Compare AI models

Specifications
Parameters
119B4B/30B/235B
Context window
256k256k
API pricing
Input price
$0.15—
Output price
$0.60—
Cached input price
$0.015—
Cheapest input
$0.15Mistral—
Cheapest output
$0.60Mistral—
$60.00Mistral list price—
Benchmarks
LiveCodeBench
63.6%74.1%
AIME 2025
83.8%92.3%
GPQA Diamond
71.2%81.1%
MMLU-Pro
78%84.4%
Overview
CompanyMistralQwen
Release dateMar 16 2026Jul 21 2025
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Qwen3-2507 leads Mistral Small 4 on 4 of the 4 benchmarks they both report (LiveCodeBench, AIME 2025, GPQA Diamond, MMLU-Pro). Only Mistral Small 4 has a verified first-party price for an available API: $0.15 per million input tokens and $0.60 per million output tokens. No currently available pay-as-you-go API rate is tracked for Qwen3-2507. Qwen3-2507 shipped 238 days before Mistral Small 4, so benchmark comparisons should account for the intervening progress.

Mistral Small 4 has 119B parameters, while Qwen3-2507 has 4B/30B/235B. Context windows are 256k (Mistral Small 4) vs 256k (Qwen3-2507).

On LiveCodeBench, Qwen3-2507 leads at 74.1% vs Mistral Small 4 at 63.6%. On AIME 2025, Qwen3-2507 leads at 92.3% vs Mistral Small 4 at 83.8%. On GPQA Diamond, Qwen3-2507 leads at 81.1% vs Mistral Small 4 at 71.2%. On MMLU-Pro, Qwen3-2507 leads at 84.4% vs Mistral Small 4 at 78%.