AI BENCHY Category
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 ↑.
| Rank | Model | Company | Instructions following Score | Score | Tests Correct | Response Time (avg) |
|---|---|---|---|---|---|---|
| #76 | Kimi K2.5 none | Moonshot AI | 6.5 | 5.5 | 1/2 | 2.67s |
| #77 | GLM 5 Turbo none | Z.ai | 6.5 | 5.5 | 1/2 | 2.13s |
| #83 | Mistral Small 4 none | Mistral | 6.5 | 5.2 | 1/2 | 380ms |
| #90 | Qwen3.5-9B none | Qwen | 6.5 | 4.8 | 1/2 | 514ms |
| #91 | Mercury 2 none | Inception | 6.5 | 4.8 | 1/2 | 551ms |
| #94 | MiMo-V2-Flash none | Xiaomi | 6.5 | 4.5 | 1/2 | 857ms |
| #52 | Grok 4.1 Fast medium | X AI | 6.6 | 6.7 | 1/2 | 5.30s |
| #51 | Nemotron 3 Super medium | NVIDIA | 7.2 | 6.7 | 1/2 | 7.72s |
| #47 | Grok 4.20 medium | X AI | 7.3 | 7.0 | 1/2 | 4.42s |
| #73 | Mistral Small 4 medium | Mistral | 7.3 | 5.7 | 1/2 | 1.38s |
| #44 | GPT-5.4 Mini medium | OpenAI | 7.4 | 7.3 | 1/2 | 2.50s |
| #28 | GPT-5.2 Chat none | OpenAI | 7.5 | 7.9 | 1/2 | 5.46s |
| #11 | Gemini 3.1 Flash Lite Preview high | 7.9 | 8.4 | 1/2 | 70.1s | |
| #62 | Gemini 2.5 Flash none | 8.0 | 6.2 | 1/2 | 672ms | |
| #45 | GPT-5 Mini medium | OpenAI | 8.0 | 7.0 | 1/2 | 15.7s |