Instructions following Ranking
See which AI models perform best on Instructions following, which ones stay reliable, and where the biggest gaps appear. Sort by: Response Time (avg) ↑.
461/461
Filter models
No models match the current search and filters.
| Rank | Model | Company | Instructions following Score | Score | Total Cost | Tests Correct | Response Time (avg) |
|---|---|---|---|---|---|---|---|
| #211 | Qwen3.5-Flash medium | Qwen | 1.0 | 0.7 | $0.184 | 2/2 | 63.5s |
| #401 | Gemini 3.1 Flash Lite Preview high | 1.0 | 0.4 | $2.310 | 2/2 | 64.0s | |
| #341 | Granite 4.2 8B low | IBM Granite | 0.3 | 0.5 | $0.036 | 0/2 | 75.8s |
| #335 | Hy4 preview low | Tencent | 1.0 | 0.5 | $1.844 | 2/2 | 77.7s |
| #398 | Granite 4.2 8B none | IBM Granite | 0.3 | 0.4 | $0.037 | 0/2 | 79.5s |
| #380 | Granite 4.2 8B high | IBM Granite | 0.6 | 0.5 | $0.111 | 1/2 | 87.5s |
| #253 | Kimi K2.5 medium | Moonshot AI | 1.0 | 0.6 | $0.841 | 2/2 | 92.5s |
| #435 | Command A+ none | Cohere | 0.3 | 0.3 | $0.000 | 0/2 | 95.7s |
| #426 | Command A+ medium | Cohere | 0.3 | 0.3 | $0.064 | 0/2 | 103.0s |
| #436 | Command A+ low | Cohere | 0.3 | 0.3 | $0.073 | 0/2 | 105.7s |
| #432 | Command A+ high | Cohere | 0.3 | 0.3 | $0.079 | 0/2 | 110.3s |