Compare AI models

Specifications
Parameters
671B30B
Context window
128k128k
API pricing
Cheapest input
$0.256DeepInfra$0.30DeepInfra
Cheapest output
$0.712DeepInfra$1.20DeepInfra
$103StreamLake$120ModelRun · bf16
Benchmarks
SWE-Bench Verified
42%76%
GPQA Diamond
59.1%83.5%
Overview
CompanyDeepSeekMeta
Release dateDec 26 2024Aug 10 2026
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Muse Glimmer leads DeepSeek V3 on 2 of the 2 benchmarks they both report (SWE-Bench Verified, GPQA Diamond). DeepSeek V3 shipped 592 days before Muse Glimmer, so benchmark comparisons should account for the intervening progress.

DeepSeek V3 has 671B parameters, while Muse Glimmer has 30B. Context windows are 128k (DeepSeek V3) vs 128k (Muse Glimmer).

On SWE-Bench Verified, Muse Glimmer leads at 76% vs DeepSeek V3 at 42%. On GPQA Diamond, Muse Glimmer leads at 83.5% vs DeepSeek V3 at 59.1%.