Qwen3.6-Plus vs Qwen3.8-Max
| Spec | Qwen3.6-Plus | Qwen3.8-Max |
|---|---|---|
| Respan Index | 35.7 (#79) | 52.9 (#35) |
| Blended price per 1M | $0.62 | $2.48 |
| Context window | 1M | 1M |
| Input / output per 1M | $0.276 / $1.65 | $1.65 / $4.95 |
| Max output | - | 131K |
| Input | text, vision | text, vision |
| Released | 2026-04-02 | 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 | Qwen3.6-Plus | Qwen3.8-Max |
|---|---|---|
| Coding | 7.6 Qwen3.6-Plus | 39.3 Qwen3.8-Max |
| Agents | 57.0 Qwen3.6-Plus | 68.7 Qwen3.8-Max |
| Reasoning | 29.9 Qwen3.6-Plus | 49.4 Qwen3.8-Max |
| Knowledge & language | 41.6 Qwen3.6-Plus | 48.1 Qwen3.8-Max |
| Human preference | 52.6 Qwen3.6-Plus | 58.0 Qwen3.8-Max |
Benchmarks both report
Qwen3.8-Max leads on 15 of the 16 benchmarks both report. Higher is better. Each score links to where it was published.
| Benchmark | Qwen3.6-Plus | Qwen3.8-Max |
|---|---|---|
| LMArena WebDev (LMArena) | 1462 | 1670 |
| LMArena Elo | 1443 | 1484 |
| Chess Puzzles (Epoch AI) | 16% | 46% |
| FrontierMath Tiers 1-3 v2 (Epoch AI) | 38.2% | 74.7% |
| GPQA Diamond | 88.4% | 92.6% |
| LiveBench Agentic Coding (LiveBench) | 41.4% | 64.6% |
| LiveBench Coding (LiveBench) | 78.2% | 72.9% |
| LiveBench Data Analysis (LiveBench) | 69.9% | 78.4% |
| LiveBench Instruction Following (LiveBench) | 58.3% | 74.1% |
| LiveBench Language (LiveBench) | 75% | 79.7% |
| LiveBench Mathematics (LiveBench) | 83.7% | 91.3% |
| LiveBench Reasoning (LiveBench) | 75.8% | 88.2% |
| Mystery Game Puzzles (Epoch AI) | 12% | 38% |
| OTIS Mock AIME 2024-2025 (Epoch AI) | 93.3% | 100% |
| SAGE (Vals AI) | 44.9% | 51.3% |
| SimpleQA Verified | 44.1% | 47.3% |
FAQ
Is Qwen3.6-Plus better than Qwen3.8-Max?
Qwen3.8-Max scores 52.9 on the Respan Index (#35), ahead of Qwen3.6-Plus at 35.7 (#79). Qwen3.8-Max leads on 15 of the 16 benchmarks both report.
Which is cheaper, Qwen3.6-Plus or Qwen3.8-Max?
Qwen3.6-Plus lists at $0.276 input and $1.65 output per 1M tokens; Qwen3.8-Max at $1.65 and $4.95. Qwen3.6-Plus is 4.0x cheaper per token at list price.
Which has the larger context window?
Both accept 1M tokens of context.