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/Claude Opus 5
Anthropic logoAnthropic

Claude Opus 5

Proprietary#7 on FB Leaderboard1M contextReleased 2026-07-2230 benchmarks evaluated
View Benchmarks →Submit a score
66.7
FB Score
#7
Overall rank
FB Score66.7Rank #7
Best benchmark99.0%ProofBench
PAVE overall—%Level 1-4
Benchmarks30 / 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
80.0%
Rank #1 of 33
Document QA
79.3%
Rank #2 of 45
Numerical
79.5%
Rank #4 of 32
Forensic
52.7%
Rank #34 of 45
Multi-domain
Not evaluated
No data
Agent Tasks
53.7%
Rank #13 of 44
Performance profile
80%Verification80.0%Document QA79.3%Numerical79.5%Forensic52.7%Agent Tasks53.7%
Benchmark results30 evaluated · 12 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
58.6#8 / 44Tier 130FB 20262026-10
MultiHiertt
Numerical
——Tier 310FB 2026Pending
FinAuditing
ForensicCompliance
——Tier 310FB 2026Pending
VALS Index
VerificationNumericalAgent Tasks
67.2#1 / 22Tier 125FB 20262026-07
MortgageTax Benchmark
NumericalForensic
72.1#1 / 22Tier 220FB 20262026-09
TaxEval v2
VerificationForensic
75.1#14 / 24Tier 220FB 20262026-07
Code Migration
Agent Tasks
57.5#1 / 23Tier 310FB 20262026-07
CyberBench
Forensic
40.7#10 / 11Tier 310FB 20262026-07
Excel Modeling Benchmark
Document QAForensic
73.6#6 / 44Tier 310FB 20262026-09
Legal Research Bench
Document QAForensic
55.3#1 / 22Tier 310FB 20262026-07
MedCode
Verification
63.6#1 / 20Tier 310FB 20262026-07
MedScribe
Document QA
91.0#1 / 20Tier 310FB 20262026-07
ProofBench v1.1
NumericalVerification
99.0#1 / 13Tier 310FB 20262026-07
SAGE
Agent Tasks
49.4#5 / 17Tier 310FB 20262026-07
Public Benefits Bench
VerificationForensic
76.9#1 / 16Tier 310FB 20262026-07
Vibe Code Bench v1.1
Agent Tasks
88.4#2 / 23Tier 310FB 20262026-07
Harvey's Legal Agent
Agent TasksForensic
6.7#11 / 22Tier 310FB 20262026-07
GPQA Diamond
NumericalVerification
93.4#4 / 20Tier 215FB 20262026-07
IOI
Numerical
91.7#1 / 8Tier 310FB 20262026-07
LiveCodeBench
Agent Tasks
89.0#2 / 19Tier 310FB 20262026-07
LegalBench
Document QAForensic
87.0#2 / 21Tier 310FB 20262026-07
MMLU Pro
NumericalVerification
91.6#1 / 21Tier 215FB 20262026-07
MMMU
Document QANumerical
89.9#1 / 14Tier 310FB 20262026-07
ProgramBench
Agent Tasks
3.0#1 / 17Tier 310FB 20262026-07
SkillsBench
Agent Tasks
60.4#4 / 17Tier 310FB 20262026-07
SWE-bench
Agent Tasks
97.0#1 / 22Tier 220FB 20262026-07
Terminal-Bench 2.1
Agent Tasks
84.6#2 / 23Tier 310FB 20262026-07
RSI Index
Agent TasksNumerical
30.9#1 / 3Tier 310FB 20262026-07
Time Horizon Index
ForensicAgent Tasks
13.7#1 / 5Tier 310FB 20262026-07
ReverseEngBench
Forensic
12.2#2 / 4Tier 310FB 20262026-07
Tax Agent Bench
ForensicAgent Tasks
45.5#14 / 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
73.2#1 / 13Tier 220FB 20262026-08
Contents.md
Model info
OrganisationAnthropic
Release date2026-07-22
LicenseProprietary
Context window1M tokens
Open weightNo
FB Score breakdown
Finance Agent×30 = 17.6
VALS Index×25 = 16.8
MortgageTax×20 = 14.4
TaxEval v2×20 = 15.0
Code Migration×10 = 5.7
CyberBench×10 = 4.1
EMB×10 = 7.4
Legal Research×10 = 5.5
MedCode×10 = 6.4
MedScribe×10 = 9.1
ProofBench×10 = 9.9
SAGE×10 = 4.9
Public Benefits×10 = 7.7
Vibe Code Bench×10 = 8.8
Harvey Legal×10 = 0.7
GPQA Diamond×15 = 14.0
IOI×10 = 9.2
LiveCodeBench×10 = 8.9
LegalBench×10 = 8.7
MMLU Pro×15 = 13.7
MMMU×10 = 9.0
ProgramBench×10 = 0.3
SkillsBench×10 = 6.0
SWE-bench×20 = 19.4
Terminal-Bench×10 = 8.5
RSI Index×10 = 3.1
Time Horizon×10 = 1.4
ReverseEngBench×10 = 1.2
Tax Agent×10 = 4.6
CorpFin×20 = 14.6
FB Score (weighted avg)66.7
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.