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 Small
Thinking Machines logoThinking Machines

Inkling Small

Open-weight#41 on FB Leaderboard262K contextReleased 2026-07-3024 benchmarks evaluated
View Benchmarks →Submit a score
51.5
FB Score
#41
Overall rank
FB Score51.5Rank #41
Best benchmark85.9%LiveCodeBench
PAVE overall—%Level 1-4
Benchmarks24 / 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
56.2%
Rank #32 of 33
Document QA
56.1%
Rank #40 of 45
Numerical
53.9%
Rank #31 of 32
Forensic
53.1%
Rank #33 of 45
Multi-domain
Not evaluated
No data
Agent Tasks
36.1%
Rank #39 of 44
Performance profile
80%Verification56.2%Document QA56.1%Numerical53.9%Forensic53.1%Agent Tasks36.1%
Benchmark results24 evaluated · 18 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
41.3#39 / 44Tier 130FB 20262026-09
MultiHiertt
Numerical
——Tier 310FB 2026Pending
FinAuditing
ForensicCompliance
——Tier 310FB 2026Pending
VALS Index
VerificationNumericalAgent Tasks
31.9#20 / 22Tier 125FB 20262026-07
MortgageTax Benchmark
NumericalForensic
62.3#21 / 22Tier 220FB 20262026-07
TaxEval v2
VerificationForensic
75.5#12 / 24Tier 220FB 20262026-07
Code Migration
Agent Tasks
13.7#18 / 23Tier 310FB 20262026-07
CyberBench
Forensic
68.8#7 / 11Tier 310FB 20262026-07
Excel Modeling Benchmark
Document QAForensic
31.8#40 / 44Tier 310FB 20262026-09
Legal Research Bench
Document QAForensic
25.5#17 / 22Tier 310FB 20262026-07
MedCode
Verification
37.9#19 / 20Tier 310FB 20262026-07
MedScribe
Document QA
84.1#12 / 20Tier 310FB 20262026-07
ProofBench v1.1
NumericalVerification
6.0#12 / 13Tier 310FB 20262026-07
SAGE
Agent Tasks
32.7#16 / 17Tier 310FB 20262026-07
Public Benefits Bench
VerificationForensic
59.4#12 / 16Tier 310FB 20262026-07
Vibe Code Bench v1.1
Agent Tasks
19.1#21 / 23Tier 310FB 20262026-07
Harvey's Legal Agent
Agent TasksForensic
1.7#16 / 22Tier 310FB 20262026-07
GPQA Diamond
NumericalVerification
83.6#20 / 20Tier 215FB 20262026-07
IOI
Numerical
——Tier 310FB 2026Pending
LiveCodeBench
Agent Tasks
85.9#10 / 19Tier 310FB 20262026-07
LegalBench
Document QAForensic
83.0#16 / 21Tier 310FB 20262026-07
MMLU Pro
NumericalVerification
85.6#20 / 21Tier 215FB 20262026-07
MMMU
Document QANumerical
——Tier 310FB 2026Pending
ProgramBench
Agent Tasks
0.5#5 / 17Tier 310FB 20262026-07
SkillsBench
Agent Tasks
33.6#15 / 17Tier 310FB 20262026-07
SWE-bench
Agent Tasks
82.2#13 / 22Tier 220FB 20262026-07
Terminal-Bench 2.1
Agent Tasks
55.0#17 / 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
——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
69.6#6 / 13Tier 220FB 20262026-08
Contents.md
Model info
OrganisationThinking Machines
Release date2026-07-30
LicenseOpen-weight
Context window262K tokens
Open weightYes
FB Score breakdown
Finance Agent×30 = 12.4
VALS Index×25 = 8.0
MortgageTax×20 = 12.5
TaxEval v2×20 = 15.1
Code Migration×10 = 1.4
CyberBench×10 = 6.9
EMB×10 = 3.2
Legal Research×10 = 2.5
MedCode×10 = 3.8
MedScribe×10 = 8.4
ProofBench×10 = 0.6
SAGE×10 = 3.3
Public Benefits×10 = 5.9
Vibe Code Bench×10 = 1.9
Harvey Legal×10 = 0.2
GPQA Diamond×15 = 12.5
LiveCodeBench×10 = 8.6
LegalBench×10 = 8.3
MMLU Pro×15 = 12.8
ProgramBench×10 = 0.1
SkillsBench×10 = 3.4
SWE-bench×20 = 16.4
Terminal-Bench×10 = 5.5
CorpFin×20 = 13.9
FB Score (weighted avg)51.5
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.