ModelsCompareBest forBenchmarksStatusPricingAPI
Compare / head-to-head

Qwen3 235B-A22BvsQwen3.6 27B

Qwen3.6 27B leads 1 of 1 shared benchmark. Both offer a 262K-token context window.

Benchmarks from cited public sources; pricing from official pages; status from official provider feeds.

Shared benchmarks
0 – 1
Qwen3.6 27B leads
Cheaper per token
list price, input + output
Larger context
Tie
both 262K tokens
Provider uptime (30d)
Qwen
Qwen3 235B-A22B
Qwen · released 2025-04-29
text
Context
262K
Max out
Input /1M
Output /1M
Cached /1M
Scores
4 · 3 core
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

BenchmarkQwen3 235B-A22BQwen3.6 27BΔEdge
Reported by both · 1
GPQA Diamond70.7% epoch87.8% -17.1 ptQwen3.6 27B
Only Qwen3 235B-A22B reports · 3
AIME 202580.8% matharenanot reported
LMArena Elo1366.1 not reported
ARC-AGI-1 (pass@1)40.75% not reported
Only Qwen3.6 27B reports · 4
SWE-bench Verifiednot reported77.2%
MMLU-Pronot reported86.2%
FrontierMath Tiers 1-3 v2 (Epoch AI run)not reported35.1% epoch
OTIS Mock AIME 2024-2025 (Epoch AI run)not reported91.1% epoch
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 235B-A22B 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

SpecQwen3 235B-A22BQwen3.6 27BEdge
Context window262K tokens262K tokensTie
Max output
Input price / 1M
Output price / 1M
Cached input / 1M
Input + output / 1M
Lower is cheaper. List prices; batch, tool and regional fees excluded.
Modalitiestexttext · visionQwen3.6 27B
Released2025-04-292026-04-21
Cited benchmark scores46
Reliability

Qwen status

All providers
More matchups

Qwen3 235B-A22B vs …

Built by Respan
Which one wins on your data?

Public benchmarks are a starting point. Run Qwen3 235B-A22B and Qwen3.6 27B on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.