Muse Spark 1.2vsgpt-oss-120b

Muse Spark 1.2
gpt-oss-120b
Specifications
Parameters
117B
Context window
1M128k
API pricing
Cheapest input
$1.25Meta$0.03AkashML
Cheapest output
$4.25Meta$0.17AkashML
Benchmarks
BullshitBench v2
50%12%
Benchmarks
SWE-Bench Verified
62.4%
DeepSWE 1.1
59.3%
Terminal-Bench 2.1
82.9%
Humanity's Last Exam · no tools
14.9%
Humanity's Last Exam · with tools
19%
GPQA Diamond
80.1%
MMLU
90%
Overview
CompanyMetaOpenAI
Release dateAug 5 2026Aug 5 2025
AccessProprietaryOpen Weight

Other comparisons

Muse Spark 1.2vsClaude Fable 5.1gpt-oss-120bvsClaude Fable 5.1Muse Spark 1.2vsGemini 3.8 Flashgpt-oss-120bvsGemini 3.8 FlashMuse Spark 1.2vsGrok 4.6gpt-oss-120bvsGrok 4.6Muse Spark 1.2vsDeepSeek-V4.1-Flashgpt-oss-120bvsDeepSeek-V4.1-FlashMuse Spark 1.2vsMistral Medium 3.5gpt-oss-120bvsMistral Medium 3.5Muse Spark 1.2vsKimi K3gpt-oss-120bvsKimi K3

Frequently asked questions

Muse Spark 1.2 leads gpt-oss-120b on 1 of the 1 benchmark they both report (BullshitBench v2). gpt-oss-120b shipped 365 days before Muse Spark 1.2, so benchmark comparisons should account for the intervening progress.

Context windows are 1M (Muse Spark 1.2) vs 128k (gpt-oss-120b). Muse Spark 1.2 is proprietary, while gpt-oss-120b is open weight.

On BullshitBench v2, Muse Spark 1.2 leads at 50% vs gpt-oss-120b at 12%.