AI BENCHY Category
Domain specific Ranking
See which AI models perform best on Domain specific, which ones stay reliable, and where the biggest gaps appear. Sort by: Metric ↑.
| Rank | Model | Company | Domain specific Score | Score | Tests Correct | Response Time (avg) |
|---|---|---|---|---|---|---|
| #30 | Step 3.5 Flash medium | Stepfun | 5.3 | 7.9 | 1/3 | 170.5s |
| #31 | GLM 5V Turbo medium | Z.ai | 5.3 | 7.8 | 1/3 | 38.1s |
| #32 | Qwen3.5-Flash medium | Qwen | 5.3 | 7.8 | 1/3 | 146.5s |
| #34 | Kimi K2.6 medium | Moonshot AI | 5.3 | 7.7 | 1/3 | 202.4s |
| #65 | MiMo-V2-Pro none | Xiaomi | 5.3 | 6.0 | 1/3 | 1.78s |
| #66 | GPT-5.4 none | OpenAI | 5.3 | 5.9 | 1/3 | 1.07s |
| #69 | Kimi K2.6 none | Moonshot AI | 5.3 | 5.8 | 1/3 | 1.48s |
| #73 | Mistral Small 4 medium | Mistral | 5.3 | 5.7 | 1/3 | 6.11s |
| #91 | Mercury 2 none | Inception | 5.3 | 4.8 | 1/3 | 534ms |
| #94 | MiMo-V2-Flash none | Xiaomi | 5.3 | 4.5 | 1/3 | 564ms |
| #8 | Qwen3.5 Plus 2026-02-15 medium | Qwen | 5.3 | 8.5 | 1/3 | 17.5s |
| #10 | Qwen3.5-27B medium | Qwen | 5.3 | 8.4 | 1/3 | 79.5s |
| #11 | Gemini 3.1 Flash Lite Preview high | 5.3 | 8.4 | 1/3 | 127.6s | |
| #12 | Gemini 3 PRO Preview medium | 5.3 | 8.4 | 1/3 | 7.01s | |
| #22 | Gemini 3.1 Flash Lite Preview low | 5.3 | 8.1 | 1/3 | 2.36s |