Model rankings
1492 models · 5 boards · 2 sources
Smartest
Best open model
Best value
Best from China
Top three by Intelligence
GPT-6 Astra (max)OpenAI54.7
Claude Opus 5 (Adaptive Reasoning, Max Effort)Anthropic54.1
Top three open models
Kimi K3 (max)Kimi · #8 overall50.2
GLM-5.3 (max)Z AI · #9 overall48.6
Qwen3.8 2.4T A95BAlibaba · #15 overall46.7
This week's changes
Claude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback)Intelligence · #1New
GPT-6 Astra (max)Intelligence · #2New
MAI-Image-2.6Image · #2New
Realtime TTS-2Speech · #2New
Muse Spark 1.3 (max)Intelligence · #5New
| Rank | Change | Model | Intelligence | Price $/M | Speed tok/s | First token |
|---|---|---|---|---|---|---|
| 1 | New | Claude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback)ClosedAnthropic · 4 more variants | 56.8 | $20 | 68 | 272 s |
| 2 | New | GPT-6 Astra (max)ClosedOpenAI · 5 more variants | 54.7 | $20 | 64 | 355 s |
| 3 | ▼ 2 | Claude Opus 5 (Adaptive Reasoning, Max Effort)ClosedAnthropic · 4 more variants | 54.1 | $10 | 56 | 95 s |
| 4 | ▼ 2 | Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)ClosedAnthropic | 53.2 | $20 | 63 | 91 s |
| 5 | New | Muse Spark 1.3 (max)ClosedMeta · 1 more variant | 53.0 | $2.0 | 233 | 26 s |
| 6 | ▼ 3 | GPT-5.6 Sol (max)ClosedOpenAI · 5 more variants | 51.3 | $8.0 | 76 | 256 s |
| 7 | ▼ 3 | Claude Opus 4.8 (Adaptive Reasoning, Max Effort)ClosedAnthropic | 47.8 | $10 | 59 | 28 s |
| 8 | New | Gemini 3.8 Flash (high)ClosedGoogle · 2 more variants | 47.1 | $1.5 | 281 | 11 s |
| 9 | ▼ 4 | Muse Spark 1.2 (xhigh)ClosedMeta | 46.8 | $2.0 | 269 | 14 s |
| 10 | ▼ 4 | GPT-5.6 Terra (max)ClosedOpenAI · 5 more variants | 46.8 | $4.5 | 114 | 160 s |
| 11 | ▼ 4 | GPT-5.5 (xhigh)ClosedOpenAI · 4 more variants | 45.6 | $11 | 85 | 82 s |
| 12 | ▼ 4 | Gemini 3.7 Flash (high)ClosedGoogle · 2 more variants | 45.2 | $1.5 | 305 | 9.5 s |
| 13 | ▼ 4 | Claude Sonnet 5 (Adaptive Reasoning, Max Effort)ClosedAnthropic · 1 more variant | 45.1 | $4.0 | 75 | 185 s |
| 14 | ▼ 4 | Claude Opus 4.7 (Adaptive Reasoning, Max Effort)ClosedAnthropic · 1 more variant | 44.3 | $10 | 48 | 14 s |
| 15 | ▼ 2 | GPT-5.6 Luna (max)ClosedOpenAI · 5 more variants | 43.4 | $0.45 | 130 | 136 s |
| 16 | ▼ 4 | GPT-5.4 (xhigh)ClosedOpenAI · 2 more variants | 42.8 | $5.6 | 149 | 123 s |
| 17 | ▼ 6 | Muse Spark 1.1 (xhigh)ClosedMeta | 41.2 | $2.0 | — | — |
| 18 | ▼ 3 | Gemini 3.6 Flash (high)ClosedGoogle | 40.3 | $1.5 | 218 | 15 s |
| 19 | ▼ 5 | Gemini 3.5 Flash (high)ClosedGoogle · 2 more variants | 39.7 | $3.4 | 212 | 16 s |
| 20 | ▼ 4 | Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort)ClosedAnthropic · 2 more variants | 38.5 | $6.0 | 59 | 119 s |
| 21 | ▼ 3 | GPT-5.3 Codex (xhigh)ClosedOpenAI | 36.9 | $4.8 | 137 | 60 s |
| 22 | ▼ 5 | Gemini 3.1 Pro PreviewClosedGoogle | 36.7 | $4.5 | 116 | 25 s |
| 23 | ▼ 4 | Claude Opus 4.6 (Adaptive Reasoning, Max Effort)ClosedAnthropic · 1 more variant | 36.4 | $10 | 42 | 21 s |
| 24 | ▼ 4 | Muse SparkClosedMeta | 35.8 | — | — | — |
| 25 | ▼ 4 | GPT-5.2 (xhigh)ClosedOpenAI · 2 more variants | 35.0 | $4.8 | 83 | 148 s |
| 26 | ▼ 4 | Claude Opus 4.5 (Reasoning)ClosedAnthropic · 1 more variant | 33.6 | $10 | 56 | 17 s |
| 27 | ▼ 4 | GPT-5.2 Codex (xhigh)ClosedOpenAI | 33.0 | $4.8 | — | — |
| 28 | ▼ 3 | Gemini 3 Pro Preview (high)ClosedGoogle · 1 more variant | 32.4 | $4.5 | — | — |
| 29 | ▼ 5 | GPT-5.4 mini (xhigh)ClosedOpenAI · 2 more variants | 31.9 | $1.7 | 153 | 16 s |
| 30 | ▼ 4 | GPT-5.4 nano (xhigh)ClosedOpenAI · 2 more variants | 30.9 | $0.46 | 178 | 15 s |
| 31 | ▼ 4 | Gemini 3 Flash Preview (Reasoning)ClosedGoogle · 1 more variant | 30.7 | $1.1 | 217 | 5.6 s |
| 32 | ▼ 1 | GPT-5 Codex (high)ClosedOpenAI | 29.2 | $3.4 | — | — |
| 33 | ▼ 5 | GPT-5.1 (high)ClosedOpenAI · 1 more variant | 29.1 | $3.4 | 114 | 28 s |
| 34 | ▼ 4 | Claude 4.5 Sonnet (Reasoning)ClosedAnthropic · 1 more variant | 29.0 | $6.0 | 47 | 13 s |
| 35 | ▼ 3 | GPT-5.1 Codex (high)ClosedOpenAI | 27.9 | $3.4 | — | — |
| 36 | ▼ 7 | Gemini 3.5 Flash-LiteClosedGoogle | 27.6 | $0.85 | 338 | 7.2 s |
| 37 | ▼ 4 | GPT-5 (high)ClosedOpenAI · 4 more variants | 27.1 | $3.4 | 105 | 68 s |
| 38 | ▼ 4 | Claude 4.1 Opus (Reasoning)ClosedAnthropic · 1 more variant | 26.9 | $30 | — | — |
| 39 | ▼ 4 | GPT-5.5 Instant (May 2026)ClosedOpenAI · 1 more variant | 26.7 | $11 | — | — |
| 40 | ▼ 4 | o3-proClosedOpenAI | 25.7 | $35 | — | — |
| 41 | ▼ 4 | Claude 4 Opus (Reasoning)ClosedAnthropic · 1 more variant | 24.3 | $30 | — | — |
| 42 | ▼ 4 | GPT-5 mini (medium)ClosedOpenAI · 2 more variants | 24.2 | $0.69 | 101 | 18 s |
| 43 | ▼ 4 | GPT-5.1 Codex mini (high)ClosedOpenAI | 24.0 | $0.69 | — | — |
| 44 | ▼ 4 | o3ClosedOpenAI | 23.7 | $3.5 | 151 | 7.0 s |
| 45 | ▼ 4 | Claude 4.5 Haiku (Reasoning)ClosedAnthropic · 1 more variant | 22.5 | $2.0 | 93 | 21 s |
| 46 | ▼ 4 | Claude 4 Sonnet (Reasoning)ClosedAnthropic · 1 more variant | 22.2 | $6.0 | — | — |
| 47 | ▼ 4 | Claude 3.7 Sonnet (Reasoning)ClosedAnthropic · 1 more variant | 20.5 | — | — | — |
| 48 | ▼ 4 | o4-mini (high)ClosedOpenAI | 19.1 | $1.9 | 161 | 21 s |
| 49 | ▼ 4 | Gemini 2.5 ProClosedGoogle | 19.0 | $3.4 | 130 | 22 s |
| 50 | ▼ 4 | Gemini 3.1 Flash-LiteClosedGoogle | 18.7 | $0.56 | 305 | 5.3 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