Instructions following Ranking
See which AI models perform best on Instructions following, which ones stay reliable, and where the biggest gaps appear. Sort by: Tests Correct ↓.
316/316
Filter models
No models match the current search and filters.
| Rank | Model | Company | Instructions following Score | Score | Total Cost | Tests Correct | Response Time (avg) |
|---|---|---|---|---|---|---|---|
| #249 | Ling-2.6-1T none | Inclusionai | 6.4 | 5.3 | $0.016 | 1/2 | 5.36s |
| #251 | Qwen3.6 35B A3B none | Qwen | 6.2 | 5.3 | $0.051 | 1/2 | 1.86s |
| #253 | Inkling none | Thinkingmachines | 6.3 | 5.2 | $0.147 | 1/2 | 1.72s |
| #255 | Nemotron 3.5 Lightning medium | NVIDIA | 8.5 | 5.1 | $0.156 | 1/2 | 3.75s |
| #256 | Mistral Small 4 none | Mistral | 6.5 | 5.1 | $0.022 | 1/2 | 380ms |
| #257 | Mistral Small 4 medium | Mistral | 7.3 | 5.1 | $0.097 | 1/2 | 1.38s |
| #259 | Qwen3 Coder Next none | Qwen | 6.3 | 5.1 | $0.026 | 1/2 | 7.78s |
| #260 | MiMo-V2.5 none | Xiaomi | 6.5 | 5.1 | $0.025 | 1/2 | 751ms |
| #261 | Qwen3.5-9B none | Qwen | 6.5 | 5.1 | $0.021 | 1/2 | 514ms |
| #262 | GLM 5 Turbo none | Z.ai | 6.5 | 5.1 | $0.047 | 1/2 | 2.13s |
| #263 | North Mini Code none | Cohere | 6.5 | 5.1 | $0.000 | 1/2 | 30.7s |
| #265 | Mercury 2.5 Preview low | Inception | 6.3 | 5.0 | $0.011 | 1/2 | 1.60s |
| #268 | GPT-4o-mini none | OpenAI | 6.3 | 5.0 | $0.010 | 1/2 | 1.11s |
| #269 | Qwen3.6 Plus Preview medium | Qwen | 6.5 | 4.9 | $0.000 | 1/2 | 3.40s |
| #270 | Mercury 2.5 Preview none | Inception | 6.3 | 4.9 | $0.018 | 1/2 | 1.26s |