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: Tests Correct ↑.
| Rank | Model | Company | Coding Score | Score | Tests Correct | Response Time (avg) |
|---|---|---|---|---|---|---|
| #45 | Gemma 4 31B none | 10.0 | 6.9 | 1/1 | 26.1s | |
| #51 | Mercury 2 medium | Inception | 10.0 | 6.5 | 1/1 | 1.53s |
| #53 | Grok 4.20 Multi Agent Beta medium | X AI | 10.0 | 6.4 | 1/1 | 27.1s |
| #55 | GLM 5V Turbo none | Z.ai | 10.0 | 6.2 | 1/1 | 5.30s |
| #56 | Qwen3.5-Flash none | Qwen | 10.0 | 6.2 | 1/1 | 1.29s |
| #58 | Seed-2.0-Lite none | Bytedance Seed | 10.0 | 6.2 | 1/1 | 4.61s |
| #59 | Gemini 2.5 Flash none | 10.0 | 6.2 | 1/1 | 1.16s | |
| #60 | Qwen3.5-35B-A3B none | Qwen | 10.0 | 6.1 | 1/1 | 2.67s |
| #62 | MiMo-V2-Pro none | Xiaomi | 10.0 | 6.0 | 1/1 | 3.82s |
| #63 | GPT-5.4 none | OpenAI | 10.0 | 5.9 | 1/1 | 2.95s |
| #64 | Qwen3.5-27B none | Qwen | 10.0 | 5.9 | 1/1 | 2.51s |
| #72 | Kimi K2.5 none | Moonshot AI | 10.0 | 5.5 | 1/1 | 38.8s |
| #76 | MiniMax M2.7 medium | Minimax | 10.0 | 5.3 | 1/1 | 91.3s |
| #80 | GPT-5.4 Mini none | OpenAI | 10.0 | 5.1 | 1/1 | 1.19s |