DeepSeek-V4.1-FlashvsMuse Spark 1.3

DeepSeek-V4.1-Flash
Muse Spark 1.3
Specifications
Context window
1M
API pricing
Cheapest input
$1.25Meta
Cheapest output
$4.25Meta
Benchmarks
DeepSWE 1.1
74.2%75.4%
Terminal-Bench 2.1
90.6%88.8%
AutomationBench
54.8%49.4%
Benchmarks
NL2Repo-Bench
65.4%
SWEAtlas CodeBase QnA
59.4%
Terminal-Bench 4.0
31.2%
Terminal-Bench 3.0
30%
JobBench
64.9%
DeepSearchQA
89.4%
CyberGym
88.1%
Humanity's Last Exam · no tools
36.8%
Humanity's Last Exam · with tools
63.9%
GPQA Diamond
90.9%
Agentic IF Index (Internal)
57.8%
OSWorld 2.0
66.9%
Agent's Last Exam · pass@1
31.8%
GDPval-AA v2
1754
Chartography · with tools
78.9%
MRCR · 256k-512k
98.5%
MRCR · 512k-1M
98.1%
threejseval
1503
Overview
CompanyDeepSeekMeta
Release dateSep 10 2026Sep 2 2026
AccessProprietaryProprietary

Other comparisons

DeepSeek-V4.1-FlashvsClaude Fable 5.1Muse Spark 1.3vsClaude Fable 5.1DeepSeek-V4.1-FlashvsGPT-6 AstraMuse Spark 1.3vsGPT-6 AstraDeepSeek-V4.1-FlashvsGemini 3.8 FlashMuse Spark 1.3vsGemini 3.8 FlashDeepSeek-V4.1-FlashvsGrok 4.6Muse Spark 1.3vsGrok 4.6DeepSeek-V4.1-FlashvsMistral Medium 3.5Muse Spark 1.3vsMistral Medium 3.5DeepSeek-V4.1-FlashvsKimi K3Muse Spark 1.3vsKimi K3

Frequently asked questions

DeepSeek-V4.1-Flash leads Muse Spark 1.3 on 2 of the 3 benchmarks they both report (DeepSWE 1.1, Terminal-Bench 2.1, AutomationBench). Muse Spark 1.3 shipped 8 days before DeepSeek-V4.1-Flash, so benchmark comparisons should account for the intervening progress.

Published specifications for these two models are limited — see each model page for the latest details.

On DeepSWE 1.1, Muse Spark 1.3 leads at 75.4% vs DeepSeek-V4.1-Flash at 74.2%. On Terminal-Bench 2.1, DeepSeek-V4.1-Flash leads at 90.6% vs Muse Spark 1.3 at 88.8%. On AutomationBench, DeepSeek-V4.1-Flash leads at 54.8% vs Muse Spark 1.3 at 49.4%.