Muse Spark

Released2026-04-08
Price per 1MNot listed
Overall score56.9 · rank 59
ProviderMeta
WeightsProprietary

Scores

DimensionScoreRankBenchmarks
Overall: Balanced 56.9 59 14
Overall: Coding 53.7 80 5
Overall: Reasoning 57.8 58 8
Overall: Agentic work 56.4 68 4
Overall: Frontend 49.8 88 5
Coding 55.0 71 2
Reasoning 58.7 59 2
Math 55.8 62 4
Knowledge 59.5 28 2
Frontend 45.4 91 1
General 61.1 25 1
Multimodal 60.6 17 2

Evidence

Coding 55.0 ±3.2

BenchmarkResultSourceDate
SWE-bench Verified (Vals run) 74.4% Vals AI 2026-09-01
SciCode 51.5% Epoch AI 2026-11-11

Reasoning 58.7 ±3.5

BenchmarkResultSourceDate
CritPt 11.3% Epoch AI 2026-11-11
GPQA Diamond 89.8% Epoch AI 2026-04-08
GPQA Diamond (Vals run) 89.6% Vals AI 2026-09-01

Math 55.8 ±1.7

BenchmarkResultSourceDate
FrontierMath Tiers 1-3 (2025 set) 39.0% Epoch AI 2026-04-08
ProofBench 17.0% Epoch AI 2026-11-11
FrontierMath Tier 4 (2025 set) 14.6% Epoch AI 2026-04-08
OTIS Mock AIME 2024-2025 88.9% Epoch AI 2026-04-08

Knowledge 59.5 ±1.3

BenchmarkResultSourceDate
Humanity's Last Exam 40.6% Epoch AI 2026-11-11
MMLU-Pro (Vals run) 87.3% Vals AI 2026-09-01

Frontend 45.4 ±0.8

BenchmarkResultSourceDate
Vibe Code Bench v1.1 19.7% Vals AI 2026-11-09

General 61.1 ±4.1

BenchmarkResultSourceDate
LMArena Text 1,489 LMArena 2026-11-09

Multimodal 60.6 ±2.3

BenchmarkResultSourceDate
MMMU-Pro (Vals run) 87.4% Vals AI 2026-09-01
LMArena Vision 1,294 LMArena 2026-11-09

Names matched to this model

muse-spark

Compare Muse Spark with other models