Instructions following Ranking
See which AI models perform best on Instructions following, which ones stay reliable, and where the biggest gaps appear. Sort by: Tests Correct ↑.
216/216
Filter models
No models match the current search and filters.
| Rank | Model | Company | Instructions following Score | Score | Total Cost | Tests Correct | Response Time (avg) |
|---|---|---|---|---|---|---|---|
| #133 | Qwen3.5-35B-A3B none | Qwen | 6.3 | 6.1 | $0.106 | 1/2 | 809ms |
| #136 | Step 3.5 Flash medium | Stepfun | 8.3 | 6.0 | $0.108 | 1/2 | 4.78s |
| #138 | GPT-5.6 Terra none | OpenAI | 8.5 | 6.0 | $0.349 | 1/2 | 1.15s |
| #140 | Mimo V2 Omni medium | Xiaomi | 8.3 | 5.9 | $0.683 | 1/2 | 4.99s |
| #142 | GPT-5.4 Mini none | OpenAI | 6.3 | 5.9 | $0.095 | 1/2 | 728ms |
| #144 | Kimi K2.6 none | Moonshot AI | 6.5 | 5.8 | $0.184 | 1/2 | 1.64s |
| #145 | GPT-5.4 none | OpenAI | 6.5 | 5.8 | $0.397 | 1/2 | 1.07s |
| #146 | Nemotron 3 Super medium | NVIDIA | 7.3 | 5.7 | $0.055 | 1/2 | 6.97s |
| #148 | Qwen3.5-122B-A10B none | Qwen | 6.3 | 5.7 | $0.247 | 1/2 | 513ms |
| #149 | Gemini 3.1 Flash Lite high | 7.3 | 5.6 | $2.044 | 1/2 | 23.3s | |
| #151 | GLM 5V Turbo none | Z.ai | 6.5 | 5.6 | $0.052 | 1/2 | 1.97s |
| #152 | Owl Alpha medium | Openrouter | 6.5 | 5.6 | $0.000 | 1/2 | 10.2s |
| #153 | Mimo V2 PRO none | Xiaomi | 6.5 | 5.6 | $0.045 | 1/2 | 2.51s |
| #154 | Owl Alpha none | Openrouter | 6.4 | 5.6 | $0.000 | 1/2 | 2.63s |
| #156 | DeepSeek V4 Flash none | DeepSeek | 6.5 | 5.6 | $0.042 | 1/2 | 17.5s |