Qwen3.8-Flash-Next scores 42.7 on the Respan Index (#39), ahead of Kimi K2.7 Code at 34.1 (#58). Qwen3.8-Flash-Next leads on 7 of the 9 benchmarks both report. Qwen3.8-Flash-Next has the larger context window (1M tokens).
* Estimated: no published scores in that category. How the Respan Index works
| LiveBench Instruction Following (LiveBench) |
| 56.3% |
| 77.1% |
| LiveBench Language (LiveBench) | 77.9% | 74.6% |
| LiveBench Mathematics (LiveBench) | 79.6% | 85.8% |
| LiveBench Reasoning (LiveBench) | 82.8% | 87.4% |
| LMArena WebDev (LMArena) | 1473 | 1638 |
Higher is better. Each score links to where it was published.