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: Response Time (avg) ↓.
| Rank | Model | Company | Instructions following Score | Score | Tests Correct | Response Time (avg) |
|---|---|---|---|---|---|---|
| #29 | Gemini 3.1 Flash Lite Preview none | 10.0 | 7.9 | 2/2 | 1.13s | |
| #78 | Trinity Large Preview none | Arcee AI | 4.1 | 5.3 | 0/2 | 1.09s |
| #98 | LFM2-24B-A2B none | Liquid | 4.8 | 4.1 | 0/2 | 1.09s |
| #60 | Gemma 4 26B A4B none | 4.4 | 6.2 | 0/2 | 1.08s | |
| #66 | GPT-5.4 none | OpenAI | 6.5 | 5.9 | 1/2 | 1.07s |
| #54 | Mercury 2 medium | Inception | 10.0 | 6.5 | 2/2 | 1.07s |
| #61 | Seed-2.0-Lite none | Bytedance Seed | 10.0 | 6.2 | 2/2 | 1.06s |
| #85 | Elephant none | Openrouter | 9.8 | 5.2 | 2/2 | 1.03s |
| #81 | Elephant medium | Openrouter | 9.8 | 5.2 | 2/2 | 987ms |
| #95 | Grok 4.1 Fast none | X AI | 3.0 | 4.5 | 0/2 | 923ms |
| #74 | GLM 4.7 Flash none | Z.ai | 6.5 | 5.6 | 1/2 | 888ms |
| #94 | MiMo-V2-Flash none | Xiaomi | 6.5 | 4.5 | 1/2 | 857ms |
| #67 | Qwen3.5-27B none | Qwen | 4.8 | 5.9 | 0/2 | 815ms |
| #63 | Qwen3.5-35B-A3B none | Qwen | 6.3 | 6.1 | 1/2 | 809ms |
| #96 | GPT-5.4 Nano none | OpenAI | 5.0 | 4.5 | 0/2 | 787ms |