AI BENCHY Category
Coding Ranking
See which AI models perform best on Coding, which ones stay reliable, and where the biggest gaps appear.
188/188
Filter models
No models match the current search and filters.
| Rank | Model | Company | Coding Score | Score | Total Cost | Tests Correct | Response Time (avg) |
|---|---|---|---|---|---|---|---|
| #102 | Gemma 4 31B medium | 4.3 | 6.3 | $0.033 | 0/3 | 219.8s | |
| #122 | Qwen3.5 Plus 2026-02-15 none | Qwen | 4.3 | 5.8 | $0.016 | 0/3 | 2.05s |
| #178 | MiMo-V2-Flash none | Xiaomi | 4.3 | 4.3 | $0.025 | 0/3 | 2.64s |
| #134 | DeepSeek V4 Flash none | DeepSeek | 4.2 | 5.5 | $0.007 | 0/3 | 17.1s |
| #171 | Elephant Alpha none | Openrouter | 4.2 | 4.6 | $0.000 | 0/3 | 1.39s |
| #117 | GLM 5 none | Z.ai | 4.0 | 6.0 | $0.027 | 0/3 | 5.12s |
| #75 | Step 3.7 Flash high | Stepfun | 4.0 | 7.1 | $1.148 | 0/3 | 206.2s |
| #139 | Qwen3.5 Plus 2026-04-20 none | Qwen | 3.9 | 5.5 | $0.032 | 0/3 | 1.69s |
| #140 | GLM 5 Turbo none | Z.ai | 3.9 | 5.3 | $0.047 | 0/3 | 2.41s |
| #154 | Qwen3.5-9B none | Qwen | 3.9 | 5.1 | $0.006 | 0/3 | 5.60s |
| #150 | North Mini Code none | Cohere | 3.9 | 5.1 | $0.000 | 0/3 | 22.0s |
| #133 | GLM 5.1 none | Z.ai | 3.9 | 5.6 | $0.057 | 0/3 | 4.96s |
| #115 | Qwen3.6 Max Preview none | Qwen | 3.8 | 6.0 | $0.075 | 0/3 | 3.12s |
| #166 | Ling-2.6-1T none | Inclusionai | 3.8 | 4.7 | $0.005 | 0/3 | 10.6s |
| #142 | GPT-5.6 Luna none | OpenAI | 3.8 | 5.3 | $0.047 | 0/3 | 980ms |