Qwen3.7-Max scores 40.5 on the Respan Index (#45), ahead of Kimi K2.6 at 34.4 (#55). Qwen3.7-Max leads on 13 of the 17 benchmarks both report. Kimi K2.6 is 2.2x cheaper per token at list price. Qwen3.7-Max has the larger context window (1M tokens).
* Estimated: no published scores in that category. How the Respan Index works
| 90.8% |
| 90.9% |
| LiveBench Agentic Coding (LiveBench) | 46.9% | 43.6% |
| LiveBench Coding (LiveBench) | 78.6% | 74.2% |
| LiveBench Data Analysis (LiveBench) | 65.1% | 71.8% |
| LiveBench Instruction Following (LiveBench) | 64.4% | 74% |
| LiveBench Language (LiveBench) | 75.1% | 79.7% |
| LiveBench Mathematics (LiveBench) | 84.3% | 85.2% |
| LiveBench Reasoning (LiveBench) | 79.4% | 83.3% |
| Mystery Game Puzzles (Epoch AI) | 18% | 32% |
| OTIS Mock AIME 2024-2025 (Epoch AI) | 96.1% | 95.6% |
| SimpleQA Verified | 34.9% | 55.8% |
| SWE-bench Verified (Epoch AI) | 76.7% | 77.3% |
| LMArena WebDev (LMArena) | 1509 | 1515 |
Higher is better. Each score links to where it was published.