Model rankings
1356 models · 5 boards · 2 sources
Smartest
Best open model
Best value
Best from China
Top three by Intelligence
GPT-5.6 Sol (max)OpenAI58.9
Claude Opus 4.8 (Adaptive Reasoning, Max Effort)Anthropic55.7
Top three open models
GLM-5.2 (max)Z AI · #11 overall51.1
MiniMax-M3MiniMax · #17 overall44.4
DeepSeek V4 Pro (Reasoning, Max Effort)DeepSeek · #18 overall44.3
This week's changes
gpt-5.6-sol-xhigh (codex-harness)Coding · #1New
Simba 3.2Speech · #1New
GPT-5.6 Sol (max)Intelligence · #2New
GPT-5.6 Terra (max)Intelligence · #4New
Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)Image · #5New
| Rank | Change | Model | Intelligence | Price $/M | Speed tok/s | First token |
|---|---|---|---|---|---|---|
| 1 | — | Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)ClosedAnthropic | 59.9 | $20 | 59 | 113 s |
| 2 | New | GPT-5.6 Sol (max)ClosedOpenAI · 5 more variants | 58.9 | $11 | 73 | 154 s |
| 3 | ▼ 1 | Claude Opus 4.8 (Adaptive Reasoning, Max Effort)ClosedAnthropic | 55.7 | $10 | 58 | 29 s |
| 4 | New | GPT-5.6 Terra (max)ClosedOpenAI · 5 more variants | 55.0 | $5.6 | 140 | 154 s |
| 5 | ▼ 2 | GPT-5.5 (xhigh)ClosedOpenAI · 4 more variants | 54.8 | $11 | 66 | 99 s |
| 6 | New | Grok 4.5 (high)ClosedSpaceXAI | 53.8 | $3.0 | 93 | 14 s |
| 7 | ▼ 3 | Claude Opus 4.7 (Adaptive Reasoning, Max Effort)ClosedAnthropic · 1 more variant | 53.5 | $10 | 47 | 22 s |
| 8 | ▼ 3 | Claude Sonnet 5 (Adaptive Reasoning, Max Effort)ClosedAnthropic · 1 more variant | 53.4 | $4.0 | 79 | 212 s |
| 9 | ▼ 3 | GPT-5.4 (xhigh)ClosedOpenAI · 2 more variants | 51.4 | $5.6 | 149 | 107 s |
| 10 | New | GPT-5.6 Luna (max)ClosedOpenAI · 5 more variants | 51.2 | $2.3 | 204 | 100 s |
| 11 | New | Muse Spark 1.1 (xhigh)ClosedMeta | 50.6 | $2.0 | 116 | 1.0 s |
| 12 | ▼ 5 | Gemini 3.5 Flash (high)ClosedGoogle · 2 more variants | 50.2 | $3.4 | 158 | 24 s |
| 13 | ▼ 5 | Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort)ClosedAnthropic · 2 more variants | 47.2 | $6.0 | 54 | 114 s |
| 14 | ▼ 5 | Gemini 3.1 Pro PreviewClosedGoogle | 46.5 | $4.5 | 136 | 25 s |
| 15 | ▼ 5 | Qwen3.7 MaxClosedAlibaba | 46.0 | $3.8 | 194 | 2.5 s |
| 16 | ▼ 5 | GPT-5.3 Codex (xhigh)ClosedOpenAI | 44.3 | $4.8 | 77 | 79 s |
| 17 | ▼ 5 | Claude Opus 4.6 (Adaptive Reasoning, Max Effort)ClosedAnthropic · 1 more variant | 43.7 | $10 | 41 | 16 s |
| 18 | ▼ 5 | Muse SparkClosedMeta | 43.1 | — | — | — |
| 19 | ▼ 5 | GPT-5.2 (xhigh)ClosedOpenAI · 2 more variants | 42.2 | $4.8 | 61 | 108 s |
| 20 | ▼ 5 | Claude Opus 4.5 (Reasoning)ClosedAnthropic · 1 more variant | 40.8 | $10 | 47 | 16 s |
| 21 | ▼ 5 | MiMo-V2-ProClosedXiaomi | 40.3 | $1.5 | — | — |
| 22 | ▼ 5 | GPT-5.2 Codex (xhigh)ClosedOpenAI | 40.1 | $4.8 | 160 | 71 s |
| 23 | ▼ 5 | Qwen3.6 Max PreviewClosedAlibaba | 40.0 | $2.9 | 47 | 3.3 s |
| 24 | ▼ 5 | GPT-5.4 mini (xhigh)ClosedOpenAI · 2 more variants | 40.0 | $1.7 | 160 | 5.4 s |
| 25 | ▼ 5 | Grok Build 0.1 0616ClosedSpaceXAI | 39.8 | $1.3 | 66 | 0.5 s |
| 26 | ▼ 5 | Qwen3.6 PlusClosedAlibaba | 39.6 | $1.1 | 53 | 2.8 s |
| 27 | ▼ 5 | Gemini 3 Pro Preview (high)ClosedGoogle · 1 more variant | 39.6 | $4.5 | — | — |
| 28 | ▼ 5 | Qwen3.7 PlusClosedAlibaba | 39.0 | $0.70 | 51 | 3.1 s |
| 29 | New | JT-4.1 Flash 236B A21BClosedChina Mobile | 38.8 | — | — | — |
| 30 | ▼ 6 | GPT-5.4 nano (xhigh)ClosedOpenAI · 2 more variants | 38.2 | $0.46 | 173 | 4.8 s |
| 31 | ▼ 6 | GLM-5-TurboClosedZ AI | 38.1 | — | — | — |
| 32 | ▼ 6 | Gemini 3 Flash Preview (Reasoning)ClosedGoogle · 1 more variant | 37.8 | $1.1 | 152 | 7.1 s |
| 33 | ▼ 6 | Grok 4.3 (high)ClosedSpaceXAI · 3 more variants | 37.6 | $1.6 | 108 | 24 s |
| 34 | ▼ 6 | Grok 4.20 0309 v2 (Reasoning)ClosedSpaceXAI · 1 more variant | 37.0 | $3.0 | 165 | 12 s |
| 35 | ▼ 6 | GPT-5.1 (high)ClosedOpenAI · 1 more variant | 36.9 | $3.4 | 95 | 45 s |
| 36 | ▼ 6 | Grok 4.20 0309 (Reasoning)ClosedSpaceXAI · 1 more variant | 36.5 | $3.0 | — | — |
| 37 | ▼ 6 | Claude 4.5 Sonnet (Reasoning)ClosedAnthropic · 1 more variant | 36.4 | $6.0 | 42 | 12 s |
| 38 | ▼ 6 | MiMo-V2-Omni-0327ClosedXiaomi · 1 more variant | 36.4 | $0.80 | — | — |
| 39 | ▼ 6 | GPT-5 Codex (high)ClosedOpenAI | 36.1 | $3.4 | 177 | 8.4 s |
| 40 | New | KAT Coder Pro V2ClosedKwaiKAT | 35.4 | $0.52 | — | — |
| 41 | ▼ 6 | GPT-5.1 Codex (high)ClosedOpenAI | 34.7 | $3.4 | 167 | 6.1 s |
| 42 | ▼ 8 | GPT-5 (high)ClosedOpenAI · 4 more variants | 34.7 | $3.4 | 81 | 76 s |
| 43 | New | KAT-Coder-Pro V1ClosedKwaiKAT | 34.6 | $0.52 | 107 | 1.5 s |
| 44 | ▼ 8 | GLM 5V Turbo (Reasoning)ClosedZ AI | 34.5 | — | — | — |
| 45 | ▼ 8 | Claude 4.1 Opus (Reasoning)ClosedAnthropic · 1 more variant | 33.7 | $30 | 29 | 11 s |
| 46 | ▼ 8 | GPT-5.5 Instant (May 2026)ClosedOpenAI · 1 more variant | 33.5 | $11 | — | — |
| 47 | ▼ 8 | Grok 4ClosedSpaceXAI | 33.3 | $11 | — | — |
| 48 | ▼ 8 | o3-proClosedOpenAI | 32.5 | $35 | 33 | 77 s |
| 49 | ▼ 8 | Qwen3 Max ThinkingClosedAlibaba · 1 more variant | 31.7 | — | — | — |
| 50 | ▼ 8 | Claude 4 Opus (Reasoning)ClosedAnthropic · 1 more variant | 31.0 | $30 | — | — |
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