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) |
|---|---|---|---|---|---|---|
| #56 | Grok 4.20 Multi Agent Beta medium | X AI | 8.3 | 6.4 | 1/2 | 4.63s |
| #71 | MiniMax M2.5 medium | Minimax | 8.1 | 5.7 | 1/2 | 4.64s |
| #35 | MiMo-V2-Omni medium | Xiaomi | 8.3 | 7.7 | 1/2 | 4.92s |
| #25 | Grok 4.20 Beta medium | X AI | 8.3 | 8.0 | 1/2 | 4.97s |
| #30 | Step 3.5 Flash medium | Stepfun | 8.5 | 7.9 | 1/2 | 4.98s |
| #84 | gpt-oss-120b none | OpenAI | 8.4 | 5.2 | 1/2 | 5.10s |
| #52 | Grok 4.1 Fast medium | X AI | 6.6 | 6.7 | 1/2 | 5.30s |
| #18 | GLM 5 Turbo medium | Z.ai | 10.0 | 8.1 | 2/2 | 5.38s |
| #28 | GPT-5.2 Chat none | OpenAI | 7.5 | 7.9 | 1/2 | 5.46s |
| #1 | Gemini 3 Flash Preview medium | 10.0 | 10.0 | 2/2 | 6.10s | |
| #5 | Gemini 3 Flash Preview low | 9.9 | 8.8 | 2/2 | 7.02s | |
| #13 | GLM 5 medium | Z.ai | 10.0 | 8.4 | 2/2 | 7.25s |
| #6 | Seed-2.0-Lite medium | Bytedance Seed | 10.0 | 8.6 | 2/2 | 7.26s |
| #92 | Qwen3 Coder Next medium | Qwen | 4.8 | 4.7 | 0/2 | 7.34s |
| #33 | GLM 5.1 medium | Z.ai | 6.4 | 7.8 | 1/2 | 7.47s |