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) |
|---|---|---|---|---|---|---|
| #75 | Ring-2.6-1T medium | Inclusionai | 9.8 | 6.9 | 2/2 | 11.8s |
| #47 | Grok Build 0.1 medium | X AI | 9.8 | 7.4 | 2/2 | 12.4s |
| #60 | Kimi K2.6 medium | Moonshot AI | 10.0 | 7.2 | 2/2 | 12.5s |
| #27 | Gemma 4 31B medium | 10.0 | 7.8 | 2/2 | 12.8s | |
| #130 | MiniMax M2.7 medium | Minimax | 3.8 | 5.3 | 0/2 | 12.8s |
| #156 | Hy3 preview none | Tencent | 6.3 | 4.4 | 1/2 | 13.0s |
| #31 | DeepSeek V4 Flash high | DeepSeek | 10.0 | 7.7 | 2/2 | 15.4s |
| #94 | GPT-5 Nano medium | OpenAI | 9.8 | 6.3 | 2/2 | 15.6s |
| #89 | Hy3 preview low | Tencent | 10.0 | 6.4 | 2/2 | 16.0s |
| #18 | Qwen3.7 Plus medium | Qwen | 10.0 | 8.2 | 2/2 | 16.1s |
| #73 | Seed-2.0-Mini medium | Bytedance Seed | 10.0 | 6.9 | 2/2 | 17.5s |
| #37 | Gemma 4 26B A4B medium | 10.0 | 7.6 | 2/2 | 17.5s | |
| #139 | DeepSeek V4 Flash none | DeepSeek | 6.5 | 5.0 | 1/2 | 17.5s |
| #38 | Grok 4.3 medium | X AI | 9.8 | 7.6 | 2/2 | 18.6s |
| #30 | Qwen3.5-27B medium | Qwen | 10.0 | 7.8 | 2/2 | 19.7s |