Model rankings
1447 models · 5 boards · 2 sources
Smartest
Best open model
Best value
Best from China
Top three by Intelligence
Claude Opus 5 (Adaptive Reasoning, Max Effort)Anthropic63.1
GPT-5.6 Sol (max)OpenAI60.9
Top three open models
Kimi K3 (max)Kimi · #5 overall59.7
Qwen3.8 2.4T A95BAlibaba · #8 overall57.7
DeepSeek V4 Pro 0813 (Reasoning, Max Effort)DeepSeek · #18 overall53.2
This week's changes
hy4-previewCoding · #5New
GLM-5.3 (max)Intelligence · #6New
MAI-Image-2.5-ProImage · #7New
qwen3.8-flash-nextCoding · #8New
glm-5.3-flashCoding · #11New
| Rank | Change | Model | Intelligence | Price $/M | Speed tok/s | First token |
|---|---|---|---|---|---|---|
| 1 | — | Claude Opus 5 (Adaptive Reasoning, Max Effort)ClosedAnthropic · 4 more variants | 63.1 | $10 | 59 | 52 s |
| 2 | — | Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)ClosedAnthropic | 62.1 | $20 | 71 | 133 s |
| 3 | — | GPT-5.6 Sol (max)ClosedOpenAI · 5 more variants | 60.9 | $11 | 72 | 146 s |
| 4 | — | Claude Opus 4.8 (Adaptive Reasoning, Max Effort)ClosedAnthropic | 57.3 | $10 | 61 | 27 s |
| 5 | — | Muse Spark 1.2 (xhigh)ClosedMeta | 56.8 | $2.0 | — | — |
| 6 | — | GPT-5.6 Terra (max)ClosedOpenAI · 5 more variants | 56.6 | $4.5 | 121 | 159 s |
| 7 | — | GPT-5.5 (xhigh)ClosedOpenAI · 4 more variants | 56.3 | $11 | 91 | 61 s |
| 8 | — | Gemini 3.7 Flash (high)ClosedGoogle · 2 more variants | 56.0 | $1.5 | 348 | 12 s |
| 9 | — | Claude Sonnet 5 (Adaptive Reasoning, Max Effort)ClosedAnthropic · 1 more variant | 55.3 | $4.0 | 81 | 172 s |
| 10 | — | Claude Opus 4.7 (Adaptive Reasoning, Max Effort)ClosedAnthropic · 1 more variant | 55.0 | $10 | 53 | 16 s |
| 11 | — | Muse Spark 1.1 (xhigh)ClosedMeta | 53.2 | $2.0 | 196 | 1.5 s |
| 12 | — | GPT-5.4 (xhigh)ClosedOpenAI · 2 more variants | 53.1 | $5.6 | 126 | 134 s |
| 13 | — | GPT-5.6 Luna (max)ClosedOpenAI · 5 more variants | 52.3 | $0.45 | 140 | 146 s |
| 14 | — | Gemini 3.5 Flash (high)ClosedGoogle · 2 more variants | 52.0 | $3.4 | 207 | 16 s |
| 15 | — | Gemini 3.6 Flash (high)ClosedGoogle | 51.6 | $1.5 | 208 | 14 s |
| 16 | — | Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort)ClosedAnthropic · 2 more variants | 48.4 | $6.0 | 56 | 124 s |
| 17 | — | Gemini 3.1 Pro PreviewClosedGoogle | 47.7 | $4.5 | 124 | 29 s |
| 18 | — | GPT-5.3 Codex (xhigh)ClosedOpenAI | 45.5 | $4.8 | 138 | 59 s |
| 19 | — | Claude Opus 4.6 (Adaptive Reasoning, Max Effort)ClosedAnthropic · 1 more variant | 44.9 | $10 | 47 | 22 s |
| 20 | — | Muse SparkClosedMeta | 44.3 | — | — | — |
| 21 | — | GPT-5.2 (xhigh)ClosedOpenAI · 2 more variants | 43.3 | $4.8 | 82 | 141 s |
| 22 | — | Claude Opus 4.5 (Reasoning)ClosedAnthropic · 1 more variant | 41.9 | $10 | 57 | 16 s |
| 23 | — | GPT-5.2 Codex (xhigh)ClosedOpenAI | 41.2 | $4.8 | — | — |
| 24 | — | GPT-5.4 mini (xhigh)ClosedOpenAI · 2 more variants | 40.9 | $1.7 | 187 | 8.5 s |
| 25 | — | Gemini 3 Pro Preview (high)ClosedGoogle · 1 more variant | 40.6 | $4.5 | — | — |
| 26 | — | GPT-5.4 nano (xhigh)ClosedOpenAI · 2 more variants | 39.7 | $0.46 | 184 | 3.7 s |
| 27 | — | Gemini 3 Flash Preview (Reasoning)ClosedGoogle · 1 more variant | 38.7 | $1.1 | 189 | 7.3 s |
| 28 | — | GPT-5.1 (high)ClosedOpenAI · 1 more variant | 37.5 | $3.4 | 116 | 38 s |
| 29 | — | Gemini 3.5 Flash-LiteClosedGoogle | 37.4 | $0.85 | 373 | 8.7 s |
| 30 | — | Claude 4.5 Sonnet (Reasoning)ClosedAnthropic · 1 more variant | 37.4 | $6.0 | 52 | 10 s |
| 31 | — | GPT-5 Codex (high)ClosedOpenAI | 37.0 | $3.4 | — | — |
| 32 | — | GPT-5.1 Codex (high)ClosedOpenAI | 35.6 | $3.4 | — | — |
| 33 | — | GPT-5 (high)ClosedOpenAI · 4 more variants | 35.3 | $3.4 | 107 | 68 s |
| 34 | — | Claude 4.1 Opus (Reasoning)ClosedAnthropic · 1 more variant | 34.5 | $30 | — | — |
| 35 | — | GPT-5.5 Instant (May 2026)ClosedOpenAI · 1 more variant | 34.3 | $11 | — | — |
| 36 | — | o3-proClosedOpenAI | 33.3 | $35 | — | — |
| 37 | — | Claude 4 Opus (Reasoning)ClosedAnthropic · 1 more variant | 31.7 | $30 | — | — |
| 38 | — | GPT-5 mini (medium)ClosedOpenAI · 2 more variants | 31.6 | $0.69 | 118 | 15 s |
| 39 | — | GPT-5.1 Codex mini (high)ClosedOpenAI | 31.3 | $0.69 | — | — |
| 40 | — | o3ClosedOpenAI | 31.1 | $3.5 | 161 | 6.4 s |
| 41 | — | Claude 4.5 Haiku (Reasoning)ClosedAnthropic · 1 more variant | 29.9 | $2.0 | 118 | 24 s |
| 42 | — | Claude 4 Sonnet (Reasoning)ClosedAnthropic · 1 more variant | 29.8 | $6.0 | — | — |
| 43 | — | Claude 3.7 Sonnet (Reasoning)ClosedAnthropic · 1 more variant | 27.6 | — | — | — |
| 44 | — | o4-mini (high)ClosedOpenAI | 26.1 | $1.9 | 175 | 27 s |
| 45 | — | Gemini 2.5 ProClosedGoogle | 25.9 | $3.4 | 137 | 19 s |
| 46 | — | Gemini 3.1 Flash-LiteClosedGoogle | 25.6 | $0.56 | 334 | 5.4 s |
| 47 | — | Gemini 2.5 Flash Preview (Sep '25) (Reasoning)ClosedGoogle · 3 more variants | 24.2 | — | — | — |
| 48 | — | o1ClosedOpenAI · 1 more variant | 23.9 | $26 | — | — |
| 49 | — | Gemini 2.5 Pro Preview (Mar' 25)ClosedGoogle · 1 more variant | 23.4 | — | — | — |
| 50 | — | Nova 2.0 Pro Preview (medium)ClosedAmazon · 2 more variants | 22.1 | $3.4 | 124 | 16 s |
Intelligence over time
Gained most · Anthropic +57.2Highest now · Anthropic 64.6Gap between highest and lowest 18.1 ptsTime range Nov 2025 – Nov 2026
64.6Anthropic60.0Google56.9OpenAI50.1Meta46.5Kimi