Coding: Did not follow instructions
Coding
Did not follow instructions
See which AI models are most likely to hit Did not follow instructions on Coding, so you can spot weak points faster. Sort by: Total Cost ↓.
Failure Reasons
38/38
Filter models
No models match the current search and filters.
| Rank | Model | Company | Did not follow instructions Count | Category Score | Total Cost | Tests Correct | Response Time (avg) |
|---|---|---|---|---|---|---|---|
| #243 | Claude Fable 5.1 low | Anthropic | 2 | 0.3 | $3.395 | 0/3 | 6.75s |
| #232 | Claude Opus 4.6 medium | Anthropic | 1 | 0.6 | $2.961 | 1/3 | 30.1s |
| #108 | Qwen3.8 2.4T A95B high | Qwen | 1 | 0.6 | $2.949 | 1/3 | 160.5s |
| #178 | Claude Opus 4.8 none | Anthropic | 1 | 0.5 | $2.334 | 1/3 | 3.29s |
| #131 | Seed-2.0-Code high | Bytedance Seed | 1 | 0.6 | $1.448 | 1/3 | 266.7s |
| #130 | Mistral Large 4 high | Mistral | 1 | 0.3 | $1.391 | 0/3 | 1277.8s |
| #107 | Gemini 3.5 Flash medium | 1 | 0.8 | $1.316 | 2/3 | 12.6s | |
| #204 | Claude Sonnet 5.5 medium | Anthropic | 2 | 0.3 | $1.100 | 0/3 | 6.07s |
| #177 | Claude Sonnet 5.5 low | Anthropic | 2 | 0.3 | $0.909 | 0/3 | 5.81s |
| #245 | Trinity Large Thinking medium | Arcee AI | 1 | 0.8 | $0.862 | 2/3 | 179.0s |
| #269 | Trinity Large Thinking high | Arcee AI | 1 | 0.4 | $0.794 | 0/3 | 245.0s |
| #77 | DeepSeek V4 Flash 0731 high | DeepSeek | 1 | 0.6 | $0.576 | 1/3 | 252.7s |
| #219 | Gemini 3.5 Flash minimal | 1 | 0.6 | $0.508 | 1/3 | 2.75s | |
| #282 | Kimi K2.6 none | Moonshot AI | 1 | 0.6 | $0.486 | 1/3 | 82.6s |
| #266 | DeepSeek V4.1 Flash none | DeepSeek | 1 | 0.6 | $0.391 | 1/3 | 83.7s |