AI BENCHY Failures
Did not follow instructions Failures
See which AI models run into Did not follow instructions most often, so you can spot reliability risks before choosing one. Sort by: Response Time (avg) ↓.
| Rank | Model | Company | Did not follow instructions Count | Score | Tests Correct | Response Time (avg) |
|---|---|---|---|---|---|---|
| #76 | Kimi K2.5 medium | Moonshot AI | 2 | 6.8 | 10/21 | 98.4s |
| #161 | Qwen3.5-9B medium | Qwen | 1 | 4.2 | 3/21 | 82.2s |
| #73 | Seed-2.0-Mini medium | Bytedance Seed | 1 | 6.9 | 11/21 | 80.2s |
| #62 | Step 3.5 Flash medium | Stepfun | 3 | 7.2 | 11/20 | 72.5s |
| #60 | Kimi K2.6 medium | Moonshot AI | 2 | 7.2 | 12/21 | 71.7s |
| #72 | DeepSeek V3.2 medium | DeepSeek | 1 | 7.0 | 11/21 | 68.7s |
| #30 | Qwen3.5-27B medium | Qwen | 2 | 7.8 | 13/21 | 68.4s |
| #67 | MiniMax M3 medium | Minimax | 2 | 7.1 | 11/21 | 68.2s |
| #12 | Gemini 3.1 Flash Lite Preview high | 1 | 8.6 | 13/16 | 68.1s | |
| #129 | MiniMax M2.5 medium | Minimax | 3 | 5.3 | 5/21 | 65.4s |
| #103 | DeepSeek V4 Pro high | DeepSeek | 1 | 6.0 | 8/21 | 65.2s |
| #49 | Qwen3.5-Flash medium | Qwen | 1 | 7.4 | 12/21 | 63.3s |
| #53 | Gemini 3.1 Flash Lite high | 3 | 7.3 | 10/18 | 62.0s | |
| #75 | Ring-2.6-1T medium | Inclusionai | 2 | 6.9 | 11/21 | 61.3s |
| #78 | Qwen3.6 27B medium | Qwen | 1 | 6.8 | 10/21 | 59.7s |