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) ↑.
Categories
293/293
Filter models
No models match the current search and filters.
| Rank | Model | Company | Did not follow instructions Count | Score | Total Cost | Tests Correct | Response Time (avg) |
|---|---|---|---|---|---|---|---|
| #288 | Gemini 3.1 Flash Lite minimal | 3 | 0.6 | $0.080 | 10/23 | 3.95s | |
| #297 | GPT-5.6 Terra none | OpenAI | 1 | 0.6 | $0.377 | 8/23 | 4.11s |
| #353 | GPT-4o-mini default | OpenAI | 1 | 0.5 | $0.024 | 5/23 | 4.16s |
| #223 | Mercury 2 medium | Inception | 3 | 0.7 | $0.121 | 10/23 | 4.40s |
| #374 | GPT-5.4 Nano none | OpenAI | 2 | 0.5 | $0.068 | 4/23 | 4.42s |
| #335 | Laguna XS 2.1 none | Poolside | 1 | 0.5 | $0.020 | 5/23 | 4.56s |
| #216 | GPT-5.6 Sol none | OpenAI | 1 | 0.7 | $0.795 | 12/23 | 4.61s |
| #247 | Gemini 3.5 Flash minimal | 1 | 0.6 | $0.508 | 13/23 | 4.67s | |
| #415 | Hunter Alpha default | OpenRouter | 2 | 0.3 | $0.000 | 6/18 | 4.70s |
| #254 | Gemini 3.5 Flash Lite low | 1 | 0.6 | $0.183 | 12/23 | 4.79s | |
| #245 | Beam 1.0 501B A23B low | Reflection | 2 | 0.6 | $0.432 | 11/23 | 4.89s |
| #350 | Mercury 2.5 Preview low | Inception | 2 | 0.5 | $0.015 | 6/23 | 4.92s |
| #324 | Qwen3.8 27B none | Qwen | 1 | 0.5 | ~$0.010 | 9/23 | 5.05s |
| #397 | Mercury 2.5 none | Inception | 4 | 0.4 | $0.026 | 2/23 | 5.10s |
| #277 | Inkling none | Thinkingmachines | 1 | 0.6 | $0.292 | 7/23 | 5.30s |