Instructions following Ranking
See which AI models perform best on Instructions following, which ones stay reliable, and where the biggest gaps appear. Sort by: Metric ↑.
210/210
Filter models
No models match the current search and filters.
| Rank | Model | Company | Instructions following Score | Score | Total Cost | Tests Correct | Response Time (avg) |
|---|---|---|---|---|---|---|---|
| #125 | Qwen3.5-Flash none | Qwen | 6.3 | 6.1 | $0.073 | 1/2 | 8.81s |
| #127 | Qwen3.5-35B-A3B none | Qwen | 6.3 | 6.1 | $0.106 | 1/2 | 809ms |
| #136 | GPT-5.4 Mini none | OpenAI | 6.3 | 5.9 | $0.095 | 1/2 | 728ms |
| #142 | Qwen3.5-122B-A10B none | Qwen | 6.3 | 5.7 | $0.247 | 1/2 | 513ms |
| #156 | Gemma 4 26B A4B none | 6.3 | 5.5 | $0.015 | 1/2 | 690ms | |
| #164 | Inkling none | Thinkingmachines | 6.3 | 5.2 | $0.147 | 1/2 | 1.72s |
| #166 | Qwen3 Coder Next none | Qwen | 6.3 | 5.1 | $0.025 | 1/2 | 7.78s |
| #174 | GPT-4o-mini none | OpenAI | 6.3 | 5.0 | $0.010 | 1/2 | 1.11s |
| #177 | Nemotron 3 Super none | NVIDIA | 6.3 | 4.9 | $0.008 | 1/2 | 804ms |
| #180 | GPT-5.4 Nano none | OpenAI | 6.3 | 4.8 | $0.041 | 1/2 | 784ms |
| #187 | Qwen3 Coder Next medium | Qwen | 6.3 | 4.7 | $0.032 | 1/2 | 7.49s |
| #191 | Grok 4.20 Beta none | X AI | 6.3 | 4.4 | $0.087 | 1/2 | 649ms |
| #197 | Grok 4.20 none | X AI | 6.3 | 4.1 | $0.057 | 1/2 | 445ms |
| #210 | LFM2-24B-A2B none | Liquid | 6.3 | 2.2 | $0.001 | 1/2 | 752ms |
| #82 | DeepSeek V4 Pro none | DeepSeek | 6.3 | 6.9 | $0.096 | 1/2 | 4.12s |