AI BENCHY Category
Coding Ranking
See which AI models perform best on Coding, which ones stay reliable, and where the biggest gaps appear. Sort by: Total Cost ↑.
189/189
Filter models
No models match the current search and filters.
| Rank | Model | Company | Coding Score | Score | Total Cost | Tests Correct | Response Time (avg) |
|---|---|---|---|---|---|---|---|
| #57 | Mercury 2 medium | Inception | 8.2 | 7.5 | $0.058 | 2/3 | 2.04s |
| #90 | MiMo-V2.5 medium | Xiaomi | 6.2 | 6.7 | $0.061 | 1/3 | 97.1s |
| #153 | Mistral Small 4 medium | Mistral | 4.4 | 5.1 | $0.068 | 0/3 | 40.0s |
| #41 | Gemini 3.1 Flash Lite Preview medium | 5.5 | 7.8 | $0.068 | 1/3 | 4.09s | |
| #133 | Grok 4.1 Fast medium | X AI | 7.8 | 5.6 | $0.069 | 0/1 | 23.6s |
| #94 | Step 3.5 Flash medium | Stepfun | 2.4 | 6.6 | $0.070 | 0/2 | 258.4s |
| #43 | Gemini 3.1 Flash Lite medium | 5.5 | 7.8 | $0.071 | 1/3 | 3.81s | |
| #116 | Qwen3.6 Max Preview none | Qwen | 3.8 | 6.0 | $0.075 | 0/3 | 3.12s |
| #128 | Kimi K2.6 none | Moonshot AI | 5.5 | 5.8 | $0.078 | 1/3 | 82.6s |
| #84 | Qwen3.5-Flash medium | Qwen | 3.7 | 6.8 | $0.080 | 0/3 | 58.9s |
| #93 | GPT-5 Nano medium | OpenAI | 7.0 | 6.7 | $0.081 | 1/3 | 41.6s |
| #169 | Grok 4.20 Beta none | X AI | 1.8 | 4.7 | $0.087 | 0/1 | 1.14s |
| #147 | MiniMax M2.7 medium | Minimax | 5.7 | 5.2 | $0.100 | 1/3 | 101.9s |
| #64 | MiMo-V2.5-Pro medium | Xiaomi | 6.2 | 7.4 | $0.106 | 1/3 | 92.1s |
| #59 | GPT-5.4 Nano medium | OpenAI | 6.1 | 7.5 | $0.107 | 1/3 | 19.1s |