The Model Index
Up to four models

Muse Spark vs Kimi K2.6

On the index (GPT-4 = 100), Muse Spark scores 160 and Kimi K2.6 152. Side by side on the same third-party tests, with price and context. The link in your address bar shares this exact comparison.

Next to Muse Spark
Presets
Muse Spark
160143–177
WeightsClosed
ReleasedApr 2026
Price in / out–
Context–
Core tests taken2 of 9
Kimi K2.6
152136–169
WeightsOpen
ReleasedApr 2026
Price in / out$0.65 / $3.41
Context262K
Core tests taken4 of 9

Muse Spark and Kimi K2.6 are too close to call (8 points apart, within the uncertainty), ahead on 0 of 1 shared core tests.

Test by testthird-party results

Muse SparkKimi K2.6
0%25%50%75%100%REASONING & KNOWLEDGEGPQA Diamond (Epoch AI)GPQA Diamond (Epoch AI)GPQA Diamond (Vals AI)GPQA Diamond (Vals AI)MMLU ProMMLU ProMMMU ProMMMU ProMATHSAIME-style maths (OTIS mock)AIME-style maths (OTIS mock)FrontierMath (2025 set)FrontierMath (2025 set)FrontierMath tier 4 (2025 set)FrontierMath tier 4 (2025 set)CODINGSWE-benchSWE-benchVibe Code Bench v1.1Vibe Code Bench v1.1PROFESSIONAL WORKCorpFin v2CorpFin v2LegalBenchLegalBenchMedCodeMedCodeMedScribeMedScribeTaxEval v2TaxEval v2
Every result as a table
TestMuse SparkKimi K2.6
Reasoning & knowledge
GPQA Diamond (Epoch AI)89.8%90.8%
GPQA Diamond (Vals AI)89.6%89.1%
MMLU Pro87.3%87.6%
MMMU Pro87.4%86.3%
Maths
AIME-style maths (OTIS mock)88.9%96.1%
FrontierMath (2025 set)39.0%39.0%
FrontierMath tier 4 (2025 set)14.6%14.6%
Coding
SWE-bench74.4%76.2%
Vibe Code Bench v1.119.7%37.9%
Professional work
CorpFin v265.1%66.7%
LegalBench84.2%84.7%
MedCode51.3%40.1%
MedScribe85.9%78.1%
TaxEval v277.7%74.7%

Tests at least two of these models have taken. Bold rows are the core tests.

This page as a chartDownload PNG