Compare / head-to-head
Qwen3.5 397B-A17BvsQwen3.6 27B
Qwen3.6 27B leads 3 of 5 shared benchmarks. Both offer a 262K-token context window.
Benchmarks from cited public sources; pricing from official pages; status from official provider feeds.
Shared benchmarks
2 – 3
Qwen3.6 27B leads
Cheaper per token
—
list price, input + output
Larger context
Tie
both 262K tokens
Provider uptime (30d)
—
Qwen
Qwen3.5 397B-A17B
Qwen · released 2026-02-15
textvision
Qwen3.6 27B
Qwen · released 2026-04-21
textvision
- Context
- 262K
- Max out
- —
- Input /1M
- —
- Output /1M
- —
- Cached /1M
- —
- Scores
- 6 · 5 core
Quality
Benchmark matrix
5 shared · 2 only Qwen3.5 397B-A17B · 0 only Qwen3.6 27B| Benchmark | Qwen3.5 397B-A17B | Qwen3.6 27B | Δ | Edge |
|---|---|---|---|---|
| Reported by both · 5 | ||||
| SWE-bench Verified | 76.4% ↗ | 77.2% ↗ | -0.8 pt | Qwen3.6 27B |
| GPQA Diamond | 88.4% ↗ | 87.8% ↗ | +0.6 pt | Qwen3.5 397B-A17B |
| MMLU-Pro | 87.8% ↗ | 86.2% ↗ | +1.6 pt | Qwen3.5 397B-A17B |
| FrontierMath Tiers 1-3 v2 (Epoch AI run) | 29.5% ↗epoch | 35.1% ↗epoch | -5.6 pt | Qwen3.6 27B |
| OTIS Mock AIME 2024-2025 (Epoch AI run) | 88.9% ↗epoch | 91.1% ↗epoch | -2.2 pt | Qwen3.6 27B |
| Only Qwen3.5 397B-A17B reports · 2 | ||||
| AIME 2026 | 94.2% ↗matharena ⚠ | not reported | — | — |
| LMArena Elo | 1438.3 ↗ | not reported | — | — |
| Only Qwen3.6 27B reports · 0 | ||||
| Qwen3.6 27B reports nothing Qwen3.5 397B-A17B does not. | ||||
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 Qwen3.5 397B-A17B minus Qwen3.6 27B 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 | Qwen3.5 397B-A17B | Qwen3.6 27B | Edge |
|---|---|---|---|
| Context window | 262K tokens | 262K tokens | Tie |
| Max output | — | — | — |
| Input price / 1M | $0.172 ↗ | — | — |
| Output price / 1M | $1.03 ↗ | — | — |
| Cached input / 1M | — | — | — |
| Input + output / 1M Lower is cheaper. List prices; batch, tool and regional fees excluded. | $1.2 | — | — |
| Modalities | text · vision | text · vision | Tie |
| Released | 2026-02-15 | 2026-04-21 | — |
| Cited benchmark scores | 8 | 6 | — |
Reliability
Qwen status
Last 60 days · refreshed daily on this page · live on /statusMore matchups
Qwen3.5 397B-A17B vs …
Models sharing the most benchmarksMore matchups
Qwen3.6 27B vs …
Models sharing the most benchmarksBuilt by Respan
Which one wins on your data?
Public benchmarks are a starting point. Run Qwen3.5 397B-A17B and Qwen3.6 27B on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.