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: Tests Correct ↑.
Failure Reasons
25/25
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) |
|---|---|---|---|---|---|---|---|
| #74 | Claude Opus 4.6 medium | Anthropic | 1 | 5.7 | $2.961 | 1/3 | 30.1s |
| #95 | Qwen3.8 2.4T A95B high | Qwen | 1 | 5.9 | $2.357 | 1/3 | 160.5s |
| #104 | Claude Opus 4.8 none | Anthropic | 1 | 5.5 | $1.166 | 1/3 | 3.29s |
| #126 | Seed-2.0-Code high | Bytedance Seed | 1 | 6.2 | $1.273 | 1/3 | 266.7s |
| #133 | DeepSeek V4 Pro none | DeepSeek | 1 | 5.6 | $0.351 | 1/3 | 13.4s |
| #141 | Gemini 3.5 Flash minimal | 1 | 5.6 | $0.300 | 1/3 | 2.75s | |
| #203 | Kimi K2.6 none | Moonshot AI | 1 | 5.5 | $0.230 | 1/3 | 82.6s |
| #18 | Gemini 3.5 Flash medium | 1 | 7.9 | $0.665 | 2/3 | 12.6s | |
| #42 | Qwen3.8 27B high | Qwen | 1 | 8.1 | ~$0.287 | 2/3 | 248.6s |
| #176 | Trinity Large Thinking medium | Arcee AI | 1 | 7.5 | $0.798 | 2/3 | 179.0s |