LIVE INTELLIGENCE · part of the Xentir AI Index

GPT-5.2 vs Muse Spark

GPT-5.2 · OpenAI, released 2025-12-11
Muse Spark · Meta AI, released 2026-04-08

“Epoch AI, 'AI Benchmarking Hub'. Published online at epoch.ai. Retrieved from 'https://epoch.ai/benchmarks' [online resource].” · epoch.ai/benchmarks · Licensed CC BY 4.0 · data last verified 2026-07-26 · Methodology · Data Sources

Head-to-head

Measured on 6 of 9 tracked benchmarks for both models — GPT-5.2 leads on 4, Muse Spark leads on 2.

Benchmark	GPT-5.2	Muse Spark	Leads
Epoch Capabilities Index (ECI)	153.7	154.3	Muse Spark
SWE-bench Verified	0.738 (high)	Not measured	Not measured on both
GPQA Diamond	0.914 (xhigh)	0.898	GPT-5.2
MATH Level 5	Not measured	Not measured	Not measured on both
OTIS Mock AIME 2024-2025	0.961 (high)	0.889	GPT-5.2
FrontierMath	0.407 (xhigh)	0.390	GPT-5.2
FrontierMath Tier 4	0.188 (xhigh)	0.146	GPT-5.2
SimpleQA Verified	0.389 (xhigh)	0.663	Muse Spark
Chess Puzzles	0.490 (xhigh)	Not measured	Not measured on both

Benchmark results measure specific tasks and should not be treated as a universal measure of model quality. A model with no row here for a benchmark has not been measured on it — that is left blank, never estimated.

Full profiles

GPT-5.2 → · Muse Spark → · the full AI Model Rankings table