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.
| Rank | Model | Company | Instructions following Score | Score | Tests Correct | Response Time (avg) |
|---|---|---|---|---|---|---|
| #20 | Qwen3.6 Plus medium | Qwen | 10.0 | 8.1 | 2/2 | 7.54s |
| #22 | Gemini 3.1 Flash Lite Preview low | 10.0 | 8.1 | 2/2 | 1.49s | |
| #24 | Gemma 4 26B A4B medium | 10.0 | 8.0 | 2/2 | 17.5s | |
| #26 | Claude Sonnet 4.6 medium | Anthropic | 10.0 | 8.0 | 2/2 | 2.61s |
| #27 | DeepSeek V3.2 medium | DeepSeek | 10.0 | 8.0 | 2/2 | 35.8s |
| #29 | Gemini 3.1 Flash Lite Preview none | 10.0 | 7.9 | 2/2 | 1.13s | |
| #32 | Qwen3.5-Flash medium | Qwen | 10.0 | 7.8 | 2/2 | 63.5s |
| #34 | Kimi K2.6 medium | Moonshot AI | 10.0 | 7.7 | 2/2 | 12.5s |
| #37 | Claude Opus 4.6 medium | Anthropic | 10.0 | 7.6 | 2/2 | 2.43s |
| #39 | Seed-2.0-Mini medium | Bytedance Seed | 10.0 | 7.5 | 2/2 | 17.5s |
| #41 | MiMo-V2-Flash medium | Xiaomi | 10.0 | 7.5 | 2/2 | 4.28s |
| #43 | Qwen3.5-35B-A3B medium | Qwen | 10.0 | 7.4 | 2/2 | 24.4s |
| #46 | Kimi K2.5 medium | Moonshot AI | 10.0 | 7.0 | 2/2 | 92.5s |
| #49 | Qwen3.5 Plus 2026-02-15 none | Qwen | 10.0 | 6.8 | 2/2 | 1.67s |
| #53 | GLM 5 none | Z.ai | 10.0 | 6.6 | 2/2 | 1.48s |