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) |
|---|---|---|---|---|---|---|---|
| #188 | Step 3.5 Flash none | Stepfun | 9.8 | 2.6 | $0.020 | 0/1 | 0ms |
| #145 | Qwen3.5-122B-A10B none | Qwen | 3.7 | 5.3 | $0.020 | 0/3 | 2.77s |
| #107 | Seed-2.0-Lite none | Bytedance Seed | 5.6 | 6.2 | $0.019 | 1/3 | 2.83s |
| #98 | Gemini 3.1 Flash Lite Preview none | 5.5 | 6.4 | $0.018 | 1/3 | 967ms | |
| #67 | Hy3 preview medium | Tencent | 5.3 | 7.3 | $0.018 | 1/3 | 31.4s |
| #137 | MiMo-V2.5-Pro none | Xiaomi | 4.3 | 5.5 | $0.017 | 0/3 | 1.41s |
| #123 | Qwen3.5 Plus 2026-02-15 none | Qwen | 4.3 | 5.8 | $0.016 | 0/3 | 2.05s |
| #146 | DeepSeek V3.2 none | DeepSeek | 3.1 | 5.3 | $0.016 | 0/3 | 14.5s |
| #109 | Gemini 2.5 Flash none | 5.5 | 6.2 | $0.016 | 1/3 | 736ms | |
| #176 | Laguna Xs.2 medium | Poolside | 2.1 | 4.3 | $0.015 | 0/1 | 14.4s |
| #100 | Hy3 preview low | Tencent | 5.3 | 6.4 | $0.015 | 1/3 | 27.9s |
| #121 | Qwen3.5-27B none | Qwen | 5.8 | 5.9 | $0.015 | 1/3 | 1.80s |
| #119 | Qwen3.6 Flash none | Qwen | 5.4 | 6.0 | $0.015 | 1/3 | 1.79s |
| #110 | Gemini 3.1 Flash Lite minimal | 5.5 | 6.1 | $0.013 | 1/3 | 831ms | |
| #112 | Gemini 3.1 Flash Lite none | 5.5 | 6.1 | $0.013 | 1/3 | 938ms |