Compare / head-to-head
Qwen3.8-MaxvsQwen3-Max
Qwen3.8-Max leads 3 of 4 shared benchmarks. Qwen3.8-Max is 1.1x cheaper per token. Qwen3.8-Max has the larger context window (1M tokens).
Benchmarks from cited public sources; pricing from official pages; status from official provider feeds.
Shared benchmarks
3 – 1
Qwen3.8-Max leads
Cheaper per token
Qwen3.8-Max
1.1x cheaper, input + output
Larger context
Qwen3.8-Max
1M tokens
Provider uptime (30d)
—
Qwen
Qwen3.8-Max
Qwen · released 2026-08-02
textvision
Quality
Benchmark matrix
4 shared · 4 only Qwen3.8-Max · 1 only Qwen3-Max| Benchmark | Qwen3.8-Max | Qwen3-Max | Δ | Edge |
|---|---|---|---|---|
| Reported by both · 4 | ||||
| GPQA Diamond | 92.6% ↗ | 72.6% ↗epoch | +20 pt | Qwen3.8-Max |
| FrontierMath Tiers 1-3 v2 (Epoch AI run) | 74.7% ↗epoch | 18.9% ↗epoch | +55.8 pt | Qwen3.8-Max |
| OTIS Mock AIME 2024-2025 (Epoch AI run) | 99.4% ↗epoch | 73.3% ↗epoch | +26.1 pt | Qwen3.8-Max |
| SimpleQA Verified | 45.8% ↗epoch | 48.7% ↗epoch | -2.9 pt | Qwen3-Max |
| Only Qwen3.8-Max reports · 4 | ||||
| LMArena Elo | 1480.6 ↗ | not reported | — | — |
| FrontierMath Tier 4 v2 (Epoch AI run) | 46.3% ↗epoch | not reported | — | — |
| SWE-Bench Pro | 67.7% ↗ | not reported | — | — |
| Terminal-Bench 2.1 | 86.6% ↗ | not reported | — | — |
| Only Qwen3-Max reports · 1 | ||||
| SWE-bench Verified | not reported | 69.6% ↗ | — | — |
Scores tagged "epoch" or "matharena" are independent runs, used only where the lab has not published its own; ⚠ marks rows MathArena flags as released after the competition. Higher is better on every row. Δ is Qwen3.8-Max minus Qwen3-Max in the benchmark's own unit. "Not reported" means the lab has not published that figure; it is not a zero. ↗ opens the source.
Specs & pricing
Side by side
Official pricing pages and model cards| Spec | Qwen3.8-Max | Qwen3-Max | Edge |
|---|---|---|---|
| Context window | 1M tokens | 262K tokens | Qwen3.8-Max |
| Max output | 131K tokens | — | — |
| Input price / 1M | $1.65 ↗ | $1.2 ↗ | Qwen3-Max |
| Output price / 1M | $4.95 ↗ | $6 ↗ | Qwen3.8-Max |
| Cached input / 1M | — | $0.12 ↗ | — |
| Input + output / 1M Lower is cheaper. List prices; batch, tool and regional fees excluded. | $6.6 | $7.2 | Qwen3.8-Max |
| Modalities | text · vision | text | Qwen3.8-Max |
| Released | 2026-08-02 | 2025-09-23 | — |
| Cited benchmark scores | 9 | 5 | — |
Reliability
Qwen status
Last 60 days · refreshed daily on this page · live on /statusMore matchups
Qwen3.8-Max vs …
Models sharing the most benchmarksMore matchups
Qwen3-Max vs …
Models sharing the most benchmarksBuilt by Respan
Which one wins on your data?
Public benchmarks are a starting point. Run Qwen3.8-Max and Qwen3-Max on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.