AI BENCHY Category Failures
Coding: Wrong answer
Coding
Wrong answer
See which AI models are most likely to hit Wrong answer on Coding, so you can spot weak points faster. Sort by: Tests Correct ↓.
Failure Reasons
134/134
Filter models
No models match the current search and filters.
| Rank | Model | Company | Wrong answer Count | Category Score | Total Cost | Tests Correct | Response Time (avg) |
|---|---|---|---|---|---|---|---|
| #70 | Claude Opus 4.8 none | Anthropic | 1 | 5.5 | $0.539 | 1/3 | 3.29s |
| #71 | DeepSeek V4 Pro none | DeepSeek | 1 | 5.6 | $0.034 | 1/3 | 13.4s |
| #73 | Qwen3.7 Plus none | Qwen | 2 | 5.5 | $0.023 | 1/3 | 2.15s |
| #75 | MiMo-V2-Flash medium | Xiaomi | 1 | 6.0 | $0.043 | 1/3 | 10.7s |
| #78 | Laguna XS 2.1 medium | Poolside | 2 | 5.5 | $0.036 | 1/3 | 70.3s |
| #81 | Gemini 3 Flash Preview none | 2 | 5.5 | $0.025 | 1/3 | 1.80s | |
| #82 | Qwen3.7 Max none | Qwen | 2 | 5.5 | $0.054 | 1/3 | 1.35s |
| #85 | Gemini 3.5 Flash minimal | 1 | 5.6 | $0.108 | 1/3 | 2.75s | |
| #90 | MiMo-V2.5 medium | Xiaomi | 2 | 6.2 | $0.061 | 1/3 | 97.1s |
| #91 | Mimo V2 PRO medium | Xiaomi | 1 | 6.0 | $0.333 | 1/3 | 94.2s |
| #92 | gpt-oss-120b medium | OpenAI | 2 | 5.9 | $0.013 | 1/3 | 38.4s |
| #93 | GPT-5 Nano medium | OpenAI | 2 | 7.0 | $0.081 | 1/3 | 41.6s |
| #96 | Gemini 3.1 Flash Lite Preview low | 2 | 5.5 | $0.026 | 1/3 | 1.39s | |
| #98 | Gemini 3.1 Flash Lite Preview none | 2 | 5.5 | $0.018 | 1/3 | 967ms | |
| #99 | Gemini 3.1 Flash Lite low | 2 | 5.5 | $0.028 | 1/3 | 1.53s |