Instructions following Ranking
See which AI models perform best on Instructions following, which ones stay reliable, and where the biggest gaps appear. Sort by: Total Cost ↓.
220/220
Filter models
No models match the current search and filters.
| Rank | Model | Company | Instructions following Score | Score | Total Cost | Tests Correct | Response Time (avg) |
|---|---|---|---|---|---|---|---|
| #167 | Laguna S 2.1 high | Poolside | 4.6 | 5.4 | $0.127 | 0/2 | 453ms |
| #101 | GLM 5.2 none | Z.ai | 9.8 | 6.6 | $0.124 | 2/2 | 3.84s |
| #132 | Qwen3.5 Plus 2026-04-20 none | Qwen | 6.2 | 6.1 | $0.122 | 1/2 | 1.17s |
| #69 | Gemini 3.1 Flash Lite medium | 9.9 | 7.3 | $0.117 | 2/2 | 2.59s | |
| #68 | Gemini 3.1 Flash Lite Preview medium | 10.0 | 7.3 | $0.115 | 2/2 | 1.91s | |
| #134 | GPT-5 Nano medium | OpenAI | 9.8 | 6.1 | $0.114 | 2/2 | 15.6s |
| #136 | Step 3.5 Flash medium | Stepfun | 8.3 | 6.0 | $0.108 | 1/2 | 4.78s |
| #116 | Gemma 4 31B medium | 10.0 | 6.3 | $0.107 | 2/2 | 12.8s | |
| #75 | Qwen3.7 Plus none | Qwen | 6.3 | 7.2 | $0.106 | 1/2 | 929ms |
| #133 | Qwen3.5-35B-A3B none | Qwen | 6.3 | 6.1 | $0.106 | 1/2 | 809ms |
| #114 | Ring-2.6-1T medium | Inclusionai | 9.8 | 6.3 | $0.103 | 2/2 | 11.8s |
| #84 | Seed-2.0-Mini medium | Bytedance Seed | 10.0 | 7.0 | $0.101 | 2/2 | 17.5s |
| #175 | Mistral Small 4 medium | Mistral | 7.3 | 5.1 | $0.096 | 1/2 | 1.38s |
| #86 | DeepSeek V4 Pro none | DeepSeek | 6.3 | 6.9 | $0.096 | 1/2 | 4.12s |
| #135 | Nemotron 3 Ultra none | NVIDIA | 10.0 | 6.1 | $0.095 | 2/2 | 1.46s |