AI BENCHY Category
Coding Ranking
See which AI models perform best on Coding, which ones stay reliable, and where the biggest gaps appear.
| Rank | Model | Company | Coding Score | Score | Tests Correct | Response Time (avg) |
|---|---|---|---|---|---|---|
| #141 | Qwen3 Coder Next medium | Qwen | 4.1 | 4.7 | 0/2 | 1.17s |
| #79 | Kimi K2.5 medium | Moonshot AI | 4.1 | 6.7 | 0/2 | 215.9s |
| #77 | Grok 4.20 medium | X AI | 4.1 | 6.7 | 0/2 | 65.1s |
| #122 | Elephant Alpha medium | Openrouter | 4.0 | 5.4 | 0/2 | 1.30s |
| #124 | Qwen3.5-122B-A10B none | Qwen | 4.0 | 5.4 | 0/2 | 2.14s |
| #135 | Mistral Small 4 none | Mistral | 4.0 | 5.0 | 0/2 | 1.03s |
| #71 | DeepSeek V3.2 medium | DeepSeek | 3.9 | 7.0 | 0/2 | 185.0s |
| #111 | gpt-oss-120b medium | OpenAI | 3.9 | 5.6 | 0/2 | 47.2s |
| #23 | Gemma 4 31B medium | 3.8 | 8.0 | 0/2 | 110.9s | |
| #143 | Mercury 2 none | Inception | 3.5 | 4.6 | 0/2 | 831ms |
| #119 | MiniMax M2.5 medium | Minimax | 3.5 | 5.4 | 0/2 | 125.8s |
| #120 | Grok 4.20 none | X AI | 3.4 | 5.4 | 0/1 | 1.22s |
| #72 | MiMo-V2-Omni medium | Xiaomi | 3.4 | 6.9 | 0/2 | 183.9s |
| #134 | Nemotron 3 Super none | NVIDIA | 3.4 | 5.0 | 0/2 | 3.02s |
| #148 | GLM 4.7 Flash medium | Z.ai | 3.4 | 4.5 | 0/2 | 55.3s |