Qwen3.8-Max scores 50.3 on the Respan Index (#22), ahead of GLM-5.3 at 49.4 (#24). Qwen3.8-Max leads on 16 of the 22 benchmarks both report. GLM-5.3 is 1.4x cheaper per token at list price.
* Estimated: no published scores in that category. How the Respan Index works
| 68.8% |
| 74.7% |
| FrontierSWE V2 (Proximal Labs) | 30.2% | 17.8% |
| GPQA Diamond | 90.9% | 92.6% |
| LiveBench Agentic Coding (LiveBench) | 60.9% | 64.6% |
| LiveBench Coding (LiveBench) | 79% | 72.9% |
| LiveBench Data Analysis (LiveBench) | 70.2% | 78.4% |
| LiveBench Instruction Following (LiveBench) | 69.3% | 74.1% |
| LiveBench Language (LiveBench) | 79.9% | 79.7% |
| LiveBench Mathematics (LiveBench) | 87.9% | 91.3% |
| LiveBench Reasoning (LiveBench) | 85.8% | 88.2% |
| Mystery Game Puzzles (Epoch AI) | 33% | 38% |
| OTIS Mock AIME 2024-2025 (Epoch AI) | 91.1% | 99.4% |
| SimpleQA Verified | 41% | 45.8% |
| Terminal-Bench 4.0 (Vals AI) | 38.9% | 34.3% |
| LMArena Agent (LMArena) | 0.0236 | 0.0251 |
| LMArena Elo | 1479 | 1481 |
| LMArena WebDev (LMArena) | 1623 | 1671 |
| Terminal-Bench 2.1 | 88.2% | 86.6% |
Higher is better. Each score links to where it was published.