Neura Intelligence Index

AI Model Benchmarks

Back to Leaderboard

K-EXAONE-236B-A23B vs Muse Spark

L

K-EXAONE-236B-A23B

LG AI Research 🇰🇷

67.0

#83—

M

Meta 🇺🇸

66.8

#86—

Category Comparison

Benchmark-by-Benchmark

math

Benchmark	K-EXAONE-236B-A23B	Muse Spark
AIME 2025	92.8	—

general

Benchmark	K-EXAONE-236B-A23B	Muse Spark
MMMLU	85.7	—

reasoning

Benchmark	K-EXAONE-236B-A23B	Muse Spark
GPQA Diamond	—	89.5
Humanity's Last Exam	—	58.4
ARC-AGI v2	—	42.5

coding

Benchmark	K-EXAONE-236B-A23B	Muse Spark
SWE-bench Verified	—	77.4
SWE-Bench Pro	—	52.4

multimodal

Benchmark	K-EXAONE-236B-A23B	Muse Spark
MMMU-Pro	—	80.4
CharXiv Reasoning	—	86.4
ScreenSpot Pro	—	84.1

Category Winners

coding

M

Muse Spark

48.3

math

L

K-EXAONE-236B-A23B

74.3

reasoning

M

Muse Spark

75.8

general

L

K-EXAONE-236B-A23B

59.8

multimodal

M

Muse Spark

85.9

K-EXAONE-236B-A23B vs Muse Spark — Benchmark Comparison | Neura Market