Model rankings
1371 models · 5 boards · 2 sources
Smartest
Best open model
Best value
Best from China
Top three open models
GLM-5.2 (max)Z AI · #12 overall51.1
MiniMax-M3MiniMax · #18 overall44.4
DeepSeek V4 Pro (Reasoning, Max Effort)DeepSeek · #19 overall44.3
This week's changes
kimi-k3-maxCoding · #1New
claude-opus-5-highCoding · #2New
Kimi K3Intelligence · #3New
glm-5.2-maxCoding · #5New
gemini-3.6-flashCoding · #13New
| Rank | Change | Model | Intelligence | Price $/M | Speed tok/s | First token |
|---|---|---|---|---|---|---|
| 1 | New | Kimi K3ClosedKimi | 57.1 | $6.0 | — | — |
| 2 | ▼ 1 | Qwen3.7 MaxClosedAlibaba | 46.0 | $3.8 | 203 | 2.4 s |
| 3 | ▼ 1 | MiMo-V2-ProClosedXiaomi | 40.3 | — | — | — |
| 4 | ▼ 1 | Qwen3.6 Max PreviewClosedAlibaba | 40.0 | $2.9 | 38 | 3.5 s |
| 5 | ▼ 1 | Qwen3.6 PlusClosedAlibaba | 39.6 | $1.1 | 53 | 2.6 s |
| 6 | ▼ 1 | Qwen3.7 PlusClosedAlibaba | 39.0 | $0.70 | 53 | 2.8 s |
| 7 | ▼ 1 | GLM-5-TurboClosedZ AI | 38.1 | — | — | — |
| 8 | ▼ 1 | MiMo-V2-Omni-0327ClosedXiaomi · 1 more variant | 36.4 | — | — | — |
| 9 | ▼ 1 | GLM 5V Turbo (Reasoning)ClosedZ AI | 34.5 | — | — | — |
| 10 | ▼ 1 | Qwen3 Max ThinkingClosedAlibaba · 1 more variant | 31.7 | — | — | — |
| 11 | ▼ 1 | Qwen3.5 Omni PlusClosedAlibaba | 30.6 | $1.5 | 54 | 2.3 s |
| 12 | ▼ 1 | Step 3.5 Flash 2603ClosedStepFun | 26.0 | $0.15 | 286 | 1.0 s |
| 13 | ▼ 1 | Doubao Seed CodeClosedByteDance Seed | 26.0 | — | — | — |
| 14 | ▼ 1 | Qwen3 MaxClosedAlibaba · 1 more variant | 24.0 | $2.4 | 54 | 2.4 s |
| 15 | ▼ 1 | ERNIE 5.0 Thinking PreviewClosedBaidu | 21.9 | — | — | — |
| 16 | ▼ 1 | Qwen3.5 Omni FlashClosedAlibaba | 19.0 | $0.28 | 237 | 1.8 s |
| 17 | ▼ 1 | Qwen2.5 MaxClosedAlibaba | 10.2 | — | — | — |
| 18 | ▼ 1 | Qwen2.5 TurboClosedAlibaba | 6.3 | $0.088 | 109 | 2.3 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