Compare AI models

Specifications
Parameters
30B>1T
Context window
128k256k
API pricing
Cheapest input
$0.30DeepInfra—
Cheapest output
$1.20DeepInfra—
$120ModelRun · bf16—
Benchmarks
SWE-Bench Verified
76%75.3%
Humanity's Last Exam · text only, no tools
22%30.2%
GPQA Diamond
83.5%87.4%
IFBench
77%70.9%
Overview
CompanyMetaQwen
Release dateAug 10 2026Jan 26 2026
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

Muse Glimmer and Qwen3-Max-Thinking are evenly matched across the 4 benchmarks they both report (SWE-Bench Verified, Humanity's Last Exam, GPQA Diamond, IFBench). Qwen3-Max-Thinking shipped 196 days before Muse Glimmer, so benchmark comparisons should account for the intervening progress.

Muse Glimmer has 30B parameters, while Qwen3-Max-Thinking has >1T. Context windows are 128k (Muse Glimmer) vs 256k (Qwen3-Max-Thinking). Muse Glimmer is open weight, while Qwen3-Max-Thinking is closed.

On SWE-Bench Verified, Muse Glimmer leads at 76% vs Qwen3-Max-Thinking at 75.3%. On Humanity's Last Exam · text only, no tools, Qwen3-Max-Thinking leads at 30.2% vs Muse Glimmer at 22%. On GPQA Diamond, Qwen3-Max-Thinking leads at 87.4% vs Muse Glimmer at 83.5%. On IFBench, Muse Glimmer leads at 77% vs Qwen3-Max-Thinking at 70.9%.