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/Inkling
Thinking Machines logoThinking Machines

Inkling

Open-weight#40 on FB Leaderboard256K contextReleased 2026-07-1526 benchmarks evaluated
View Benchmarks →Submit a score
52.3
FB Score
#40
Overall rank
FB Score52.3Rank #40
Best benchmark87.1%GPQA Diamond
PAVE overall—%Level 1-4
Benchmarks26 / 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
56.4%
Rank #31 of 33
Document QA
62.7%
Rank #34 of 45
Numerical
58.3%
Rank #30 of 32
Forensic
52.6%
Rank #35 of 45
Multi-domain
Not evaluated
No data
Agent Tasks
35.9%
Rank #40 of 44
Performance profile
80%Verification56.4%Document QA62.7%Numerical58.3%Forensic52.6%Agent Tasks35.9%
Benchmark results26 evaluated · 16 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
46.6#34 / 44Tier 130FB 20262026-09
MultiHiertt
Numerical
——Tier 310FB 2026Pending
FinAuditing
ForensicCompliance
——Tier 310FB 2026Pending
VALS Index
VerificationNumericalAgent Tasks
34.1#19 / 22Tier 125FB 20262026-07
MortgageTax Benchmark
NumericalForensic
64.0#19 / 22Tier 220FB 20262026-07
TaxEval v2
VerificationForensic
75.3#13 / 24Tier 220FB 20262026-07
Code Migration
Agent Tasks
11.8#20 / 23Tier 310FB 20262026-07
CyberBench
Forensic
64.1#8 / 11Tier 310FB 20262026-07
Excel Modeling Benchmark
Document QAForensic
38.4#39 / 44Tier 310FB 20262026-09
Legal Research Bench
Document QAForensic
28.4#16 / 22Tier 310FB 20262026-07
MedCode
Verification
41.2#15 / 20Tier 310FB 20262026-07
MedScribe
Document QA
85.4#8 / 20Tier 310FB 20262026-07
ProofBench v1.1
NumericalVerification
0.0#13 / 13Tier 310FB 20262026-07
SAGE
Agent Tasks
36.5#14 / 17Tier 310FB 20262026-07
Public Benefits Bench
VerificationForensic
58.5#13 / 16Tier 310FB 20262026-07
Vibe Code Bench v1.1
Agent Tasks
19.2#20 / 23Tier 310FB 20262026-07
Harvey's Legal Agent
Agent TasksForensic
2.1#15 / 22Tier 310FB 20262026-07
GPQA Diamond
NumericalVerification
87.1#15 / 20Tier 215FB 20262026-07
IOI
Numerical
——Tier 310FB 2026Pending
LiveCodeBench
Agent Tasks
85.5#13 / 19Tier 310FB 20262026-07
LegalBench
Document QAForensic
83.0#17 / 21Tier 310FB 20262026-07
MMLU Pro
NumericalVerification
86.3#15 / 21Tier 215FB 20262026-07
MMMU
Document QANumerical
78.5#13 / 14Tier 310FB 20262026-07
ProgramBench
Agent Tasks
0.0#8 / 17Tier 310FB 20262026-07
SkillsBench
Agent Tasks
26.1#17 / 17Tier 310FB 20262026-07
SWE-bench
Agent Tasks
77.6#17 / 22Tier 220FB 20262026-07
Terminal-Bench 2.1
Agent Tasks
47.6#23 / 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
43.5#17 / 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
68.6#7 / 13Tier 220FB 20262026-08
Contents.md
Model info
OrganisationThinking Machines
Release date2026-07-15
LicenseOpen-weight
Context window256K tokens
Open weightYes
FB Score breakdown
Finance Agent×30 = 14.0
VALS Index×25 = 8.5
MortgageTax×20 = 12.8
TaxEval v2×20 = 15.1
Code Migration×10 = 1.2
CyberBench×10 = 6.4
EMB×10 = 3.8
Legal Research×10 = 2.8
MedCode×10 = 4.1
MedScribe×10 = 8.5
ProofBench×10 = 0.0
SAGE×10 = 3.7
Public Benefits×10 = 5.8
Vibe Code Bench×10 = 1.9
Harvey Legal×10 = 0.2
GPQA Diamond×15 = 13.1
LiveCodeBench×10 = 8.6
LegalBench×10 = 8.3
MMLU Pro×15 = 12.9
MMMU×10 = 7.8
ProgramBench×10 = 0.0
SkillsBench×10 = 2.6
SWE-bench×20 = 15.5
Terminal-Bench×10 = 4.8
Tax Agent×10 = 4.4
CorpFin×20 = 13.7
FB Score (weighted avg)52.3
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.