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) |
|---|---|---|---|---|---|---|
| #78 | Mistral Small 4 none | Mistral | 4.5 | 5.2 | 0/1 | 1.28s |
| #79 | gpt-oss-120b none | OpenAI | 4.3 | 5.2 | 0/1 | 9.57s |
| #81 | Qwen3 Coder Next none | Qwen | 7.3 | 5.1 | 0/1 | 3.14s |
| #82 | Nemotron 3 Super none | NVIDIA | 3.3 | 5.1 | 0/1 | 2.99s |
| #83 | GPT-4o-mini none | OpenAI | 3.0 | 4.9 | 0/1 | 2.55s |
| #84 | Qwen3.5-9B none | Qwen | 5.2 | 4.8 | 0/1 | 5.69s |
| #85 | Mercury 2 none | Inception | 3.6 | 4.8 | 0/1 | 969ms |
| #86 | Qwen3 Coder Next medium | Qwen | 4.7 | 4.7 | 0/1 | 1.69s |
| #87 | GLM 4.7 Flash medium | Z.ai | 3.6 | 4.6 | 0/1 | 21.3s |
| #88 | MiMo-V2-Flash none | Xiaomi | 6.3 | 4.5 | 0/1 | 2.79s |
| #89 | Grok 4.1 Fast none | X AI | 5.3 | 4.5 | 0/1 | 1.79s |
| #90 | GPT-5.4 Nano none | OpenAI | 7.1 | 4.5 | 0/1 | 1.43s |
| #91 | Qwen3.5-9B medium | Qwen | 2.6 | 4.4 | 0/1 | 135.6s |
| #93 | Step 3.5 Flash none | Stepfun | 3.0 | 3.0 | 0/1 | 0ms |