2026-10-20UPDATEPlatform updated: 52 models tracked across 42 independent benchmarks including CorpFin • 2026-10-20BENCHCorpFin added to benchmark suite — long credit agreement comprehension evaluations live • 2026-10-19MODELClaude Sonnet 5.5 and Opus 5.5 achieve 75.9% and 75.8% on Excel Modeling Benchmark v1.1 • 2026-10-19MODELTax Agent Bench updated: Claude Fable 5.1 (49.2%) and Gemini 4 Argon (44.6%) lead corporate tax research • 2026-10-18MODELGemini 4 Argon claims #1 rank on Finance Agent (v2) with 65.4% • 2026-10-13MODELGoogle launches Gemini 4 Argon with 1M-token output limit and native multimodal reasoning • 2026-10-06MODELAnthropic completes Claude 5.5 generation with Claude Haiku 5.5, Opus 5.5, and Sonnet 5.5 • 2026-10-20UPDATEPlatform updated: 52 models tracked across 42 independent benchmarks including CorpFin • 2026-10-20BENCHCorpFin added to benchmark suite — long credit agreement comprehension evaluations live • 2026-10-19MODELClaude Sonnet 5.5 and Opus 5.5 achieve 75.9% and 75.8% on Excel Modeling Benchmark v1.1 • 2026-10-19MODELTax Agent Bench updated: Claude Fable 5.1 (49.2%) and Gemini 4 Argon (44.6%) lead corporate tax research • 2026-10-18MODELGemini 4 Argon claims #1 rank on Finance Agent (v2) with 65.4% • 2026-10-13MODELGoogle launches Gemini 4 Argon with 1M-token output limit and native multimodal reasoning • 2026-10-06MODELAnthropic completes Claude 5.5 generation with Claude Haiku 5.5, Opus 5.5, and Sonnet 5.5 •
Home/Models/Muse Spark 1.2
Meta logoMeta

Muse Spark 1.2

Proprietary#17 on FB Leaderboard1M contextReleased 2026-08-0523 benchmarks evaluated
View Benchmarks →Submit a score
63.7
FB Score
#17
Overall rank
FB Score63.7Rank #17
Best benchmark90.1%MedScribe
PAVE overall—%Level 1-4
Benchmarks23 / 42Evaluated
✦Official Certification
Get your AI model certified by FinanceBenchmark
Verified performance scores · Embeddable trust badge · Leaderboard listing
Claim Your Badge

Score by domain

Verification
65.4%
Rank #23 of 33
Document QA
72.4%
Rank #18 of 45
Numerical
64.9%
Rank #26 of 32
Forensic
58.8%
Rank #21 of 45
Multi-domain
Not evaluated
No data
Agent Tasks
54.2%
Rank #11 of 44
Performance profile
80%Verification65.4%Document QA72.4%Numerical64.9%Forensic58.8%Agent Tasks54.2%
Benchmark results23 evaluated · 19 pending
BenchmarkScoreRankTierWeightSourceDate
Pave Interchange Fee Benchmark
VerificationForensic
——Tier 130FB 2026Pending
FinanceBench
Document QA
——Tier 220FB 2026Pending
FinBen
Multi-domain
——Tier 310FB 2026Pending
FinQA
Numerical
——Tier 220FB 2026Pending
ConvFinQA
Document QA
——Tier 220FB 2026Pending
Finance Agent Benchmark
Agent Tasks
60.6#3 / 44Tier 130FB 20262026-10
MultiHiertt
Numerical
——Tier 310FB 2026Pending
FinAuditing
ForensicCompliance
——Tier 310FB 2026Pending
VALS Index
VerificationNumericalAgent Tasks
57.0#8 / 22Tier 125FB 20262026-08
MortgageTax Benchmark
NumericalForensic
65.4#17 / 22Tier 220FB 20262026-08
TaxEval v2
VerificationForensic
80.4#1 / 24Tier 220FB 20262026-09
Code Migration
Agent Tasks
29.9#14 / 23Tier 310FB 20262026-08
CyberBench
Forensic
——Tier 310FB 2026Pending
Excel Modeling Benchmark
Document QAForensic
57.0#28 / 44Tier 310FB 20262026-09
Legal Research Bench
Document QAForensic
43.8#7 / 22Tier 310FB 20262026-08
MedCode
Verification
49.4#4 / 20Tier 310FB 20262026-08
MedScribe
Document QA
90.1#2 / 20Tier 310FB 20262026-08
ProofBench v1.1
NumericalVerification
43.0#10 / 13Tier 310FB 20262026-08
SAGE
Agent Tasks
47.7#8 / 17Tier 310FB 20262026-08
Public Benefits Bench
VerificationForensic
68.5#3 / 16Tier 310FB 20262026-08
Vibe Code Bench v1.1
Agent Tasks
79.1#7 / 23Tier 310FB 20262026-08
Harvey's Legal Agent
Agent TasksForensic
25.4#1 / 22Tier 310FB 20262026-08
GPQA Diamond
NumericalVerification
——Tier 215FB 2026Pending
IOI
Numerical
49.5#7 / 8Tier 310FB 20262026-08
LiveCodeBench
Agent Tasks
——Tier 310FB 2026Pending
LegalBench
Document QAForensic
85.3#8 / 21Tier 310FB 20262026-08
MMLU Pro
NumericalVerification
88.3#9 / 21Tier 215FB 20262026-08
MMMU
Document QANumerical
86.1#9 / 14Tier 310FB 20262026-08
ProgramBench
Agent Tasks
——Tier 310FB 2026Pending
SkillsBench
Agent Tasks
53.0#9 / 17Tier 310FB 20262026-08
SWE-bench
Agent Tasks
86.6#9 / 22Tier 220FB 20262026-08
Terminal-Bench 2.1
Agent Tasks
69.7#9 / 23Tier 310FB 20262026-08
RSI Index
Agent TasksNumerical
——Tier 310FB 2026Pending
Time Horizon Index
ForensicAgent Tasks
——Tier 310FB 2026Pending
ReverseEngBench
Forensic
——Tier 310FB 2026Pending
Tax Agent Bench
ForensicAgent Tasks
32.8#25 / 25Tier 310FB 20262026-10
Big Finance Bench
ForensicDocument QA
——Tier 310FB 2026Pending
GDPval-MM
Document QANumerical
——Tier 310FB 2026Pending
BankerToolBench
Agent Tasks
——Tier 310FB 2026Pending
GDPval-Rubrics
Forensic
——Tier 310FB 2026Pending
PRBench-Finance
NumericalForensic
——Tier 310FB 2026Pending
CorpFin
ForensicVerification
70.9#5 / 13Tier 220FB 20262026-08
Contents.md
Model info
OrganisationMeta
Release date2026-08-05
LicenseProprietary
Context window1M tokens
Open weightNo
FB Score breakdown
Finance Agent×30 = 18.2
VALS Index×25 = 14.3
MortgageTax×20 = 13.1
TaxEval v2×20 = 16.1
Code Migration×10 = 3.0
EMB×10 = 5.7
Legal Research×10 = 4.4
MedCode×10 = 4.9
MedScribe×10 = 9.0
ProofBench×10 = 4.3
SAGE×10 = 4.8
Public Benefits×10 = 6.8
Vibe Code Bench×10 = 7.9
Harvey Legal×10 = 2.5
IOI×10 = 5.0
LegalBench×10 = 8.5
MMLU Pro×15 = 13.2
MMMU×10 = 8.6
SkillsBench×10 = 5.3
SWE-bench×20 = 17.3
Terminal-Bench×10 = 7.0
Tax Agent×10 = 3.3
CorpFin×20 = 14.2
FB Score (weighted avg)63.7
Compare - all models
AClaude Opus 4.773.8%
OGPT-5.572.2%
OGPT-6 Sol71.1%
DDeepSeek V4 Pro70.1%
GGemini 3.1 Pro70.0%
OGPT-6 Luna70.0%
Compare vs Claude Opus 4.7 in full →
Evaluation notes
Scores reflect median of 3 runs per task at temperature 0.0 with 0-shot prompting. PAVE evaluation conducted by FinanceBenchmark. Other scores sourced from latest published arXiv papers.