Combined Ranking
See which AI models perform best on Combined, which ones stay reliable, and where the biggest gaps appear. Sort by: Response Time (avg) ↓.
330/330
Filter models
No models match the current search and filters.
| Rank | Model | Company | Combined Score | Score | Total Cost | Tests Correct | Response Time (avg) |
|---|---|---|---|---|---|---|---|
| #29 | Qwen3.8 Max medium | Qwen | 8.7 | 9.0 | $0.771 | 1/2 | 91.3s |
| #124 | GLM 5.3 Flash high | Z.ai | 6.4 | 7.3 | $0.034 | 1/2 | 91.1s |
| #82 | Qwen3.8 27B low | Qwen | 10.0 | 7.9 | ~$0.071 | 2/2 | 90.6s |
| #148 | Kimi K2.5 medium | Moonshot AI | 6.7 | 7.0 | $0.479 | 1/2 | 89.2s |
| #75 | DeepSeek V4 Flash 0731 high | DeepSeek | 10.0 | 8.0 | $0.058 | 2/2 | 87.1s |
| #185 | Dots 3 Note Preview low | Dots Studio | 6.9 | 6.4 | $0.000 | 1/2 | 85.2s |
| #66 | Gemini 2.5 Flash medium | 10.0 | 8.2 | $0.644 | 2/2 | 84.5s | |
| #11 | Gemini 3.5 Flash high | 8.2 | 9.4 | $2.011 | 1/2 | 84.1s | |
| #301 | MiniMax M2.5 medium | Minimax | 3.7 | 4.6 | $0.327 | 0/2 | 83.2s |
| #244 | Qwen3.6 27B none | Qwen | 3.2 | 5.5 | $0.062 | 0/2 | 83.1s |
| #81 | Step 3.7 Flash medium | Stepfun | 7.3 | 7.9 | $0.495 | 1/2 | 80.9s |
| #142 | DeepSeek V3.2 medium | DeepSeek | 7.3 | 7.0 | $0.078 | 1/2 | 79.9s |
| #96 | DeepSeek V4 Pro high | DeepSeek | 10.0 | 7.7 | $0.761 | 2/2 | 79.0s |
| #245 | Hy3 preview low | Tencent | 5.0 | 5.5 | $0.042 | 1/1 | 78.7s |
| #259 | Seed-2.0-Code none | Bytedance Seed | 3.0 | 5.3 | $0.151 | 0/2 | 78.4s |