Compare AI models

Specifications
Parameters
1T4B/30B/235B
Context window
256k256k
API pricing
Cheapest input
$0.60Novita—
Cheapest output
$2.50Novita—
$245Novita · fp8—
Benchmarks
Humanity's Last Exam · text only, no tools
7.9%18.2%
AIME 2025
51%92.3%
GPQA Diamond
74.2%81.1%
MMLU-Pro
81.9%84.4%
Overview
CompanyMoonshot AIQwen
Release dateSep 5 2025Jul 21 2025
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Qwen3-2507 leads Kimi K2 (0905) on 4 of the 4 benchmarks they both report (Humanity's Last Exam, AIME 2025, GPQA Diamond, MMLU-Pro). Qwen3-2507 shipped 46 days before Kimi K2 (0905), so benchmark comparisons should account for the intervening progress.

Kimi K2 (0905) has 1T parameters, while Qwen3-2507 has 4B/30B/235B. Context windows are 256k (Kimi K2 (0905)) vs 256k (Qwen3-2507).

On Humanity's Last Exam · text only, no tools, Qwen3-2507 leads at 18.2% vs Kimi K2 (0905) at 7.9%. On AIME 2025, Qwen3-2507 leads at 92.3% vs Kimi K2 (0905) at 51%. On GPQA Diamond, Qwen3-2507 leads at 81.1% vs Kimi K2 (0905) at 74.2%. On MMLU-Pro, Qwen3-2507 leads at 84.4% vs Kimi K2 (0905) at 81.9%.