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 K2.6
Moonshot AI logoMoonshot AI

Kimi K2.6

Open-weight#6 on FB Leaderboard128K contextReleased 2026-029 benchmarks evaluated
View Benchmarks →Submit a score
67.4
FB Score
#6
Overall rank
FB Score67.4Rank #6
Best benchmark82.0%FinanceBench
PAVE overall66.0%Level 1-4
Benchmarks9 / 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
67.1%
Rank #21 of 33
Document QA
72.6%
Rank #17 of 45
Numerical
74.0%
Rank #17 of 32
Forensic
64.0%
Rank #10 of 45
Multi-domain
75.0%
Rank #6 of 8
Agent Tasks
44.9%
Rank #33 of 44
Performance profile
80%Verification67.1%Document QA72.6%Numerical74.0%Forensic64.0%Multi-domain75.0%Agent Tasks44.9%
PAVE - Level breakdownFull benchmark →
Level 1
92%
Deterministic aggregation
Level 2
66%
Multi-rule classification
Level 3
45%
Cross-scheme reconciliation
Level 4
61%
Strategic impact modelling
Benchmark results9 evaluated · 33 pending
BenchmarkScoreRankTierWeightSourceDate
Pave Interchange Fee Benchmark
VerificationForensic
66.0#6 / 9Tier 130FB 20262026-05
FinanceBench
Document QA
82.0#6 / 8Tier 220FB 20262026-04
FinBen
Multi-domain
75.0#6 / 8Tier 310FB 20262026-03
FinQA
Numerical
76.0#6 / 8Tier 220FB 20262026-03
ConvFinQA
Document QA
78.0#6 / 8Tier 220FB 20262026-04
Finance Agent Benchmark
Agent Tasks
44.9#35 / 44Tier 130FB 20262026-09
MultiHiertt
Numerical
72.0#6 / 8Tier 310FB 20262026-03
FinAuditing
ForensicCompliance
——Tier 310FB 2026Pending
VALS Index
VerificationNumericalAgent Tasks
——Tier 125FB 2026Pending
MortgageTax Benchmark
NumericalForensic
——Tier 220FB 2026Pending
TaxEval v2
VerificationForensic
——Tier 220FB 2026Pending
Code Migration
Agent Tasks
——Tier 310FB 2026Pending
CyberBench
Forensic
——Tier 310FB 2026Pending
Excel Modeling Benchmark
Document QAForensic
57.9#27 / 44Tier 310FB 20262026-09
Legal Research Bench
Document QAForensic
——Tier 310FB 2026Pending
MedCode
Verification
——Tier 310FB 2026Pending
MedScribe
Document QA
——Tier 310FB 2026Pending
ProofBench v1.1
NumericalVerification
——Tier 310FB 2026Pending
SAGE
Agent Tasks
——Tier 310FB 2026Pending
Public Benefits Bench
VerificationForensic
——Tier 310FB 2026Pending
Vibe Code Bench v1.1
Agent Tasks
——Tier 310FB 2026Pending
Harvey's Legal Agent
Agent TasksForensic
——Tier 310FB 2026Pending
GPQA Diamond
NumericalVerification
——Tier 215FB 2026Pending
IOI
Numerical
——Tier 310FB 2026Pending
LiveCodeBench
Agent Tasks
——Tier 310FB 2026Pending
LegalBench
Document QAForensic
——Tier 310FB 2026Pending
MMLU Pro
NumericalVerification
——Tier 215FB 2026Pending
MMMU
Document QANumerical
——Tier 310FB 2026Pending
ProgramBench
Agent Tasks
——Tier 310FB 2026Pending
SkillsBench
Agent Tasks
——Tier 310FB 2026Pending
SWE-bench
Agent Tasks
——Tier 220FB 2026Pending
Terminal-Bench 2.1
Agent Tasks
——Tier 310FB 2026Pending
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
——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
68.3#10 / 13Tier 220FB 20262026-08
Contents.md
Model info
OrganisationMoonshot AI
Release date2026-02
LicenseOpen-weight
Context window128K tokens
Open weightYes
FB Score breakdown
Pave×30 = 19.8
FinanceBench×20 = 16.4
FinBen×10 = 7.5
FinQA×20 = 15.2
ConvFinQA×20 = 15.6
Finance Agent×30 = 13.5
MultiHiertt×10 = 7.2
EMB×10 = 5.8
CorpFin×20 = 13.7
FB Score (weighted avg)67.4
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.