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 | — | GLM-5.2 (max)OpenZ AI · 1 more variant | 51.1 | $2.2 | 174 | 1.4 s |
| 2 | — | MiniMax-M3OpenMiniMax | 44.4 | $0.52 | 99 | 1.8 s |
| 3 | — | DeepSeek V4 Pro (Reasoning, Max Effort)OpenDeepSeek · 2 more variants | 44.3 | $0.54 | 55 | 1.8 s |
| 4 | — | Kimi K2.6OpenKimi · 1 more variant | 44.2 | $1.7 | 37 | 2.3 s |
| 5 | — | MiMo-V2.5-ProOpenXiaomi · 1 more variant | 42.2 | $0.54 | 50 | 3.6 s |
| 6 | — | Kimi K2.7 CodeOpenKimi | 41.9 | $1.7 | 45 | 3.1 s |
| 7 | — | DeepSeek V4 Flash (Reasoning, Max Effort)OpenDeepSeek · 2 more variants | 40.3 | $0.18 | 99 | 1.3 s |
| 8 | — | GLM-5.1 (Reasoning)OpenZ AI · 1 more variant | 40.2 | $2.2 | 66 | 1.3 s |
| 9 | ▲ 1 | GLM-5 (Reasoning)OpenZ AI · 1 more variant | 39.5 | $1.6 | 43 | 2.0 s |
| 10 | ▲ 1 | MiniMax-M2.7OpenMiniMax | 38.1 | $0.52 | 44 | 1.9 s |
| 11 | ▲ 1 | Kimi K2.5 (Reasoning)OpenKimi · 1 more variant | 38.1 | $1.2 | 52 | 2.9 s |
| 12 | ▼ 3 | MiMo-V2.5OpenXiaomi | 37.2 | $0.18 | 81 | 2.5 s |
| 13 | — | Qwen3.6 27B (Reasoning)OpenAlibaba · 1 more variant | 37.1 | $1.4 | 60 | 3.8 s |
| 14 | — | Qwen3.5 27B (Reasoning)OpenAlibaba · 1 more variant | 33.8 | $0.83 | 80 | 5.7 s |
| 15 | — | GLM-4.7 (Reasoning)OpenZ AI · 1 more variant | 33.7 | $1.0 | 133 | 0.8 s |
| 16 | — | Qwen3.5 397B A17B (Reasoning)OpenAlibaba · 1 more variant | 33.7 | $1.4 | 55 | 2.8 s |
| 17 | — | MiniMax-M2.5OpenMiniMax | 33.7 | $0.52 | 74 | 1.8 s |
| 18 | — | Hy3-preview (Reasoning)OpenTencent · 1 more variant | 33.6 | $0.20 | 183 | 3.1 s |
| 19 | ▲ 1 | MiMo-V2-Flash (Feb 2026)OpenXiaomi · 2 more variants | 33.2 | $0.15 | — | — |
| 20 | ▲ 1 | Kimi K2 ThinkingOpenKimi | 32.7 | $1.1 | 158 | 1.2 s |
| 21 | ▲ 1 | Qwen3.5 122B A10B (Reasoning)OpenAlibaba · 1 more variant | 32.3 | $1.1 | 139 | 2.4 s |
| 22 | ▼ 3 | DeepSeek V3.2 (Reasoning)OpenDeepSeek · 1 more variant | 32.0 | $0.32 | — | — |
| 23 | — | Qwen3.6 35B A3B (Reasoning)OpenAlibaba · 1 more variant | 31.6 | $0.56 | 156 | 2.3 s |
| 24 | — | MiniMax-M2.1OpenMiniMax | 31.4 | $0.52 | 75 | 1.8 s |
| 25 | — | Ring-2.6-1TOpenInclusionAI | 30.6 | $0.85 | 124 | 3.3 s |
| 26 | ▲ 3 | DeepSeek V3.1 Terminus (Reasoning)OpenDeepSeek · 1 more variant | 30.4 | $1.9 | — | — |
| 27 | ▼ 1 | Step 3.7 FlashOpenStepFun | 30.3 | $0.44 | 373 | 0.9 s |
| 28 | ▼ 1 | Qwen3.5 35B A3B (Reasoning)OpenAlibaba · 1 more variant | 29.3 | $0.69 | 158 | 2.3 s |
| 29 | ▲ 4 | GLM-4.6 (Reasoning)OpenZ AI · 1 more variant | 28.7 | $0.96 | 41 | 1.1 s |
| 30 | ▼ 2 | MiniMax-M2OpenMiniMax | 28.3 | $0.52 | 76 | 1.8 s |
| 31 | ▼ 1 | Ling-2.6-1TOpenInclusionAI | 26.1 | $0.85 | — | — |
| 32 | ▼ 1 | Step 3.5 FlashOpenStepFun | 25.5 | $0.15 | 201 | 1.1 s |
| 33 | ▼ 1 | DeepSeek V3.2 Exp (Reasoning)OpenDeepSeek · 1 more variant | 25.4 | $0.32 | — | — |
| 34 | — | Kimi K2 0905OpenKimi · 1 more variant | 23.5 | $1.1 | 37 | 2.0 s |
| 35 | — | GLM-4.7-Flash (Reasoning)OpenZ AI · 1 more variant | 22.9 | $0.15 | 92 | 1.2 s |
| 36 | — | DeepSeek V3.2 SpecialeOpenDeepSeek | 22.2 | — | — | — |
| 37 | — | Qwen3.5 9B (Reasoning)OpenAlibaba · 1 more variant | 21.4 | $0.11 | 59 | 1.8 s |
| 38 | — | Qwen3 Coder NextOpenAlibaba | 21.1 | $0.56 | 96 | 1.7 s |
| 39 | — | DeepSeek V3.1 (Non-reasoning)OpenDeepSeek · 1 more variant | 21.0 | $0.84 | — | — |
| 40 | — | Qwen3 VL 235B A22B (Reasoning)OpenAlibaba | 20.6 | $2.6 | 57 | 3.0 s |
| 41 | — | Qwen3.5 4B (Reasoning)OpenAlibaba · 1 more variant | 20.1 | $0.060 | 31 | 0.8 s |
| 42 | — | DeepSeek R1 0528 (May '25)OpenDeepSeek · 1 more variant | 20.1 | $2.1 | — | — |
| 43 | — | Qwen3 235B A22B 2507 (Reasoning)OpenAlibaba · 2 more variants | 19.6 | $2.6 | 50 | 2.9 s |
| 44 | — | GLM-4.5 (Reasoning)OpenZ AI | 19.5 | $1.0 | — | — |
| 45 | ▲ 1 | Seed-OSS-36B-InstructOpenByteDance Seed | 18.3 | $0.30 | 35 | 3.1 s |
| 46 | ▲ 1 | Qwen3 235B A22B 2507 InstructOpenAlibaba | 18.2 | $1.2 | 58 | 2.3 s |
| 47 | ▲ 1 | Qwen3 Coder 480B A35B InstructOpenAlibaba | 18.0 | $3.0 | 56 | 3.1 s |
| 48 | ▲ 1 | Qwen3 VL 32B (Reasoning)OpenAlibaba | 17.9 | $2.6 | 91 | 2.7 s |
| 49 | ▲ 1 | MiniMax M1 80kOpenMiniMax | 17.7 | $0.96 | — | — |
| 50 | ▲ 1 | LongCat Flash LiteOpenLongCat | 17.2 | — | — | — |
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