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) ↑.
461/461
Filter models
No models match the current search and filters.
| Rank | Model | Company | Instructions following Score | Score | Total Cost | Tests Correct | Response Time (avg) |
|---|---|---|---|---|---|---|---|
| #363 | KAT Coder AIR V2.5 low | Kwaipilot | 1.0 | 0.5 | $0.046 | 2/2 | 1.64s |
| #237 | Minimax M3.1 Flash high | Minimax | 0.5 | 0.7 | $0.000 | 0/2 | 1.65s |
| #227 | GLM 5.3 Flash low | Z.ai | 1.0 | 0.7 | $0.038 | 2/2 | 1.65s |
| #456 | Solar Decide Flash default | Upstage | 0.2 | 0.2 | $0.003 | 0/1 | 1.66s |
| #268 | Qwen3.5 Plus 2026-02-15 none | Qwen | 1.0 | 0.6 | $0.176 | 2/2 | 1.67s |
| #319 | Solar Pro 4 none | Upstage | 0.6 | 0.6 | $0.022 | 1/2 | 1.67s |
| #427 | Laguna Xs.2 medium | Poolside | 1.0 | 0.3 | $0.015 | 2/2 | 1.68s |
| #286 | Inkling none | Thinkingmachines | 0.6 | 0.6 | $0.292 | 1/2 | 1.72s |
| #176 | Gemini 3.5 Flash Lite medium | 1.0 | 0.7 | $0.440 | 2/2 | 1.72s | |
| #265 | Minimax M3.1 Flash medium | Minimax | 0.5 | 0.6 | $0.000 | 0/2 | 1.72s |
| #252 | Minimax M3.1 Flash xhigh | Minimax | 0.5 | 0.6 | $0.000 | 0/2 | 1.72s |
| #164 | GLM 5.3 FlashX high | Z.ai | 1.0 | 0.7 | $0.210 | 2/2 | 1.72s |
| #108 | DeepSeek V4.1 Flash 1017 max | DeepSeek | 1.0 | 0.8 | $0.757 | 2/2 | 1.73s |
| #203 | Minimax M3.1 Flash max | Minimax | 0.5 | 0.7 | $0.000 | 0/2 | 1.73s |
| #263 | Gemini 3.5 Flash Lite low | 1.0 | 0.6 | $0.183 | 2/2 | 1.75s |