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/Grok 4.5
xAI logoxAI

Grok 4.5

Proprietary#34 on FB Leaderboard500K contextReleased 2026-07-1625 benchmarks evaluated
View Benchmarks →Submit a score
56.8
FB Score
#34
Overall rank
FB Score56.8Rank #34
Best benchmark92.9%GPQA Diamond
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
63.9%
Rank #25 of 33
Document QA
65.1%
Rank #31 of 45
Numerical
64.7%
Rank #27 of 32
Forensic
44.2%
Rank #42 of 45
Multi-domain
Not evaluated
No data
Agent Tasks
47.3%
Rank #31 of 44
Performance profile
80%Verification63.9%Document QA65.1%Numerical64.7%Forensic44.2%Agent Tasks47.3%
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
48.4#31 / 44Tier 130FB 20262026-09
MultiHiertt
Numerical
——Tier 310FB 2026Pending
FinAuditing
ForensicCompliance
——Tier 310FB 2026Pending
VALS Index
VerificationNumericalAgent Tasks
51.5#16 / 22Tier 125FB 20262026-07
MortgageTax Benchmark
NumericalForensic
61.8#22 / 22Tier 220FB 20262026-07
TaxEval v2
VerificationForensic
71.7#21 / 24Tier 220FB 20262026-07
Code Migration
Agent Tasks
36.6#10 / 23Tier 310FB 20262026-07
CyberBench
Forensic
——Tier 310FB 2026Pending
Excel Modeling Benchmark
Document QAForensic
52.9#32 / 44Tier 310FB 20262026-09
Legal Research Bench
Document QAForensic
38.0#11 / 22Tier 310FB 20262026-07
MedCode
Verification
43.3#11 / 20Tier 310FB 20262026-07
MedScribe
Document QA
86.9#6 / 20Tier 310FB 20262026-07
ProofBench v1.1
NumericalVerification
31.0#11 / 13Tier 310FB 20262026-07
SAGE
Agent Tasks
35.0#15 / 17Tier 310FB 20262026-07
Public Benefits Bench
VerificationForensic
——Tier 310FB 2026Pending
Vibe Code Bench v1.1
Agent Tasks
69.0#12 / 23Tier 310FB 20262026-07
Harvey's Legal Agent
Agent TasksForensic
12.9#4 / 22Tier 310FB 20262026-07
GPQA Diamond
NumericalVerification
92.9#7 / 20Tier 215FB 20262026-07
IOI
Numerical
——Tier 310FB 2026Pending
LiveCodeBench
Agent Tasks
87.3#6 / 19Tier 310FB 20262026-07
LegalBench
Document QAForensic
86.0#7 / 21Tier 310FB 20262026-07
MMLU Pro
NumericalVerification
89.2#4 / 21Tier 215FB 20262026-07
MMMU
Document QANumerical
61.8#14 / 14Tier 310FB 20262026-07
ProgramBench
Agent Tasks
0.0#8 / 17Tier 310FB 20262026-07
SkillsBench
Agent Tasks
66.0#1 / 17Tier 310FB 20262026-07
SWE-bench
Agent Tasks
86.6#9 / 22Tier 220FB 20262026-07
Terminal-Bench 2.1
Agent Tasks
67.8#11 / 23Tier 310FB 20262026-07
RSI Index
Agent TasksNumerical
——Tier 310FB 2026Pending
Time Horizon Index
ForensicAgent Tasks
6.3#3 / 5Tier 310FB 20262026-07
ReverseEngBench
Forensic
0.8#3 / 4Tier 310FB 20262026-07
Tax Agent Bench
ForensicAgent Tasks
——Tier 310FB 2026Pending
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
67.4#12 / 13Tier 220FB 20262026-08
Contents.md
Model info
OrganisationxAI
Release date2026-07-16
LicenseProprietary
Context window500K tokens
Open weightNo
FB Score breakdown
Finance Agent×30 = 14.5
VALS Index×25 = 12.9
MortgageTax×20 = 12.4
TaxEval v2×20 = 14.3
Code Migration×10 = 3.7
EMB×10 = 5.3
Legal Research×10 = 3.8
MedCode×10 = 4.3
MedScribe×10 = 8.7
ProofBench×10 = 3.1
SAGE×10 = 3.5
Vibe Code Bench×10 = 6.9
Harvey Legal×10 = 1.3
GPQA Diamond×15 = 13.9
LiveCodeBench×10 = 8.7
LegalBench×10 = 8.6
MMLU Pro×15 = 13.4
MMMU×10 = 6.2
ProgramBench×10 = 0.0
SkillsBench×10 = 6.6
SWE-bench×20 = 17.3
Terminal-Bench×10 = 6.8
Time Horizon×10 = 0.6
ReverseEngBench×10 = 0.1
CorpFin×20 = 13.5
FB Score (weighted avg)56.8
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.