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 · 1 more variant | 41.7 | — | — | — |
| 2 | ▲ 2 | DeepSeek V3.2 (Reasoning)OpenDeepSeek · 1 more variant | 41.2 | — | — | — |
| 3 | ▼ 1 | Kimi K2 ThinkingOpenKimi | 40.3 | — | — | — |
| 4 | ▲ 1 | MiniMax-M2.1OpenMiniMax | 39.4 | — | — | — |
| 5 | ▼ 2 | MiMo-V2-Flash (Reasoning)OpenXiaomi · 1 more variant | 39.1 | — | — | — |
| 6 | — | MiniMax-M2OpenMiniMax | 35.7 | — | — | — |
| 7 | ▲ 2 | DeepSeek V3.1 Terminus (Reasoning)OpenDeepSeek · 1 more variant | 33.5 | — | — | — |
| 8 | ▼ 1 | gpt-oss-120B (high)OpenOpenAI · 1 more variant | 32.9 | — | — | — |
| 9 | ▲ 3 | DeepSeek V3.2 Exp (Reasoning)OpenDeepSeek · 1 more variant | 32.5 | — | — | — |
| 10 | ▲ 3 | GLM-4.6 (Reasoning)OpenZ AI · 1 more variant | 32.2 | — | — | — |
| 11 | New | K-EXAONE (Reasoning)OpenLG AI Research · 1 more variant | 31.9 | — | — | — |
| 12 | ▼ 2 | Qwen3 235B A22B 2507 (Reasoning)OpenAlibaba · 2 more variants | 29.4 | — | — | — |
| 13 | ▼ 5 | DeepSeek V3.2 SpecialeOpenDeepSeek | 29.0 | — | — | — |
| 14 | ▲ 10 | Kimi K2 0905OpenKimi | 28.0 | — | — | — |
| 15 | ▲ 1 | DeepSeek V3.1 (Reasoning)OpenDeepSeek · 1 more variant | 27.9 | — | — | — |
| 16 | ▼ 5 | Apriel-v1.6-15B-ThinkerOpenServiceNow | 27.8 | — | — | — |
| 17 | ▼ 3 | Qwen3 VL 235B A22B (Reasoning)OpenAlibaba | 27.5 | — | — | — |
| 18 | — | DeepSeek R1 0528 (May '25)OpenDeepSeek · 1 more variant | 27.1 | — | — | — |
| 19 | ▲ 4 | GLM-4.5 (Reasoning)OpenZ AI | 26.8 | — | — | — |
| 20 | ▼ 5 | Qwen3 Next 80B A3B (Reasoning)OpenAlibaba | 26.5 | — | — | — |
| 21 | — | Seed-OSS-36B-InstructOpenByteDance Seed | 25.0 | — | — | — |
| 22 | ▲ 17 | Qwen3 Coder 480B A35B InstructOpenAlibaba | 24.8 | — | — | — |
| 23 | ▼ 3 | NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)OpenNVIDIA · 1 more variant | 24.7 | — | — | — |
| 24 | ▼ 7 | gpt-oss-20B (high)OpenOpenAI · 1 more variant | 24.7 | — | — | — |
| 25 | ▲ 4 | Qwen3 235B A22B 2507 InstructOpenAlibaba | 24.6 | — | — | — |
| 26 | ▲ 2 | MiniMax M1 80kOpenMiniMax | 24.3 | — | — | — |
| 27 | ▲ 7 | HyperCLOVA X SEED Think (32B)OpenNaver | 24.0 | — | — | — |
| 28 | ▲ 16 | GLM-4.6V (Reasoning)OpenZ AI · 1 more variant | 23.8 | — | — | — |
| 29 | ▼ 4 | GLM-4.5-AirOpenZ AI | 23.6 | — | — | — |
| 30 | New | Mi:dm K 2.5 ProOpenKorea Telecom | 23.2 | — | — | — |
| 31 | ▼ 5 | Qwen3 30B A3B 2507 (Reasoning)OpenAlibaba · 2 more variants | 22.8 | — | — | — |
| 32 | ▲ 10 | DeepSeek V3 0324OpenDeepSeek · 1 more variant | 22.6 | — | — | — |
| 33 | ▲ 20 | Mistral Large 3OpenMistral | 22.5 | — | — | — |
| 34 | New | INTELLECT-3OpenPrime Intellect | 22.2 | — | — | — |
| 35 | ▲ 25 | Devstral 2OpenMistral | 21.7 | — | — | — |
| 36 | ▼ 9 | K2-V2 (high)OpenMBZUAI Institute of Foundation Models · 2 more variants | 21.1 | — | — | — |
| 37 | ▼ 2 | Qwen3 VL 235B A22B InstructOpenAlibaba | 20.8 | — | — | — |
| 38 | ▼ 6 | Qwen3 Next 80B A3B InstructOpenAlibaba | 20.3 | — | — | — |
| 39 | ▲ 26 | Qwen3 Coder 30B A3B InstructOpenAlibaba | 20.2 | — | — | — |
| 40 | ▼ 7 | Ling-1TOpenInclusionAI | 19.7 | — | — | — |
| 40 | ▼ 10 | Qwen3 VL 30B A3B (Reasoning)OpenAlibaba | 19.7 | — | — | — |
| 42 | ▼ 11 | Llama Nemotron Super 49B v1.5 (Reasoning)OpenNVIDIA · 1 more variant | 19.4 | — | — | — |
| 43 | ▲ 28 | Devstral Small 2OpenMistral | 19.1 | — | — | — |
| 44 | ▲ 19 | Llama 4 MaverickOpenMeta | 18.9 | — | — | — |
| 45 | ▼ 9 | Qwen3 4B 2507 (Reasoning)OpenAlibaba | 18.8 | — | — | — |
| 46 | ▲ 37 | Llama 3.1 Instruct 405BOpenMeta | 17.5 | — | — | — |
| 47 | ▼ 4 | Qwen3 VL 32B InstructOpenAlibaba | 17.1 | — | — | — |
| 48 | ▲ 2 | Qwen3 32B (Reasoning)OpenAlibaba | 17.1 | — | — | — |
| 49 | ▲ 19 | Qwen3 VL 8B (Reasoning)OpenAlibaba | 17.0 | — | — | — |
| 50 | ▼ 12 | EXAONE 4.0 32B (Reasoning)OpenLG AI Research · 1 more variant | 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