cache read 96%, Input 1.9%, Cache write 1.6%, Output 0.3%, Reasoning <0.1%
- List price
- OpenAI: input $0.20, output $1.20, cache read $0.02, cache write $0.25 per 1M
The list price of each token type, weighted by its share of the mix. Reasoning tokens are priced as output. Discounts, batch prices and long-context tiers are not applied. Not what anyone paid.
- 19Claude Sonnet 5Anthropic
- Active users
- 130Down 364 from 494 active users in the previous 30 days.
- Top agent
Claude Code89%
- ECI
- 156.9
Epoch Capabilities Index: 156.9
- Model
- Claude Sonnet 5
- Listed as
- Claude Sonnet 5
- Conditions
- Not reported
- Interval
- 154.8–159.2
- Unit
- ECI
- Model released
- Jun 30, 2026
- Retrieved
- Nov 12, 2026
Source · Epoch AI, ‘Capabilities & benchmarking’, epoch.ai/benchmarks (CC BY 4.0)
- Terminal-Bench 4
- 12.1%Max · Claude Code
Terminal-Bench 4.1: 12.1%
- Model
- Claude Sonnet 5
- Listed as
- Sonnet 5
- Conditions
- Max · Claude Code
- Interval
- 9.1–15.1%
- Unit
- % resolved
- Published
- Nov 3, 2026
- Retrieved
- Nov 12, 2026
Source · Terminal-Bench 4.1 official leaderboard, tbench.ai
- WebDev Arena
- 1,540High
WebDev Arena: 1,540
- Model
- Claude Sonnet 5
- Listed as
- Claude Sonnet 5 (High)
- Conditions
- High
- Interval
- 1534–1546
- Unit
- Arena score
- Published
- Oct 19, 2026
- Retrieved
- Oct 21, 2026
Source · LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset on Hugging Face), CC BY 4.0
- $/1M at agent mix
- $0.31
Estimate at list prices
- Estimate
- $0.31 per 1M tokens
- Mix
- the community token mix: Cache read 96%, Input 1.9%, Cache write 1.6%, Output 0.3%, Reasoning <0.1%
- List price
- Anthropic: input $2, output $10, cache read $0.20, cache write $2.50 per 1M
The list price of each token type, weighted by its share of the mix. Reasoning tokens are priced as output. Discounts, batch prices and long-context tiers are not applied. Not what anyone paid.
- 20GLM-5.3Z.ai
- Active users
- 128Down 55 from 183 active users in the previous 30 days.
- Top agent
Oh My Pi31%
- ECI
- 157.1
Epoch Capabilities Index: 157.1
- Model
- GLM-5.3
- Listed as
- GLM-5.3
- Conditions
- Not reported
- Interval
- 154.9–159.5
- Unit
- ECI
- Model released
- Aug 14, 2026
- Retrieved
- Nov 12, 2026
Source · Epoch AI, ‘Capabilities & benchmarking’, epoch.ai/benchmarks (CC BY 4.0)
- Terminal-Bench 4
- 41.2%Max · Claude Code
Terminal-Bench 4.1: 41.2%
- Model
- GLM-5.3
- Listed as
- GLM-5.3
- Conditions
- Max · Claude Code
- Interval
- 37.9–44.5%
- Unit
- % resolved
- Published
- Nov 3, 2026
- Retrieved
- Nov 12, 2026
Source · Terminal-Bench 4.1 official leaderboard, tbench.ai
- WebDev Arena
- 1,621Max
WebDev Arena: 1,621
- Model
- GLM-5.3
- Listed as
- GLM-5.3 (Max)
- Conditions
- Max
- Interval
- 1614–1629
- Unit
- Arena score
- Published
- Oct 19, 2026
- Retrieved
- Oct 21, 2026
Source · LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset on Hugging Face), CC BY 4.0
- $/1M at agent mix
- $0.29
Estimate at list prices
- Estimate
- $0.29 per 1M tokens
- Mix
- the community token mix: Cache read 96%, Input 1.9%, Cache write 1.6%, Output 0.3%, Reasoning <0.1%
- List price
- Z.AI: input $1.40, output $4.40, cache read $0.26, cache write $0 per 1M
The list price of each token type, weighted by its share of the mix. Reasoning tokens are priced as output. Discounts, batch prices and long-context tiers are not applied. Not what anyone paid.
Usage counts public Tokscale submissions only; hidden accounts are excluded. Scores are the best result each source reports for the model, with its effort and agent or harness; open a score for its source and date. Prices are list prices from models.dev, and every $/1M figure is an estimate at list prices, not what anyone paid. Usage and scores are shown side by side; one does not explain the other. Sorting by a score puts models that were not evaluated last.
Usage, capability and price
The models in the table that have an Epoch Capabilities Index. These charts put usage and scores side by side; they do not show that one causes the other.
ECI but no Tokscale usage in this period: GPT-5.5 Pro (162.7), GPT-5.4 Pro (160.2).
Show data
| Model | Active users | ECI |
|---|---|---|
| Claude Fable 5.2 | 326 | 173.4 |
| Gemini 4 Carbon | 21 | 169.8 |
| GPT-6 Astra | 562 | 169.0 |
| Claude Opus 5.5 | 711 | 168.5 |
| GPT-6.1 Sol | 671 | 168.5 |
| GPT-6.1 Terra | 304 | 167.7 |
| Claude Fable 5.1 | 353 | 167.0 |
| Claude Sonnet 5.5 | 554 | 166.6 |
| Gemini 4 Argon | 79 | 166.5 |
| Claude Opus 5 | 168 | 164.7 |
| Claude Fable 5 | 38 | 164.1 |
| GPT-6 Sol | 213 | 163.8 |
| GPT-5.6 Sol | 208 | 163.0 |
| GPT-5.5 Pro | No usage | 162.7 |
| Muse Wonder 1.0 | 16 | 161.7 |
| Kimi K3.1 Pro | 47 | 161.4 |
| GPT-5.6 Terra | 114 | 160.7 |
| Claude Haiku 5.5 | 498 | 160.4 |
| GPT-5.4 Pro | No usage | 160.2 |
| GPT-5.5 | 6 | 160.1 |
| Claude Opus 4.8 | 221 | 159.9 |
| DeepSeek V4.1 Flash 1017 | 83 | 159.4 |
| Gemini 3.8 Flash | 73 | 158.8 |
| Kimi K3 | 54 | 158.6 |
| Muse Spark 1.3 | 22 | 158.2 |
| Grok 4.6 | 41 | 157.8 |
| Qwen3.8 Max | 16 | 157.6 |
| Claude Opus 4.7 | 21 | 157.4 |
| GLM-5.3 | 128 | 157.1 |
| Claude Sonnet 5 | 130 | 156.9 |
| DeepSeek V4.1 Flash | 223 | 156.7 |
| GPT-5.6 Luna | 144 | 156.7 |
| GPT-6 Luna | 425 | 156.4 |
| Claude Opus 4.6 | 52 | 156.3 |
| Grok 4.7 | 119 | 156.2 |
| DeepSeek V4 Pro 0813 | 5 | 155.9 |
| Grok 4.5 | 9 | 155.0 |
| DeepSeek V4 Flash 0731 | 16 | 154.4 |
| GLM-5.3 Flash | 158 | 153.8 |
| GLM-5.2 | 12 | 153.0 |
| Claude Sonnet 4.6 | 52 | 152.9 |
| Qwen3.8 27B | 7 | 152.6 |
| Kimi K2.7 Code | 15 | 151.2 |
| DeepSeek V4 Pro | 48 | 150.2 |
| MiniMax M3 | 21 | 147.7 |
| Claude Sonnet 4.5 | 20 | 147.6 |
| DeepSeek V4 Flash | 41 | 146.8 |
| Gemini 3.5 Flash Lite | 14 | 145.6 |
| Gemini 3.1 Flash Lite | 6 | 145.0 |
| Claude Haiku 4.5 | 93 | 142.8 |
| Gemini 2.5 Flash | 9 | 140.8 |
| GPT OSS 120B | 5 | 140.2 |
| GPT-4.1 2025 04 14 | 5 | 136.2 |
| GPT-4.1 Mini 2025 04 14 | 5 | 134.2 |
Show data
| Model | Est. $/1M | ECI | Frontier |
|---|---|---|---|
| DeepSeek V4.1 Flash 1017 | $0.01 | 159.4 | Yes |
| Claude Haiku 5.5 | $0.02 | 160.4 | Yes |
| GPT-6 Luna | $0.02 | 156.4 | |
| DeepSeek V4.1 Flash | $0.02 | 156.7 | |
| GPT-5.6 Luna | $0.03 | 156.7 | |
| GLM-5.3 Flash | $0.03 | 153.8 | |
| DeepSeek V4 Flash 0731 | $0.04 | 154.4 | |
| Gemini 3.1 Flash Lite | $0.04 | 145.0 | |
| Qwen3.8 27B | $0.05 | 152.6 | |
| Gemini 3.5 Flash Lite | $0.05 | 145.6 | |
| Gemini 2.5 Flash | $0.05 | 140.8 | |
| DeepSeek V4 Pro 0813 | $0.05 | 155.9 | |
| MiniMax M3 | $0.07 | 147.7 | |
| GPT-6.1 Terra | $0.11 | 167.7 | Yes |
| Gemini 3.8 Flash | $0.11 | 158.8 | |
| GPT OSS 120B | $0.15 | 140.2 | |
| Claude Haiku 4.5 | $0.15 | 142.8 | |
| DeepSeek V4 Flash | $0.19 | 146.8 | |
| Gemini 4 Argon | $0.20 | 166.5 | |
| Gemini 4 Carbon | $0.20 | 169.8 | Yes |
| Muse Spark 1.3 | $0.20 | 158.2 | |
| GPT-6.1 Sol | $0.21 | 168.5 | |
| Claude Sonnet 5.5 | $0.21 | 166.6 | |
| Kimi K2.7 Code | $0.23 | 151.2 | |
| GLM-5.3 | $0.29 | 157.1 | |
| GLM-5.2 | $0.29 | 153.0 | |
| Kimi K3.1 Pro | $0.30 | 161.4 | |
| GPT-6 Sol | $0.31 | 163.8 | |
| Claude Sonnet 5 | $0.31 | 156.9 | |
| GPT-5.6 Terra | $0.31 | 160.7 | |
| Qwen3.8 Max | $0.34 | 157.6 | |
| Grok 4.5 | $0.38 | 155.0 | |
| Muse Wonder 1.0 | $0.40 | 161.7 | |
| Claude Opus 5.5 | $0.42 | 168.5 | |
| Kimi K3 | $0.45 | 158.6 | |
| Claude Sonnet 4.6 | $0.46 | 152.9 | |
| Claude Sonnet 4.5 | $0.46 | 147.6 | |
| Grok 4.7 | $0.57 | 156.2 | |
| Grok 4.6 | $0.57 | 157.8 | |
| GPT-5.6 Sol | $0.61 | 163.0 | |
| Claude Fable 5.2 | $0.65 | 173.4 | Yes |
| GPT-5.5 | $0.76 | 160.1 | |
| Claude Opus 4.8 | $0.77 | 159.9 | |
| Claude Opus 5 | $0.77 | 164.7 | |
| Claude Opus 4.6 | $0.77 | 156.3 | |
| Claude Opus 4.7 | $0.77 | 157.4 | |
| Claude Fable 5.1 | $0.81 | 167.0 | |
| GPT-6 Astra | $1.53 | 169.0 | |
| Claude Fable 5 | $1.53 | 164.1 | |
| DeepSeek V4 Pro | $1.75 | 150.2 | |
| GPT-5.5 Pro | $30.54 | 162.7 | |
| GPT-5.4 Pro | $30.54 | 160.2 |
Sources and attribution
Each score keeps its own source, unit and run conditions. Tokscale does not combine benchmarks into one score, and a missing score means the model was not evaluated, not that it scored zero.