Claude Haiku 4.5 scores 18.2 on the Respan Index (#105), ahead of Qwen3-Max at 18.0 (#106). Qwen3-Max leads on 5 of the 8 benchmarks both report. Claude Haiku 4.5 is 1.2x cheaper per token at list price. Qwen3-Max has the larger context window (262K tokens).
* Estimated: no published scores in that category. How the Respan Index works
| 13.2% |
| 48.7% |
| Vending-Bench 2 (Andon Labs) | 458.89 | 71.57 |
| LMArena Elo | 1414 | 1423 |
| SWE-bench Verified | 73.3% | 69.6% |
Higher is better. Each score links to where it was published.