Compare AI models

Specifications
Parameters
1B/4B/12B/27B4B/30B/235B
Context window
—256k
API pricing
Cheapest input
$0.04DeepInfra—
Cheapest output
$0.05Parasail—
$10.50Parasail · bf16—
Benchmarks
LiveCodeBench
29.7%74.1%
IFEval
90.4%87.8%
GPQA Diamond
42.4%81.1%
MMLU-Pro
67.5%84.4%
Overview
CompanyGoogleQwen
Release dateMar 12 2025Jul 21 2025
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Qwen3-2507 leads Gemma 3 on 3 of the 4 benchmarks they both report (LiveCodeBench, IFEval, GPQA Diamond, MMLU-Pro). Gemma 3 shipped 131 days before Qwen3-2507, so benchmark comparisons should account for the intervening progress.

Gemma 3 has 1B/4B/12B/27B parameters, while Qwen3-2507 has 4B/30B/235B.

On LiveCodeBench, Qwen3-2507 leads at 74.1% vs Gemma 3 at 29.7%. On IFEval, Gemma 3 leads at 90.4% vs Qwen3-2507 at 87.8%. On GPQA Diamond, Qwen3-2507 leads at 81.1% vs Gemma 3 at 42.4%. On MMLU-Pro, Qwen3-2507 leads at 84.4% vs Gemma 3 at 67.5%.