Qwen3.7-Max vs Qwen3.8-Max
| Spec | Qwen3.7-Max | Qwen3.8-Max |
|---|---|---|
| Respan Index | 43.1 (#63) | 52.8 (#35) |
| Blended price per 1M | $1.88 | $2.48 |
| Context window | 1M | 1M |
| Input / output per 1M | $1.25 / $3.75 | $1.65 / $4.95 |
| Max output | - | 131K |
| Input | text, vision | text, vision |
| Released | 2026-05-20 | 2026-08-02 |
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-Max |
|---|---|---|
| Coding | 16.7 Qwen3.7-Max | 39.3 Qwen3.8-Max |
| Agents | 52.7 Qwen3.7-Max | 68.6 Qwen3.8-Max |
| Reasoning | 48.6 Qwen3.7-Max | 49.4 Qwen3.8-Max |
| Knowledge & language | 55.0 Qwen3.7-Max | 48.1 Qwen3.8-Max |
| Human preference | 54.0 Qwen3.7-Max | 58.0 Qwen3.8-Max |
Benchmarks both report
Qwen3.8-Max leads on 13 of the 16 benchmarks both report. Higher is better. Each score links to where it was published.
| Benchmark | Qwen3.7-Max | Qwen3.8-Max |
|---|---|---|
| LMArena Agent (LMArena) | -0.0825 | -0.0091 |
| Chess Puzzles (Epoch AI) | 27% | 46% |
| LMArena WebDev (LMArena) | 1515 | 1671 |
| FrontierMath Tier 4 v2 (Epoch AI) | 34.1% | 46.3% |
| FrontierMath Tiers 1-3 v2 (Epoch AI) | 64.6% | 74.7% |
| GPQA Diamond | 90.9% | 92.6% |
| LiveBench Agentic Coding (LiveBench) | 43.6% | 64.6% |
| LiveBench Coding (LiveBench) | 74.2% | 72.9% |
| LiveBench Data Analysis (LiveBench) | 71.8% | 78.4% |
| LiveBench Instruction Following (LiveBench) | 74% | 74.1% |
| LiveBench Language (LiveBench) | 79.7% | 79.7% |
| LiveBench Mathematics (LiveBench) | 85.2% | 91.3% |
| LiveBench Reasoning (LiveBench) | 83.3% | 88.2% |
| Mystery Game Puzzles (Epoch AI) | 32% | 38% |
| OTIS Mock AIME 2024-2025 (Epoch AI) | 95.6% | 100% |
| SimpleQA Verified | 55.8% | 47.3% |
FAQ
Is Qwen3.7-Max better than Qwen3.8-Max?
Qwen3.8-Max scores 52.8 on the Respan Index (#35), ahead of Qwen3.7-Max at 43.1 (#63). Qwen3.8-Max leads on 13 of the 16 benchmarks both report.
Which is cheaper, Qwen3.7-Max or Qwen3.8-Max?
Qwen3.7-Max lists at $1.25 input and $3.75 output per 1M tokens; Qwen3.8-Max at $1.65 and $4.95. Qwen3.7-Max is 1.3x cheaper per token at list price.
Which has the larger context window?
Both accept 1M tokens of context.