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/GPT-5.6 Luna
OpenAI logoOpenAI

GPT-5.6 Luna

Proprietary#14 on FB Leaderboard1M contextReleased 2026-07-0925 benchmarks evaluated
View Benchmarks →Submit a score
64.6
FB Score
#14
Overall rank
FB Score64.6Rank #14
Best benchmark93.0%SWE-bench
PAVE overall—%Level 1-4
Benchmarks25 / 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
68.2%
Rank #17 of 33
Document QA
71.4%
Rank #20 of 45
Numerical
74.7%
Rank #16 of 32
Forensic
59.8%
Rank #16 of 45
Multi-domain
Not evaluated
No data
Agent Tasks
52.3%
Rank #16 of 44
Performance profile
80%Verification68.2%Document QA71.4%Numerical74.7%Forensic59.8%Agent Tasks52.3%
Benchmark results25 evaluated · 17 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
55.0#17 / 44Tier 130FB 20262026-09
MultiHiertt
Numerical
——Tier 310FB 2026Pending
FinAuditing
ForensicCompliance
——Tier 310FB 2026Pending
VALS Index
VerificationNumericalAgent Tasks
59.9#4 / 22Tier 125FB 20262026-07
MortgageTax Benchmark
NumericalForensic
67.3#12 / 22Tier 220FB 20262026-07
TaxEval v2
VerificationForensic
76.2#4 / 24Tier 220FB 20262026-09
Code Migration
Agent Tasks
44.5#5 / 23Tier 310FB 20262026-07
CyberBench
Forensic
83.9#2 / 11Tier 310FB 20262026-07
Excel Modeling Benchmark
Document QAForensic
67.1#17 / 44Tier 310FB 20262026-09
Legal Research Bench
Document QAForensic
36.5#13 / 22Tier 310FB 20262026-07
MedCode
Verification
42.4#13 / 20Tier 310FB 20262026-07
MedScribe
Document QA
84.4#11 / 20Tier 310FB 20262026-07
ProofBench v1.1
NumericalVerification
60.0#7 / 13Tier 310FB 20262026-07
SAGE
Agent Tasks
44.2#12 / 17Tier 310FB 20262026-07
Public Benefits Bench
VerificationForensic
61.2#11 / 16Tier 310FB 20262026-07
Vibe Code Bench v1.1
Agent Tasks
77.1#8 / 23Tier 310FB 20262026-07
Harvey's Legal Agent
Agent TasksForensic
1.3#17 / 22Tier 310FB 20262026-07
GPQA Diamond
NumericalVerification
91.7#10 / 20Tier 215FB 20262026-07
IOI
Numerical
72.9#4 / 8Tier 310FB 20262026-07
LiveCodeBench
Agent Tasks
——Tier 310FB 2026Pending
LegalBench
Document QAForensic
84.0#13 / 21Tier 310FB 20262026-07
MMLU Pro
NumericalVerification
86.0#17 / 21Tier 215FB 20262026-07
MMMU
Document QANumerical
85.0#10 / 14Tier 310FB 20262026-07
ProgramBench
Agent Tasks
0.0#8 / 17Tier 310FB 20262026-07
SkillsBench
Agent Tasks
60.5#3 / 17Tier 310FB 20262026-07
SWE-bench
Agent Tasks
93.0#7 / 22Tier 220FB 20262026-07
Terminal-Bench 2.1
Agent Tasks
79.0#5 / 23Tier 310FB 20262026-07
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
60.8#7 / 25Tier 310FB 20262026-09
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
——Tier 220FB 2026Pending
Contents.md
Model info
OrganisationOpenAI
Release date2026-07-09
LicenseProprietary
Context window1M tokens
Open weightNo
FB Score breakdown
Finance Agent×30 = 16.5
VALS Index×25 = 15.0
MortgageTax×20 = 13.5
TaxEval v2×20 = 15.2
Code Migration×10 = 4.5
CyberBench×10 = 8.4
EMB×10 = 6.7
Legal Research×10 = 3.7
MedCode×10 = 4.2
MedScribe×10 = 8.4
ProofBench×10 = 6.0
SAGE×10 = 4.4
Public Benefits×10 = 6.1
Vibe Code Bench×10 = 7.7
Harvey Legal×10 = 0.1
GPQA Diamond×15 = 13.8
IOI×10 = 7.3
LegalBench×10 = 8.4
MMLU Pro×15 = 12.9
MMMU×10 = 8.5
ProgramBench×10 = 0.0
SkillsBench×10 = 6.0
SWE-bench×20 = 18.6
Terminal-Bench×10 = 7.9
Tax Agent×10 = 6.1
FB Score (weighted avg)64.6
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.