Qwen3.7-Max scores 40.5 on the Respan Index (#45), ahead of GLM-5.3-Flash at 40.4 (#47). Qwen3.7-Max leads on 10 of the 15 benchmarks both report. GLM-5.3-Flash is 16x cheaper per token at list price.
* Estimated: no published scores in that category. How the Respan Index works
| 56.8% |
| 43.6% |
| LiveBench Coding (LiveBench) | 79% | 74.2% |
| LiveBench Data Analysis (LiveBench) | 76.4% | 71.8% |
| LiveBench Instruction Following (LiveBench) | 52.8% | 74% |
| LiveBench Language (LiveBench) | 77.3% | 79.7% |
| LiveBench Mathematics (LiveBench) | 81.2% | 85.2% |
| LiveBench Reasoning (LiveBench) | 77.6% | 83.3% |
| Mystery Game Puzzles (Epoch AI) | 8% | 32% |
| OTIS Mock AIME 2024-2025 (Epoch AI) | 93.9% | 95.6% |
| LMArena Agent (LMArena) | -0.0044 | -0.0513 |
| LMArena WebDev (LMArena) | 1616 | 1515 |
Higher is better. Each score links to where it was published.