The Model Index
Up to four models

Muse Spark 1.2 vs Gemini 3.1 Pro

On the index (GPT-4 = 100), Muse Spark 1.2 scores 162 and Gemini 3.1 Pro 161. 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 1.2
Presets
Muse Spark 1.2
162146–178
WeightsClosed
ReleasedAug 2026
Price in / out$1.25 / $4.25
Context1.05M
Core tests taken3 of 9
Gemini 3.1 Pro
161146–177
WeightsClosed
ReleasedFeb 2026
Price in / out$2.0 / $12
Context1.05M
Core tests taken9 of 9

Muse Spark 1.2 and Gemini 3.1 Pro are too close to call (1 point apart, within the uncertainty), ahead on 3 of 3 shared core tests, and costs 2.3× less.

Test by testthird-party results

Muse Spark 1.2Gemini 3.1 Pro
0%25%50%75%100%REASONING & KNOWLEDGEMMLU ProMMLU ProMMMU ProMMMU ProSimpleBenchSimpleBenchSimpleQA VerifiedSimpleQA VerifiedMATHSProofBench v1.1ProofBench v1.1Chess puzzlesChess puzzlesCODINGTerminal-Bench 4.0Terminal-Bench 4.0Code MigrationCode MigrationIOIIOIProgramBenchProgramBenchSWE-benchSWE-benchVibe Code Bench v1.1Vibe Code Bench v1.1DeepSWEDeepSWEWeirdMLWeirdMLAGENTSAPEX-AgentsAPEX-AgentsBioMysteryBenchBioMysteryBenchSRE BenchSRE BenchDTBenchDTBenchLMCALMCAPROFESSIONAL WORKFinance Agent (v2)Finance Agent (v2)CorpFin v2CorpFin v2EMBEMBLegalBenchLegalBenchLegal Research BenchLegal Research BenchMedCodeMedCodeMedScribeMedScribeMortgageTaxMortgageTaxPublic Benefits Bench v1.1Public Benefits Bench v1.1Tax Agent BenchTax Agent BenchTaxEval v2TaxEval v2
Every result as a table
TestMuse Spark 1.2Gemini 3.1 Pro
Reasoning & knowledge
MMLU Pro88.3%91.0%
MMMU Pro86.1%88.2%
SimpleBench74.5%79.6%
SimpleQA Verified60.3%73.5%
Maths
ProofBench v1.143.0%26.0%
Chess puzzles27.0%51.0%
Coding
Terminal-Bench 4.06.1%2.5%
Code Migration29.9%17.3%
IOI21.8%51.8%
ProgramBench0.5%0.0%
SWE-bench86.6%78.8%
Vibe Code Bench v1.179.1%32.0%
DeepSWE54.9%11.7%
WeirdML60.4%72.1%
Agents
APEX-Agents45.4%35.1%
BioMysteryBench64.8%60.0%
SRE Bench0.0%0.0%
DTBench94.7%97.1%
LMCA48.4%53.8%
Professional work
Finance Agent (v2)60.6%43.0%
CorpFin v270.9%64.5%
EMB57.0%52.6%
LegalBench85.3%87.4%
Legal Research Bench43.8%20.7%
MedCode49.4%59.1%
MedScribe90.1%76.1%
MortgageTax65.4%69.4%
Public Benefits Bench v1.168.5%53.8%
Tax Agent Bench32.8%9.3%
TaxEval v280.4%72.9%
Task length · METR46 sec

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

This page as a chartDownload PNG