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/Kimi K3
Moonshot AI logoMoonshot AI

Kimi K3

Open-weight#18 on FB Leaderboard1M contextReleased 2026-07-1627 benchmarks evaluated
View Benchmarks →Submit a score
63.4
FB Score
#18
Overall rank
FB Score63.4Rank #18
Best benchmark93.4%SWE-bench
PAVE overall—%Level 1-4
Benchmarks27 / 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
73.8%
Rank #6 of 33
Document QA
75.5%
Rank #10 of 45
Numerical
71.8%
Rank #20 of 32
Forensic
55.6%
Rank #27 of 45
Multi-domain
Not evaluated
No data
Agent Tasks
46.3%
Rank #32 of 44
Performance profile
80%Verification73.8%Document QA75.5%Numerical71.8%Forensic55.6%Agent Tasks46.3%
Benchmark results27 evaluated · 15 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
54.4#19 / 44Tier 130FB 20262026-09
MultiHiertt
Numerical
——Tier 310FB 2026Pending
FinAuditing
ForensicCompliance
——Tier 310FB 2026Pending
VALS Index
VerificationNumericalAgent Tasks
57.8#7 / 22Tier 125FB 20262026-07
MortgageTax Benchmark
NumericalForensic
66.3#14 / 22Tier 220FB 20262026-07
TaxEval v2
VerificationForensic
75.7#7 / 24Tier 220FB 20262026-09
Code Migration
Agent Tasks
16.1#17 / 23Tier 310FB 20262026-07
CyberBench
Forensic
79.0#3 / 11Tier 310FB 20262026-07
Excel Modeling Benchmark
Document QAForensic
71.3#11 / 44Tier 310FB 20262026-10
Legal Research Bench
Document QAForensic
44.2#6 / 22Tier 310FB 20262026-07
MedCode
Verification
48.9#5 / 20Tier 310FB 20262026-07
MedScribe
Document QA
88.0#5 / 20Tier 310FB 20262026-07
ProofBench v1.1
NumericalVerification
87.0#3 / 13Tier 310FB 20262026-07
SAGE
Agent Tasks
54.3#1 / 17Tier 310FB 20262026-07
Public Benefits Bench
VerificationForensic
68.3#4 / 16Tier 310FB 20262026-07
Vibe Code Bench v1.1
Agent Tasks
85.0#3 / 23Tier 310FB 20262026-07
Harvey's Legal Agent
Agent TasksForensic
10.8#6 / 22Tier 310FB 20262026-07
GPQA Diamond
NumericalVerification
92.9#7 / 20Tier 215FB 20262026-07
IOI
Numerical
——Tier 310FB 2026Pending
LiveCodeBench
Agent Tasks
87.2#8 / 19Tier 310FB 20262026-07
LegalBench
Document QAForensic
86.0#6 / 21Tier 310FB 20262026-07
MMLU Pro
NumericalVerification
88.0#10 / 21Tier 215FB 20262026-07
MMMU
Document QANumerical
88.2#4 / 14Tier 310FB 20262026-07
ProgramBench
Agent Tasks
2.0#2 / 17Tier 310FB 20262026-07
SkillsBench
Agent Tasks
——Tier 310FB 2026Pending
SWE-bench
Agent Tasks
93.4#6 / 22Tier 220FB 20262026-07
Terminal-Bench 2.1
Agent Tasks
80.9#3 / 23Tier 310FB 20262026-07
RSI Index
Agent TasksNumerical
22.1#3 / 3Tier 310FB 20262026-07
Time Horizon Index
ForensicAgent Tasks
5.2#4 / 5Tier 310FB 20262026-07
ReverseEngBench
Forensic
——Tier 310FB 2026Pending
Tax Agent Bench
ForensicAgent Tasks
33.4#23 / 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
71.6#3 / 13Tier 220FB 20262026-08
Contents.md
Model info
OrganisationMoonshot AI
Release date2026-07-16
LicenseOpen-weight
Context window1M tokens
Open weightYes
FB Score breakdown
Finance Agent×30 = 16.3
VALS Index×25 = 14.5
MortgageTax×20 = 13.3
TaxEval v2×20 = 15.1
Code Migration×10 = 1.6
CyberBench×10 = 7.9
EMB×10 = 7.1
Legal Research×10 = 4.4
MedCode×10 = 4.9
MedScribe×10 = 8.8
ProofBench×10 = 8.7
SAGE×10 = 5.4
Public Benefits×10 = 6.8
Vibe Code Bench×10 = 8.5
Harvey Legal×10 = 1.1
GPQA Diamond×15 = 13.9
LiveCodeBench×10 = 8.7
LegalBench×10 = 8.6
MMLU Pro×15 = 13.2
MMMU×10 = 8.8
ProgramBench×10 = 0.2
SWE-bench×20 = 18.7
Terminal-Bench×10 = 8.1
RSI Index×10 = 2.2
Time Horizon×10 = 0.5
Tax Agent×10 = 3.3
CorpFin×20 = 14.3
FB Score (weighted avg)63.4
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.