Find a model
Most choices start from constraints rather than a ranking: a budget, a wait you can live with, a licence you need, one thing the model has to be good at. Set those and the shortlist ranks on the skill you asked for, not on the overall index.
443 ranked models · data as of 21 Oct 2026
Good at
Costs at most
Runs at least
Answers within
Context of
And
443 models match, highest index is Claude Opus 5.5 at 72.7 for $8.00 per million tokens.
| # | Model | Index | Price $/M | Speed | First answer | Context |
|---|---|---|---|---|---|---|
| 1 |  Claude Opus 5.5maxAnthropic | 72.7±6 | $8.00 | 95 | 609 s | 1M |
| 2 |  Gemini 4 ArgonhighGoogle | 71.0±3 | $4.00 | 83 | 49 s | 1.0M |
| 3 |  Muse Wonder FullmaxMeta | 70.7±9 | – | – | – | 1M |
| 4 |  GPT-6 AstramaxOpenAI | 70.6±4 | $20.00 | 64 | 328 s | 1.1M |
| 5 | Claude Fable 5.1maxAnthropic | 70.6±5 | $20.00 | 69 | 221 s | 1M |
| 6 | GPT-6.1 SolmaxOpenAI | 70.0±3 | $4.00 | 55 | 248 s | 1.1M |
| 7 | Claude Sonnet 5.5maxAnthropic | 69.5±5 | $4.00 | 137 | 428 s | 1M |
| 8 | Claude Fable 5maxAnthropic | 69.4±4 | $20.00 | 67 | 75 s | 1M |
| 9 | Claude Opus 5maxAnthropic | 68.9±3 | $10.00 | 54 | 69 s | 1M |
| 10 | GPT-5.6 SolmaxOpenAI | 68.0±4 | $8.00 | 84 | 93 s | 1.1M |
| 11 | Muse WondermaxMeta | 67.5±5 | $8.00 | 161 | 45 s | 1.0M |
| 12 | Muse Spark 1.3maxMeta | 67.2±4 | $2.00 | 128 | 80 s | 1.0M |
| 13 | GPT-6 SolmaxOpenAI | 66.6±4 | $4.00 | 118 | 90 s | 1.1M |
| 14 | GPT-5.5xhighOpenAI | 66.1±4 | $11.25 | 92 | 52 s | 1.1M |
| 15 | GPT-5.5 ProxhighOpenAI | 65.3±8 | $67.50 | 23 | 4.35 s | 1.1M |
| 16 |  Kimi K3maxMoonshot AIopen | 64.9±3 | $6.00 | 42 | 52 s | 1.0M |
| 17 | GPT-5.4xhighOpenAI | 64.8±3 | $5.63 | 112 | 134 s | 1.1M |
| 18 | Gemini 3.8 FlashhighGoogle | 64.5±4 | $1.50 | 144 | 26 s | 1.0M |
| 19 | Muse SparkMeta | 64.4±3 | – | – | – | 262k |
| 20 | GPT-5.6 TerramaxOpenAI | 64.4±5 | $4.50 | 133 | 128 s | 1.1M |
| 21 |  MiMo-V2.6-ProXiaomiopen | 64.2±4 | $0.548 | 50 | 43 s | 1.0M |
| 22 |  Grok 4.6mediumSpaceXAI | 64.2±4 | $3.00 | 68 | 31 s | 500k |
| 23 | Grok 4.7highSpaceXAI | 64.0±7 | $3.00 | 87 | 33 s | 500k |
| 24 | GPT-5.3-CodexxhighOpenAI | 63.8±5 | $4.81 | 120 | 58 s | 400k |
| 25 |  GLM 5.3maxZhipu AIopen | 63.6±3 | $2.15 | 84 | 26 s | 1M |
| 26 | Gemini 3.7 FlashhighGoogle | 63.5±4 | $0.755 | 80 | 2.48 s | 1.0M |
| 27 | GPT-5.4 ProOpenAI | 63.5±3 | $67.50 | 10 | 6.11 s | 1.1M |
| 28 | Claude Opus 4.7Anthropic | 63.4±3 | $10.00 | 60 | 1.23 s | 1M |
| 29 | Claude Opus 4.8maxAnthropic | 63.4±5 | $10.00 | 63 | 45 s | 1M |
| 30 |  Qwen3.8 MaxmaxAlibaba | 63.3±4 | $3.00 | 40 | 53 s | 1M |
| 31 | Gemini 3.5 FlashhighGoogle | 63.2±3 | $3.38 | 208 | 15 s | 1.0M |
| 32 | Muse Spark 1.2xhighMeta | 63.2±5 | $2.00 | 315 | 22 s | 1.0M |
| 33 | Qwen3.8 2.4T A95BAlibabaopen | 63.2±5 | $3.00 | 42 | 51 s | 1M |
| 34 |  DeepSeek V4.1 Flash 1017maxDeepSeekopen | 63.1±7 | $0.525 | 209 | 11 s | 1.0M |
| 35 | Muse Spark 1.1Meta | 62.9±6 | $2.00 | 236 | 1.68 s | 1.0M |
| 36 | Claude Opus 4.6highAnthropic | 62.9±2 | $10.00 | 40 | 1.21 s | 1M |
| 37 | GLM 5.3 FlashZhipu AIopen | 62.8±4 | $0.238 | 77 | 29 s | 1M |
| 38 | DeepSeek V4 PromaxDeepSeekopen | 62.7±3 | $1.98 | 103 | 47 s | 1.0M |
| 39 | GLM 5.2maxZhipu AIopen | 62.4±4 | $2.15 | 88 | 26 s | 1M |
| 40 | Qwen3.6 MaxmaxAlibaba | 62.4±3 | $2.96 | – | – | 246k |
Category scores are on the same scale as the index: 50 is the average evaluated model and 15 points is one standard deviation. A model only appears under a skill if it has been measured on benchmarks in that category.