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) |
|---|---|---|---|---|---|---|
| #46 | Kimi K2.5 medium | Moonshot AI | 10.0 | 7.0 | 2/2 | 92.5s |
| #11 | Gemini 3.1 Flash Lite Preview high | 7.9 | 8.4 | 1/2 | 70.1s | |
| #32 | Qwen3.5-Flash medium | Qwen | 10.0 | 7.8 | 2/2 | 63.5s |
| #27 | DeepSeek V3.2 medium | DeepSeek | 10.0 | 8.0 | 2/2 | 35.8s |
| #8 | Qwen3.5 Plus 2026-02-15 medium | Qwen | 10.0 | 8.5 | 2/2 | 31.9s |
| #43 | Qwen3.5-35B-A3B medium | Qwen | 10.0 | 7.4 | 2/2 | 24.4s |
| #10 | Qwen3.5-27B medium | Qwen | 10.0 | 8.4 | 2/2 | 19.7s |
| #24 | Gemma 4 26B A4B medium | 10.0 | 8.0 | 2/2 | 17.5s | |
| #39 | Seed-2.0-Mini medium | Bytedance Seed | 10.0 | 7.5 | 2/2 | 17.5s |
| #97 | Qwen3.5-9B medium | Qwen | 6.4 | 4.4 | 1/2 | 17.1s |
| #45 | GPT-5 Mini medium | OpenAI | 8.0 | 7.0 | 1/2 | 15.7s |
| #14 | Gemma 4 31B medium | 10.0 | 8.3 | 2/2 | 12.8s | |
| #80 | MiniMax M2.7 medium | Minimax | 3.7 | 5.3 | 0/2 | 12.6s |
| #34 | Kimi K2.6 medium | Moonshot AI | 10.0 | 7.7 | 2/2 | 12.5s |
| #57 | GPT-5 Nano medium | OpenAI | 8.5 | 6.3 | 1/2 | 11.9s |