Model rankings
1470 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
GLM-5.3 (max)Z AI · #6 overall59.5
Qwen3.8 2.4T A95BAlibaba · #8 overall57.7
This week's changes
gpt-6-astra-maxCoding · #1New
Wan 3.0Video · #1New
claude-fable-5.1-maxCoding · #2New
MAI-Image-2.6-PreviewImage · #2New
GLM-5.3-FlashIntelligence · #9New
| 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 | 53 | 62 s |
| 2 | — | Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)ClosedAnthropic | 62.1 | $20 | 67 | 100 s |
| 3 | — | GPT-5.6 Sol (max)ClosedOpenAI · 5 more variants | 60.9 | $8.0 | 79 | 116 s |
| 4 | — | Grok 4.6 (high)ClosedSpaceXAI · 3 more variants | 60.9 | $3.0 | 57 | 44 s |
| 5 | ▲ 1 | Qwen3.8 MaxClosedAlibaba | 58.1 | $3.0 | 38 | 2.5 s |
| 6 | ▲ 1 | Claude Opus 4.8 (Adaptive Reasoning, Max Effort)ClosedAnthropic | 57.3 | $10 | 57 | 42 s |
| 7 | ▲ 1 | Muse Spark 1.2 (xhigh)ClosedMeta | 56.8 | $2.0 | — | — |
| 8 | ▲ 1 | GPT-5.6 Terra (max)ClosedOpenAI · 5 more variants | 56.6 | $4.5 | 122 | 137 s |
| 9 | ▲ 1 | GPT-5.5 (xhigh)ClosedOpenAI · 4 more variants | 56.3 | $11 | 94 | 45 s |
| 10 | ▲ 1 | Gemini 3.7 Flash (high)ClosedGoogle · 2 more variants | 56.0 | $1.5 | 315 | 9.2 s |
| 11 | ▲ 1 | Grok 4.5 (high)ClosedSpaceXAI | 55.8 | $3.0 | 52 | 15 s |
| 12 | ▲ 1 | Claude Sonnet 5 (Adaptive Reasoning, Max Effort)ClosedAnthropic · 1 more variant | 55.3 | $4.0 | 75 | 200 s |
| 13 | ▲ 1 | Claude Opus 4.7 (Adaptive Reasoning, Max Effort)ClosedAnthropic · 1 more variant | 55.0 | $10 | 47 | 18 s |
| 14 | ▲ 1 | Muse Spark 1.1 (xhigh)ClosedMeta | 53.2 | $2.0 | 197 | 1.4 s |
| 15 | ▲ 1 | GPT-5.4 (xhigh)ClosedOpenAI · 2 more variants | 53.1 | $5.6 | 164 | 98 s |
| 16 | ▲ 1 | GPT-5.6 Luna (max)ClosedOpenAI · 5 more variants | 52.3 | $0.45 | 130 | 147 s |
| 17 | ▲ 1 | Gemini 3.5 Flash (high)ClosedGoogle · 2 more variants | 52.0 | $3.4 | 213 | 16 s |
| 18 | ▲ 1 | Gemini 3.6 Flash (high)ClosedGoogle | 51.6 | $1.5 | 173 | 17 s |
| 19 | New | DeepSeek V4 Flash Vision (Reasoning, Max Effort)ClosedDeepSeek | 51.5 | $0.66 | 113 | 1.2 s |
| 20 | New | Agnes 2.5 Pro BetaClosedSapiens AI | 49.1 | $0.15 | 150 | 2.3 s |
| 21 | ▼ 1 | Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort)ClosedAnthropic · 2 more variants | 48.4 | $6.0 | 68 | 121 s |
| 22 | ▼ 1 | Gemini 3.1 Pro PreviewClosedGoogle | 47.7 | $4.5 | 116 | 30 s |
| 23 | ▼ 1 | Qwen3.7 MaxClosedAlibaba | 46.7 | $3.8 | 205 | 2.2 s |
| 24 | ▼ 1 | GPT-5.3 Codex (xhigh)ClosedOpenAI | 45.5 | $4.8 | 132 | 41 s |
| 25 | ▼ 1 | Motif 3 (Beta)ClosedMotif Technologies | 45.3 | — | — | — |
| 26 | ▼ 1 | Claude Opus 4.6 (Adaptive Reasoning, Max Effort)ClosedAnthropic · 1 more variant | 44.9 | $10 | 40 | 21 s |
| 27 | ▼ 1 | Muse SparkClosedMeta | 44.3 | — | — | — |
| 28 | ▼ 1 | GPT-5.2 (xhigh)ClosedOpenAI · 2 more variants | 43.3 | $4.8 | 83 | 150 s |
| 29 | ▼ 1 | Claude Opus 4.5 (Reasoning)ClosedAnthropic · 1 more variant | 41.9 | $10 | 47 | 15 s |
| 30 | ▼ 1 | Solar Pro 4ClosedUpstage | 41.6 | $0.52 | 52 | 2.4 s |
| 31 | ▼ 1 | MiMo-V2-ProClosedXiaomi | 41.4 | — | — | — |
| 32 | ▼ 1 | GPT-5.2 Codex (xhigh)ClosedOpenAI | 41.2 | $4.8 | — | — |
| 33 | ▼ 1 | Qwen3.6 Max PreviewClosedAlibaba | 41.1 | $2.9 | 58 | 3.6 s |
| 34 | ▼ 1 | GPT-5.4 mini (xhigh)ClosedOpenAI · 2 more variants | 40.9 | $1.7 | 189 | 5.1 s |
| 35 | ▼ 1 | Grok Build 0.1 0616ClosedSpaceXAI | 40.7 | $1.3 | 54 | 0.5 s |
| 36 | ▼ 1 | Gemini 3 Pro Preview (high)ClosedGoogle · 1 more variant | 40.6 | $4.5 | — | — |
| 37 | ▼ 1 | Qwen3.6 PlusClosedAlibaba | 40.5 | $1.1 | 56 | 2.1 s |
| 38 | ▼ 1 | JT-4.1 Flash 236B A21BClosedChina Mobile | 39.9 | — | — | — |
| 39 | ▼ 1 | GPT-5.4 nano (xhigh)ClosedOpenAI · 2 more variants | 39.7 | $0.46 | 183 | 5.2 s |
| 40 | — | Qwen3.7 PlusClosedAlibaba | 39.4 | $0.70 | 56 | 2.1 s |
| 41 | — | GLM-5-TurboClosedZ AI | 39.1 | — | — | — |
| 42 | — | Gemini 3 Flash Preview (Reasoning)ClosedGoogle · 1 more variant | 38.7 | $1.1 | 179 | 6.0 s |
| 43 | — | Grok 4.20 0309 v2 (Reasoning)ClosedSpaceXAI · 1 more variant | 38.0 | $1.6 | 108 | 20 s |
| 44 | — | Grok 4.3 (high)ClosedSpaceXAI · 3 more variants | 37.9 | $1.6 | 121 | 20 s |
| 45 | — | GPT-5.1 (high)ClosedOpenAI · 1 more variant | 37.5 | $3.4 | 105 | 47 s |
| 46 | — | Gemini 3.5 Flash-LiteClosedGoogle | 37.4 | $0.85 | 358 | 9.2 s |
| 47 | — | Grok 4.20 0309 (Reasoning)ClosedSpaceXAI · 1 more variant | 37.4 | $3.0 | — | — |
| 48 | — | Claude 4.5 Sonnet (Reasoning)ClosedAnthropic · 1 more variant | 37.4 | $6.0 | 43 | 13 s |
| 49 | — | MiMo-V2-Omni-0327ClosedXiaomi · 1 more variant | 37.3 | — | — | — |
| 50 | — | GPT-5 Codex (high)ClosedOpenAI | 37.0 | $3.4 | — | — |
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