AI BENCHY Failures
Wrong answer Failures
See which AI models run into Wrong answer most often, so you can spot reliability risks before choosing one. Sort by: Total Cost ↑.
Categories
169/169
Filter models
No models match the current search and filters.
| Rank | Model | Company | Wrong answer Count | Score | Total Cost | Tests Correct | Response Time (avg) |
|---|---|---|---|---|---|---|---|
| #106 | Qwen3.5 Plus 2026-02-15 none | Qwen | 12 | 5.8 | $0.016 | 9/21 | 2.31s |
| #119 | MiMo-V2.5-Pro none | Xiaomi | 11 | 5.5 | $0.017 | 6/21 | 1.78s |
| #126 | DeepSeek V3.2 none | DeepSeek | 7 | 5.3 | $0.017 | 6/21 | 13.8s |
| #84 | Gemini 3.1 Flash Lite Preview none | 7 | 6.4 | $0.018 | 12/21 | 1.21s | |
| #86 | Hy3 preview low | Tencent | 4 | 6.4 | $0.018 | 10/21 | 24.6s |
| #92 | Seed-2.0-Lite none | Bytedance Seed | 13 | 6.2 | $0.019 | 8/21 | 2.49s |
| #125 | Qwen3.5-122B-A10B none | Qwen | 13 | 5.3 | $0.020 | 6/21 | 3.41s |
| #168 | Step 3.5 Flash none | Stepfun | 1 | 2.6 | $0.020 | 6/12 | 39.0s |
| #87 | Nemotron 3 Super medium | NVIDIA | 5 | 6.3 | $0.021 | 8/21 | 32.0s |
| #114 | Mimo V2 Omni none | Xiaomi | 10 | 5.7 | $0.021 | 8/21 | 2.44s |
| #54 | Hy3 preview medium | Tencent | 3 | 7.3 | $0.021 | 14/21 | 16.3s |
| #60 | Qwen3.7 Plus none | Qwen | 10 | 7.2 | $0.023 | 10/21 | 2.85s |
| #67 | Gemini 3 Flash Preview none | 8 | 6.9 | $0.025 | 13/21 | 1.65s | |
| #159 | MiMo-V2-Flash none | Xiaomi | 13 | 4.3 | $0.025 | 4/21 | 2.76s |
| #82 | Gemini 3.1 Flash Lite Preview low | 7 | 6.5 | $0.026 | 13/21 | 2.77s |