Combined Ranking
See which AI models perform best on Combined, which ones stay reliable, and where the biggest gaps appear. Sort by: Metric ↑.
220/220
Filter models
No models match the current search and filters.
| Rank | Model | Company | Combined Score | Score | Total Cost | Tests Correct | Response Time (avg) |
|---|---|---|---|---|---|---|---|
| #111 | Gemini 3.1 Flash Lite low | 3.2 | 6.5 | $0.621 | 0/2 | 161.2s | |
| #158 | Qwen3.6 27B none | Qwen | 3.2 | 5.5 | $0.087 | 0/2 | 83.1s |
| #164 | Laguna S 2.1 medium | Poolside | 3.2 | 5.4 | $0.059 | 0/2 | 284.7s |
| #166 | GPT-5.6 Luna none | OpenAI | 3.2 | 5.4 | $0.142 | 0/2 | 6.68s |
| #179 | North Mini Code none | Cohere | 3.2 | 5.1 | $0.000 | 0/2 | 96.2s |
| #98 | GLM 5V Turbo medium | Z.ai | 3.4 | 6.7 | $0.457 | 0/1 | 15.1s |
| #199 | MiniMax M2.5 medium | Minimax | 3.7 | 4.6 | $0.340 | 0/2 | 83.2s |
| #93 | Gemini 3 Flash Preview none | 3.8 | 6.8 | $0.085 | 0/2 | 12.4s | |
| #104 | Gemini 3.5 Flash-Lite medium | 3.8 | 6.5 | $0.369 | 0/2 | 28.7s | |
| #180 | MiniMax M2.7 medium | Minimax | 3.8 | 5.0 | $0.163 | 0/2 | 72.1s |
| #191 | KAT-Coder-Air V2.5 none | Kwaipilot | 3.8 | 4.8 | $0.067 | 0/2 | 73.0s |
| #121 | Gemma 4 31B none | 3.8 | 6.2 | $0.021 | 0/2 | 30.0s | |
| #125 | Qwen3.5-35B-A3B medium | Qwen | 3.8 | 6.2 | $0.837 | 0/2 | 512.8s |
| #130 | Qwen3.6 Flash none | Qwen | 3.8 | 6.1 | $0.062 | 0/2 | 26.5s |
| #133 | Qwen3.5-35B-A3B none | Qwen | 3.8 | 6.1 | $0.106 | 0/2 | 128.3s |