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: Metric ↑.
| Rank | Model | Company | Combined Score | Score | Tests Correct | Response Time (avg) |
|---|---|---|---|---|---|---|
| #160 | LFM2-24B-A2B none | Liquid | 3.0 | 4.2 | 0/1 | 0ms |
| #161 | Qwen3.5-9B medium | Qwen | 3.0 | 4.2 | 0/1 | 0ms |
| #162 | Nemotron 3 Nano Omni 30b A3b Reasoning none | NVIDIA | 3.0 | 4.1 | 0/1 | 0ms |
| #163 | Granite 4.1 8B none | IBM Granite | 3.0 | 4.0 | 0/1 | 1.88s |
| #129 | MiniMax M2.5 medium | Minimax | 4.5 | 5.3 | 0/1 | 60.4s |
| #139 | DeepSeek V4 Flash none | DeepSeek | 4.5 | 5.0 | 0/1 | 112.0s |
| #48 | Gemini 3 Flash Preview none | 4.7 | 7.4 | 0/1 | 3.56s | |
| #51 | Mimo V2 PRO medium | Xiaomi | 4.7 | 7.4 | 0/1 | 64.7s |
| #66 | Qwen3.5-35B-A3B medium | Qwen | 4.7 | 7.1 | 0/1 | 75.3s |
| #79 | Hunter Alpha medium | OpenRouter | 4.7 | 6.7 | 0/1 | 30.5s |
| #130 | MiniMax M2.7 medium | Minimax | 4.7 | 5.3 | 0/1 | 41.0s |
| #133 | DeepSeek V3.2 none | DeepSeek | 6.5 | 5.2 | 0/1 | 115.9s |
| #59 | GLM 5V Turbo medium | Z.ai | 6.9 | 7.2 | 0/1 | 15.1s |
| #78 | Qwen3.6 27B medium | Qwen | 7.0 | 6.8 | 0/1 | 83.1s |
| #4 | Gemini 3.1 Pro Preview medium | 9.5 | 9.4 | 1/1 | 40.6s |