Compare / head-to-head
Qwen3.5 35B-A3BvsQwen3.8 27B
Qwen3.8 27B leads 2 of 2 shared benchmarks. Qwen3.5 35B-A3B is 4.1x cheaper per token. Both offer a 262K-token context window.
Benchmarks from cited public sources; pricing from official pages; status from official provider feeds.
Shared benchmarks
0 – 2
Qwen3.8 27B leads
Cheaper per token
Qwen3.5 35B-A3B
4.1x cheaper, input + output
Larger context
Tie
both 262K tokens
Provider uptime (30d)
—
Qwen
Qwen3.5 35B-A3B
Qwen
textvision
Qwen3.8 27B
Qwen · released 2026-08-14
textvision
Quality
Benchmark matrix
2 shared · 2 only Qwen3.5 35B-A3B · 2 only Qwen3.8 27B| Benchmark | Qwen3.5 35B-A3B | Qwen3.8 27B | Δ | Edge |
|---|---|---|---|---|
| Reported by both · 2 | ||||
| GPQA Diamond | 83.5% ↗epoch | 89.2% ↗ | -5.7 pt | Qwen3.8 27B |
| LMArena Elo | 1395.5 ↗ | 1439.3 ↗ | -43.8 | Qwen3.8 27B |
| Only Qwen3.5 35B-A3B reports · 2 | ||||
| AIME 2026 | 93.3% ↗matharena ⚠ | not reported | — | — |
| OTIS Mock AIME 2024-2025 (Epoch AI run) | 54.4% ↗epoch | not reported | — | — |
| Only Qwen3.8 27B reports · 2 | ||||
| SWE-Bench Pro | not reported | 61.7% ↗ | — | — |
| Terminal-Bench 2.1 | not reported | 73% ↗ | — | — |
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 35B-A3B minus Qwen3.8 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 35B-A3B | Qwen3.8 27B | Edge |
|---|---|---|---|
| Context window | 262K tokens | 262K tokens | Tie |
| Max output | — | — | — |
| Input price / 1M | $0.057 ↗ | $0.424 ↗ | Qwen3.5 35B-A3B |
| Output price / 1M | $0.459 ↗ | $1.7 ↗ | Qwen3.5 35B-A3B |
| Cached input / 1M | — | — | — |
| Input + output / 1M Lower is cheaper. List prices; batch, tool and regional fees excluded. | $0.516 | $2.12 | Qwen3.5 35B-A3B |
| Modalities | text · vision | text · vision | Tie |
| Released | — | 2026-08-14 | — |
| Cited benchmark scores | 4 | 4 | — |
Reliability
Qwen status
Last 60 days · refreshed daily on this page · live on /statusMore matchups
Qwen3.5 35B-A3B vs …
Models sharing the most benchmarksMore matchups
Qwen3.8 27B vs …
Models sharing the most benchmarksBuilt by Respan
Which one wins on your data?
Public benchmarks are a starting point. Run Qwen3.5 35B-A3B and Qwen3.8 27B on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.