Qwen3.7-Max vs Qwen3.8-Flash-Next
| Spec | Qwen3.7-Max | Qwen3.8-Flash-Next |
|---|---|---|
| Respan Index | 43.1 (#52) | 44.3 (#50) |
| Blended price per 1M | $1.88 | - |
| Context window | 1M | 1M |
| Input / output per 1M | $1.25 / $3.75 | - |
| Max output | - | - |
| Input | text, vision | text, vision |
| Released | 2026-05-20 | - |
Respan Index by category
Each category is scored 0 to 100, and how far ahead the winner is. Leads under a point are close to even.
| Category | Qwen3.7-Max | Qwen3.8-Flash-Next |
|---|---|---|
| Coding | 16.6 Qwen3.7-Max | 25.7 Qwen3.8-Flash-Next |
| Agents | 53.0 Qwen3.7-Max | 56.1 Qwen3.8-Flash-Next |
| Reasoning | 48.5 Qwen3.7-Max | 43.3 Qwen3.8-Flash-Next |
| Knowledge & language | 55.0 Qwen3.7-Max | 44.9 Qwen3.8-Flash-Next |
| Human preference | 53.7 Qwen3.7-Max | 56.7 Qwen3.8-Flash-Next |
Benchmarks both report
Qwen3.8-Flash-Next leads on 8 of the 10 benchmarks both report. Higher is better. Each score links to where it was published.
| Benchmark | Qwen3.7-Max | Qwen3.8-Flash-Next |
|---|---|---|
| LMArena Agent (LMArena) | -0.0659 | -0.0402 |
| LMArena WebDev (LMArena) | 1515 | 1628 |
| GPQA Diamond | 90.9% | 91.7% |
| LiveBench Agentic Coding (LiveBench) | 43.6% | 61.6% |
| LiveBench Coding (LiveBench) | 74.2% | 72.6% |
| LiveBench Data Analysis (LiveBench) | 71.8% | 74.2% |
| LiveBench Instruction Following (LiveBench) | 74% | 77.1% |
| LiveBench Language (LiveBench) | 79.7% | 74.6% |
| LiveBench Mathematics (LiveBench) | 85.2% | 85.8% |
| LiveBench Reasoning (LiveBench) | 83.3% | 87.4% |
FAQ
Is Qwen3.7-Max better than Qwen3.8-Flash-Next?
Qwen3.8-Flash-Next scores 44.3 on the Respan Index (#50), ahead of Qwen3.7-Max at 43.1 (#52). Qwen3.8-Flash-Next leads on 8 of the 10 benchmarks both report.
Which has the larger context window?
Both accept 1M tokens of context.