AI BENCHY Category
Combined Ranking
See which AI models perform best on Combined, which ones stay reliable, and where the biggest gaps appear. Sort by: Tests Correct ↓.
| Rank | Model | Company | Combined Score | Score | Tests Correct | Response Time (avg) |
|---|---|---|---|---|---|---|
| #19 | Qwen3.5-122B-A10B medium | Qwen | 10.0 | 8.1 | 1/1 | 107.8s |
| #20 | Qwen3.6 Plus medium | Qwen | 10.0 | 8.1 | 1/1 | 35.0s |
| #24 | Gemma 4 26B A4B medium | 9.6 | 8.0 | 1/1 | 73.5s | |
| #25 | Grok 4.20 Beta medium | X AI | 10.0 | 8.0 | 1/1 | 20.9s |
| #26 | Claude Sonnet 4.6 medium | Anthropic | 10.0 | 8.0 | 1/1 | 46.4s |
| #27 | DeepSeek V3.2 medium | DeepSeek | 10.0 | 8.0 | 1/1 | 93.1s |
| #28 | GPT-5.2 Chat none | OpenAI | 10.0 | 7.9 | 1/1 | 9.12s |
| #30 | Step 3.5 Flash medium | Stepfun | 10.0 | 7.9 | 1/1 | 29.6s |
| #32 | Qwen3.5-Flash medium | Qwen | 10.0 | 7.8 | 1/1 | 17.8s |
| #33 | GLM 5.1 medium | Z.ai | 9.5 | 7.8 | 1/1 | 43.1s |
| #34 | Kimi K2.6 medium | Moonshot AI | 10.0 | 7.7 | 1/1 | 41.0s |
| #35 | MiMo-V2-Omni medium | Xiaomi | 10.0 | 7.7 | 1/1 | 19.3s |
| #36 | GPT-5.3 Chat none | OpenAI | 10.0 | 7.7 | 1/1 | 12.0s |
| #37 | Claude Opus 4.6 medium | Anthropic | 10.0 | 7.6 | 1/1 | 76.7s |
| #38 | GPT-5.4 Nano medium | OpenAI | 9.8 | 7.6 | 1/1 | 24.1s |