ModelsCompareBest forBenchmarksStatusPricingAPI
Compare / head-to-head

Gemma 4 26B A4BvsQwen3 235B-A22B

Gemma 4 26B A4B leads 2 of 2 shared benchmarks. Qwen3 235B-A22B has the larger context window (262K tokens).

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

Shared benchmarks
2 – 0
Gemma 4 26B A4B leads
Cheaper per token
list price, input + output
Larger context
Qwen3 235B-A22B
262K tokens
Provider uptime (30d)
100% · —
Google · Qwen
Gemma 4 26B A4B
Google · released 2026-04-02
textvision
Context
256K
Max out
Input /1M
Output /1M
Cached /1M
Scores
6 · 5 core
Qwen3 235B-A22B
Qwen · released 2025-04-29
text
Context
262K
Max out
Input /1M
Output /1M
Cached /1M
Scores
4 · 3 core
Quality

Benchmark matrix

BenchmarkGemma 4 26B A4BQwen3 235B-A22BΔEdge
Reported by both · 2
GPQA Diamond82.3% 70.7% epoch+11.6 ptGemma 4 26B A4B
LMArena Elo1434.5 1366.1 +68.4Gemma 4 26B A4B
Only Gemma 4 26B A4B reports · 4
MMLU-Pro82.6% not reported
AIME 202688.3% not reported
Humanity's Last Exam (no tools)8.7% not reported
LiveCodeBench v677.1% not reported
Only Qwen3 235B-A22B reports · 2
AIME 2025not reported80.8% matharena
ARC-AGI-1 (pass@1)not reported40.75%
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 Gemma 4 26B A4B minus Qwen3 235B-A22B 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

SpecGemma 4 26B A4BQwen3 235B-A22BEdge
Context window256K tokens262K tokensQwen3 235B-A22B
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.
Modalitiestext · visiontextGemma 4 26B A4B
Released2026-04-022025-04-29
Cited benchmark scores64
Reliability

Provider 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 Gemma 4 26B A4B and Qwen3 235B-A22B on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.