Model rankings
757 models · 5 boards · 2 sources
Smartest
Best open model
Best from China
Top three by Intelligence
GPT-5.2 (xhigh)OpenAI50.6
Claude Opus 4.5 (Reasoning)Anthropic49.1
Gemini 3 Pro Preview (high)Google47.9
Top three open models
GLM-4.7 (Reasoning)Z AI · #9 overall41.7
DeepSeek V3.2 (Reasoning)DeepSeek · #12 overall41.2
Kimi K2 ThinkingKimi · #14 overall40.3
This week's changes
GPT Image 1.5 (high)Image · #1New
FLUX.2 [max]Image · #3New
Kling O1 ProVideo · #9New
Kling 2.6 Pro (No Audio)Video · #10New
Imagen 4 UltraImage · #12New
| Rank | Change | Model | Intelligence | Price $/M | Speed tok/s | First token |
|---|---|---|---|---|---|---|
| 1 | — | GLM-4.7 (Reasoning)OpenZ AI | 41.7 | — | — | — |
| 2 | ▲ 2 | DeepSeek V3.2 (Reasoning)OpenDeepSeek | 41.2 | — | — | — |
| 3 | ▼ 1 | Kimi K2 ThinkingOpenKimi | 40.3 | — | — | — |
| 4 | ▲ 1 | MiniMax-M2.1OpenMiniMax | 39.4 | — | — | — |
| 5 | ▼ 2 | MiMo-V2-Flash (Reasoning)OpenXiaomi | 39.1 | — | — | — |
| 6 | ▲ 1 | MiniMax-M2OpenMiniMax | 35.7 | — | — | — |
| 7 | ▲ 18 | GLM-4.7 (Non-reasoning)OpenZ AI | 33.8 | — | — | — |
| 8 | ▲ 1 | DeepSeek V3.1 Terminus (Reasoning)OpenDeepSeek | 33.5 | — | — | — |
| 9 | ▲ 2 | Doubao Seed CodeClosedByteDance Seed | 33.2 | — | — | — |
| 10 | ▲ 2 | DeepSeek V3.2 Exp (Reasoning)OpenDeepSeek | 32.5 | — | — | — |
| 11 | ▲ 3 | Qwen3 Max ThinkingClosedAlibaba | 32.3 | — | — | — |
| 12 | ▲ 1 | GLM-4.6 (Reasoning)OpenZ AI | 32.2 | — | — | — |
| 13 | ▲ 7 | DeepSeek V3.2 (Non-reasoning)OpenDeepSeek | 31.9 | — | — | — |
| 14 | ▲ 1 | Qwen3 MaxClosedAlibaba | 31.0 | — | — | — |
| 15 | ▲ 18 | MiMo-V2-Flash (Non-reasoning)OpenXiaomi | 30.1 | — | — | — |
| 16 | ▲ 24 | GLM-4.6 (Non-reasoning)OpenZ AI | 29.8 | — | — | — |
| 17 | ▼ 7 | Qwen3 235B A22B 2507 (Reasoning)OpenAlibaba | 29.4 | — | — | — |
| 18 | ▼ 10 | DeepSeek V3.2 SpecialeOpenDeepSeek | 29.0 | — | — | — |
| 19 | — | ERNIE 5.0 Thinking PreviewClosedBaidu | 28.9 | — | — | — |
| 20 | ▲ 6 | Kimi K2 0905OpenKimi | 28.0 | — | — | — |
| 21 | ▲ 10 | DeepSeek V3.2 Exp (Non-reasoning)OpenDeepSeek | 28.0 | — | — | — |
| 22 | ▲ 12 | DeepSeek V3.1 Terminus (Non-reasoning)OpenDeepSeek | 28.0 | — | — | — |
| 23 | ▼ 5 | DeepSeek V3.1 (Reasoning)OpenDeepSeek | 27.9 | — | — | — |
| 24 | ▲ 15 | DeepSeek V3.1 (Non-reasoning)OpenDeepSeek | 27.7 | — | — | — |
| 25 | ▼ 9 | Qwen3 VL 235B A22B (Reasoning)OpenAlibaba | 27.5 | — | — | — |
| 26 | ▼ 5 | DeepSeek R1 0528 (May '25)OpenDeepSeek | 27.1 | — | — | — |
| 27 | ▼ 3 | GLM-4.5 (Reasoning)OpenZ AI | 26.8 | — | — | — |
| 28 | ▼ 11 | Qwen3 Next 80B A3B (Reasoning)OpenAlibaba | 26.5 | — | — | — |
| 29 | ▼ 6 | Seed-OSS-36B-InstructOpenByteDance Seed | 25.0 | — | — | — |
| 30 | ▲ 14 | Qwen3 Coder 480B A35B InstructOpenAlibaba | 24.8 | — | — | — |
| 31 | ▲ 4 | Qwen3 235B A22B 2507 InstructOpenAlibaba | 24.6 | — | — | — |
| 32 | — | MiniMax M1 80kOpenMiniMax | 24.3 | — | — | — |
| 33 | ▲ 16 | GLM-4.6V (Reasoning)OpenZ AI | 23.8 | — | — | — |
| 34 | ▼ 7 | GLM-4.5-AirOpenZ AI | 23.6 | — | — | — |
| 35 | ▼ 5 | Qwen3 30B A3B 2507 (Reasoning)OpenAlibaba | 22.8 | — | — | — |
| 36 | ▲ 11 | DeepSeek V3 0324OpenDeepSeek | 22.6 | — | — | — |
| 37 | ▲ 4 | Qwen3 VL 235B A22B InstructOpenAlibaba | 20.8 | — | — | — |
| 38 | ▼ 1 | Qwen3 Next 80B A3B InstructOpenAlibaba | 20.3 | — | — | — |
| 39 | ▲ 22 | Qwen3 Coder 30B A3B InstructOpenAlibaba | 20.2 | — | — | — |
| 40 | ▲ 6 | Qwen3 235B A22B (Reasoning)OpenAlibaba | 19.9 | — | — | — |
| 41 | ▼ 3 | Ling-1TOpenInclusionAI | 19.7 | — | — | — |
| 41 | ▼ 5 | Qwen3 VL 30B A3B (Reasoning)OpenAlibaba | 19.7 | — | — | — |
| 43 | — | Qwen3 4B 2507 (Reasoning)OpenAlibaba | 18.8 | — | — | — |
| 44 | ▼ 2 | DeepSeek R1 (Jan '25)OpenDeepSeek | 18.7 | — | — | — |
| 45 | ▲ 23 | GLM-4.6V (Non-reasoning)OpenZ AI | 17.4 | — | — | — |
| 46 | ▲ 25 | Qwen3 235B A22B (Non-reasoning)OpenAlibaba | 17.3 | — | — | — |
| 47 | ▲ 1 | Qwen3 VL 32B InstructOpenAlibaba | 17.1 | — | — | — |
| 48 | ▲ 5 | Qwen3 32B (Reasoning)OpenAlibaba | 17.1 | — | — | — |
| 49 | ▲ 16 | Qwen3 VL 8B (Reasoning)OpenAlibaba | 17.0 | — | — | — |
| 50 | ▲ 14 | DeepSeek V3 (Dec '24)OpenDeepSeek | 17.0 | — | — | — |
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