Model rankings
1275 models · 5 boards · 2 sources
Smartest
Best open model
Best value
Best from China
Top three by Intelligence
Claude Opus 4.8 (Adaptive Reasoning, Max Effort)Anthropic61.4
GPT-5.5 (xhigh)OpenAI60.2
Top three open models
Kimi K2.6Kimi · #10 overall53.9
MiMo-V2.5-ProXiaomi · #11 overall53.8
DeepSeek V4 Pro (Reasoning, Max Effort)DeepSeek · #19 overall51.5
This week's changes
Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)Intelligence · #1New
claude-fable-5Coding · #1New
HiDream-O1-Image-1.5Image · #3New
MAI-Image-2.5-Flash (Foundry)Image · #8New
MAI-Image-2.5 (Foundry)Image · #12New
| Rank | Change | Model | Intelligence | Price $/M | Speed tok/s | First token |
|---|---|---|---|---|---|---|
| 1 | New | Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)ClosedAnthropic | 64.9 | $20 | 63 | 109 s |
| 2 | ▼ 1 | Claude Opus 4.8 (Adaptive Reasoning, Max Effort)ClosedAnthropic | 61.4 | $10 | 58 | 31 s |
| 3 | ▼ 1 | GPT-5.5 (xhigh)ClosedOpenAI · 4 more variants | 60.2 | $11 | 51 | 99 s |
| 4 | ▼ 1 | Claude Opus 4.7 (Adaptive Reasoning, Max Effort)ClosedAnthropic · 1 more variant | 57.3 | $10 | 47 | 18 s |
| 5 | ▼ 1 | Gemini 3.1 Pro PreviewClosedGoogle | 57.2 | $4.5 | 125 | 25 s |
| 6 | ▼ 1 | GPT-5.4 (xhigh)ClosedOpenAI · 2 more variants | 56.8 | $5.6 | 82 | 181 s |
| 7 | ▼ 1 | Qwen3.7 MaxClosedAlibaba | 56.6 | $3.8 | 171 | 2.5 s |
| 8 | ▼ 1 | Gemini 3.5 Flash (high)ClosedGoogle · 2 more variants | 55.3 | $3.4 | 158 | 19 s |
| 9 | ▼ 1 | MiniMax-M3ClosedMiniMax | 54.7 | $0.52 | 55 | 2.7 s |
| 10 | ▼ 1 | GPT-5.3 Codex (xhigh)ClosedOpenAI | 53.6 | $4.8 | 72 | 88 s |
| 11 | ▼ 1 | Qwen3.7 PlusClosedAlibaba | 53.3 | $0.59 | 53 | 2.1 s |
| 12 | ▼ 1 | Grok 4.3 (high)ClosedxAI · 3 more variants | 53.2 | $1.6 | 151 | 16 s |
| 13 | ▼ 1 | Claude Opus 4.6 (Adaptive Reasoning, Max Effort)ClosedAnthropic · 1 more variant | 52.9 | $10 | 40 | 11 s |
| 14 | ▼ 1 | Muse SparkClosedMeta | 52.2 | — | — | — |
| 15 | ▼ 1 | Qwen3.6 Max PreviewClosedAlibaba | 51.8 | $2.9 | 38 | 3.4 s |
| 16 | ▼ 1 | Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort)ClosedAnthropic · 2 more variants | 51.7 | $6.0 | 52 | 113 s |
| 17 | ▼ 1 | GPT-5.2 (xhigh)ClosedOpenAI · 2 more variants | 51.3 | $4.8 | 68 | 111 s |
| 18 | ▼ 1 | Qwen3.6 PlusClosedAlibaba | 50.0 | $1.1 | 52 | 3.1 s |
| 19 | ▼ 1 | Claude Opus 4.5 (Reasoning)ClosedAnthropic · 1 more variant | 49.7 | $10 | 46 | 18 s |
| 20 | ▼ 1 | Grok 4.20 0309 v2 (Reasoning)ClosedxAI · 1 more variant | 49.3 | $3.0 | 176 | 12 s |
| 21 | ▼ 1 | MiMo-V2-ProClosedXiaomi | 49.2 | $1.5 | 39 | 3.6 s |
| 22 | ▼ 1 | GPT-5.2 Codex (xhigh)ClosedOpenAI | 49.0 | $4.8 | 138 | 52 s |
| 23 | ▼ 1 | GPT-5.4 mini (xhigh)ClosedOpenAI · 2 more variants | 48.9 | $1.7 | 150 | 7.9 s |
| 24 | ▼ 1 | Grok 4.20 0309 (Reasoning)ClosedxAI · 1 more variant | 48.5 | $3.0 | 171 | 11 s |
| 25 | ▼ 1 | Gemini 3 Pro Preview (high)ClosedGoogle · 1 more variant | 48.4 | $4.5 | — | — |
| 26 | ▼ 1 | GPT-5.1 (high)ClosedOpenAI · 1 more variant | 47.7 | $3.4 | 105 | 36 s |
| 27 | ▼ 1 | GLM-5-TurboClosedZ AI | 46.8 | — | — | — |
| 28 | ▼ 1 | Gemini 3 Flash Preview (Reasoning)ClosedGoogle · 1 more variant | 46.4 | $1.1 | 166 | 7.8 s |
| 29 | ▼ 1 | MiMo-V2-Omni-0327ClosedXiaomi · 1 more variant | 44.9 | $0.80 | 84 | 3.2 s |
| 30 | ▼ 1 | GPT-5 Codex (high)ClosedOpenAI | 44.6 | $3.4 | 168 | 9.1 s |
| 31 | ▼ 1 | GPT-5 (high)ClosedOpenAI · 4 more variants | 44.6 | $3.4 | 84 | 66 s |
| 32 | ▼ 1 | GPT-5.4 nano (xhigh)ClosedOpenAI · 2 more variants | 44.0 | $0.46 | 149 | 4.1 s |
| 33 | ▼ 1 | GPT-5.1 Codex (high)ClosedOpenAI | 43.1 | $3.4 | 166 | 6.2 s |
| 34 | ▼ 1 | Claude 4.5 Sonnet (Reasoning)ClosedAnthropic · 1 more variant | 43.0 | $6.0 | 43 | 17 s |
| 35 | ▼ 1 | GLM 5V Turbo (Reasoning)ClosedZ AI | 42.9 | — | — | — |
| 36 | ▼ 1 | Claude 4.1 Opus (Reasoning)ClosedAnthropic · 1 more variant | 42.0 | $30 | 31 | 18 s |
| 37 | ▼ 1 | GPT-5.5 Instant (May 2026)ClosedOpenAI | 41.8 | $11 | — | — |
| 38 | ▼ 1 | Grok 4ClosedxAI | 41.5 | $11 | — | — |
| 39 | ▼ 1 | GPT-5 mini (high)ClosedOpenAI · 2 more variants | 41.2 | $0.69 | 93 | 82 s |
| 40 | ▼ 1 | o3-proClosedOpenAI | 40.7 | $35 | 28 | 94 s |
| 41 | ▼ 1 | Qwen3 Max ThinkingClosedAlibaba · 1 more variant | 39.8 | $2.4 | — | — |
| 42 | ▼ 1 | Claude 4 Opus (Reasoning)ClosedAnthropic · 1 more variant | 39.0 | $30 | 32 | 9.5 s |
| 43 | ▼ 1 | Claude 4 Sonnet (Reasoning)ClosedAnthropic · 1 more variant | 38.7 | $6.0 | 44 | 13 s |
| 44 | ▼ 1 | Qwen3.5 Omni PlusClosedAlibaba | 38.6 | $1.5 | 54 | 2.5 s |
| 45 | ▼ 1 | GPT-5.1 Codex mini (high)ClosedOpenAI | 38.6 | $0.69 | 213 | 6.7 s |
| 46 | ▼ 1 | Grok 4.1 Fast (Reasoning)ClosedxAI · 1 more variant | 38.6 | — | — | — |
| 47 | ▼ 1 | Step 3.5 Flash 2603ClosedStepFun | 38.5 | $0.15 | 223 | 1.1 s |
| 48 | ▼ 1 | o3ClosedOpenAI | 38.4 | $3.5 | 95 | 7.4 s |
| 49 | ▼ 1 | Claude 4.5 Haiku (Reasoning)ClosedAnthropic · 1 more variant | 37.1 | $2.0 | 98 | 18 s |
| 50 | ▼ 1 | JT-35B-FlashClosedChina Mobile | 36.1 | — | — | — |
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