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: Total Cost ↑.
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) |
|---|---|---|---|---|---|---|---|
| #271 | Gemini 3.1 Flash Lite Preview none | 2 | 0.6 | $0.090 | 12/23 | 3.60s | |
| #349 | Laguna S 2.1 medium | Poolside | 1 | 0.5 | $0.092 | 4/23 | 63.1s |
| #241 | Solar Pro 4 medium | Upstage | 2 | 0.6 | $0.098 | 12/23 | 133.9s |
| #211 | Solar Pro 4 low | Upstage | 2 | 0.7 | $0.101 | 11/23 | 145.2s |
| #300 | Ring 2.6 1t medium | Inclusionai | 2 | 0.6 | $0.102 | 11/23 | 65.5s |
| #336 | Qwen3.6 35B A3B none | Qwen | 2 | 0.5 | $0.105 | 4/23 | 8.43s |
| #328 | Step 3.5 Flash medium | Stepfun | 3 | 0.5 | $0.105 | 10/22 | 190.5s |
| #399 | Qwen3.5-9B medium | Qwen | 1 | 0.4 | $0.106 | 3/23 | 110.2s |
| #377 | Laguna S 2.1 low | Poolside | 2 | 0.5 | $0.108 | 3/23 | 88.2s |
| #286 | Inkling Small medium | Thinkingmachines | 4 | 0.6 | $0.113 | 10/23 | 6.03s |
| #180 | GLM 5.3 FlashX medium | Z.ai | 1 | 0.7 | $0.114 | 12/23 | 7.37s |
| #168 | Qwen3.5-27B none | Qwen | 2 | 0.7 | $0.116 | 10/23 | 9.98s |
| #373 | DeepSeek V3.2 none | DeepSeek | 1 | 0.5 | $0.119 | 6/23 | 22.4s |
| #313 | Qwen3.5-35B-A3B none | Qwen | 2 | 0.6 | $0.120 | 6/23 | 18.3s |
| #223 | Mercury 2 medium | Inception | 3 | 0.7 | $0.121 | 10/23 | 4.40s |