Model rankings
1432 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 · #7 overall57.7
DeepSeek V4 Pro 0813 (Reasoning, Max Effort)DeepSeek · #17 overall53.2
This week's changes
Sonic 3.6Speech · #1New
Grok 4.6 (high)Intelligence · #4New
Qwen3.8 2.4T A95BIntelligence · #7New
glm-5.3-maxCoding · #8New
Qwen-Image-3.0-ProImage · #8New
| Rank | Change | Model | Intelligence | Price $/M | Speed tok/s | First token |
|---|---|---|---|---|---|---|
| 1 | — | Kimi K3 (max)OpenKimi · 1 more variant | 59.7 | $6.0 | 38 | 2.9 s |
| 2 | New | Qwen3.8 2.4T A95BOpenAlibaba | 57.7 | $3.0 | 47 | 2.7 s |
| 3 | ▲ 2 | DeepSeek V4 Pro 0813 (Reasoning, Max Effort)OpenDeepSeek · 3 more variants | 53.2 | $2.0 | 80 | 1.7 s |
| 4 | ▼ 2 | GLM-5.2 (max)OpenZ AI · 1 more variant | 52.6 | $2.2 | 155 | 1.4 s |
| 5 | New | Qwen3.8 27BOpenAlibaba | 52.0 | — | — | — |
| 6 | ▼ 3 | DeepSeek V4 Flash 0731 (Reasoning, Max Effort)OpenDeepSeek · 3 more variants | 51.8 | $0.66 | 107 | 1.2 s |
| 7 | ▼ 3 | MiniMax-M3OpenMiniMax | 45.4 | $0.52 | 96 | 1.2 s |
| 8 | ▼ 2 | Kimi K2.6OpenKimi · 1 more variant | 45.1 | $1.7 | 47 | 2.7 s |
| 9 | ▼ 2 | Kimi K2.7 CodeOpenKimi | 43.0 | $1.7 | 39 | 2.8 s |
| 10 | ▼ 2 | MiMo-V2.5-ProOpenXiaomi · 1 more variant | 42.9 | $0.54 | 57 | 3.3 s |
| 11 | ▼ 2 | Hy3OpenTencent | 42.2 | $0.24 | 70 | 2.8 s |
| 12 | ▼ 2 | GLM-5.1 (Reasoning)OpenZ AI · 1 more variant | 41.0 | $2.1 | 83 | 1.5 s |
| 13 | ▼ 2 | GLM-5 (Reasoning)OpenZ AI · 1 more variant | 40.6 | $1.6 | 43 | 1.5 s |
| 14 | ▼ 2 | MiniMax-M2.7OpenMiniMax | 38.9 | $0.52 | 65 | 1.7 s |
| 15 | ▼ 2 | MiMo-V2.5OpenXiaomi | 38.0 | $0.18 | 66 | 2.6 s |
| 16 | ▼ 2 | Ling 3.0 FlashOpenInclusionAI | 37.8 | $0.11 | — | — |
| 17 | ▼ 2 | Qwen3.6 27B (Reasoning)OpenAlibaba · 1 more variant | 37.7 | $1.4 | 58 | 3.7 s |
| 18 | ▼ 2 | Kimi K2.5 (Reasoning)OpenKimi · 1 more variant | 36.0 | $1.2 | 46 | 3.0 s |
| 19 | ▼ 2 | Qwen3.5 27B (Reasoning)OpenAlibaba · 1 more variant | 34.6 | $0.83 | 77 | 5.6 s |
| 20 | ▼ 2 | MiniMax-M2.5OpenMiniMax | 34.5 | $0.52 | 99 | 1.7 s |
| 21 | ▼ 2 | GLM-4.7 (Reasoning)OpenZ AI · 1 more variant | 34.5 | $1.0 | 127 | 0.9 s |
| 22 | ▼ 2 | Hy3-preview (Reasoning)OpenTencent · 1 more variant | 34.4 | $0.100 | — | — |
| 23 | ▼ 2 | Qwen3.5 397B A17B (Reasoning)OpenAlibaba · 1 more variant | 34.3 | $1.4 | 99 | 2.2 s |
| 24 | ▼ 2 | MiMo-V2-Flash (Feb 2026)OpenXiaomi · 2 more variants | 34.0 | — | — | — |
| 25 | ▼ 2 | LongCat 2.0OpenLongCat | 34.0 | $1.3 | 44 | 2.7 s |
| 26 | ▼ 2 | Kimi K2 ThinkingOpenKimi | 33.5 | $1.1 | 129 | 1.3 s |
| 27 | ▼ 2 | Qwen3.5 122B A10B (Reasoning)OpenAlibaba · 1 more variant | 32.8 | $1.1 | 133 | 2.3 s |
| 28 | ▼ 2 | DeepSeek V3.2 (Reasoning)OpenDeepSeek · 1 more variant | 32.8 | $0.32 | — | — |
| 29 | ▼ 2 | Qwen3.6 35B A3B (Reasoning)OpenAlibaba · 1 more variant | 32.1 | $0.84 | 124 | 2.0 s |
| 30 | ▼ 2 | MiniMax-M2.1OpenMiniMax | 32.1 | $0.52 | 91 | 1.8 s |
| 31 | ▼ 2 | Ring-2.6-1TOpenInclusionAI | 31.7 | $0.85 | — | — |
| 32 | ▼ 1 | DeepSeek V3.1 Terminus (Reasoning)OpenDeepSeek · 1 more variant | 31.1 | $1.9 | — | — |
| 33 | ▼ 3 | Step 3.7 FlashOpenStepFun | 30.9 | $0.44 | 137 | 2.6 s |
| 34 | ▼ 2 | Qwen3.5 35B A3B (Reasoning)OpenAlibaba · 1 more variant | 29.9 | $0.69 | 152 | 2.0 s |
| 35 | ▼ 2 | GLM-4.6 (Reasoning)OpenZ AI · 1 more variant | 29.3 | $0.96 | 51 | 2.4 s |
| 36 | ▼ 2 | MiniMax-M2OpenMiniMax | 28.9 | $0.52 | 99 | 1.6 s |
| 37 | ▼ 2 | Ling-2.6-1TOpenInclusionAI | 26.6 | $0.85 | — | — |
| 38 | ▼ 2 | Step 3.5 FlashOpenStepFun | 26.0 | $0.15 | 243 | 1.1 s |
| 39 | ▼ 2 | DeepSeek V3.2 Exp (Reasoning)OpenDeepSeek · 1 more variant | 25.9 | $0.32 | — | — |
| 40 | New | Ling 3.0 TinyOpenInclusionAI | 24.5 | $0.000 | 155 | 2.5 s |
| 41 | ▼ 3 | Kimi K2 0905OpenKimi · 1 more variant | 24.0 | $1.1 | 41 | 1.1 s |
| 42 | ▼ 3 | GLM-4.7-Flash (Reasoning)OpenZ AI · 1 more variant | 23.3 | $0.15 | 105 | 1.1 s |
| 43 | ▼ 3 | DeepSeek V3.2 SpecialeOpenDeepSeek | 22.6 | — | — | — |
| 44 | ▼ 3 | Qwen3.5 9B (Reasoning)OpenAlibaba · 1 more variant | 21.8 | $0.15 | 82 | 2.1 s |
| 45 | ▼ 3 | DeepSeek V3.1 (Non-reasoning)OpenDeepSeek · 1 more variant | 21.4 | $0.84 | — | — |
| 46 | ▼ 3 | Qwen3 Coder NextOpenAlibaba | 21.3 | $0.56 | 140 | 1.3 s |
| 47 | ▼ 3 | Qwen3 VL 235B A22B (Reasoning)OpenAlibaba | 20.9 | $2.6 | 57 | 3.0 s |
| 48 | ▼ 3 | Qwen3.5 4B (Reasoning)OpenAlibaba · 1 more variant | 20.4 | $0.060 | 48 | 0.7 s |
| 49 | ▼ 3 | DeepSeek R1 0528 (May '25)OpenDeepSeek · 1 more variant | 20.4 | $2.1 | — | — |
| 50 | ▼ 3 | Qwen3 235B A22B 2507 (Reasoning)OpenAlibaba · 2 more variants | 19.9 | $2.6 | 65 | 2.7 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