Atlas

Compare Models

Claude Haiku 5.5 vs Inkling 2 Small

Claude Haiku 5.5 leads by 1.2 capability points (≈95% interval −0.9 to +3.3): statistically tied · P(higher) ≈ 87%

Inkling 2 Small wins 57 of 107 shared benchmarks (44 lost, 6 tied)

Capability vs. relative cost
Claude Haiku 5.5Inkling 2 SmallClosed weightsOpen weights

Each line runs through one model’s priced reasoning settings, cheapest to most expensive; grey points are other models’ priced settings in the same range. Results whose reasoning effort the source didn’t report are left out wherever a model has named effort levels. Capability and relative cost are the published estimates (relative cost is cost per task as a multiple of GPT-5 (high)); hover a setting, or use the arrow keys, to set it beside the other model’s same setting.

Claude Haiku 5.5vsInkling 2 Smallcapability vs. relative costData Nov 15, 2026Village LLM Atlasatlas.village.dev

Benchmark wins44 – 57 · 107 shared, 6 tied

Comparing matching setups only (49 benchmarks excluded) · suites counted once
← Claude Haiku 5.5Inkling 2 Small →

Claude Haiku 5.5vsInkling 2 Smallwins by categoryData Nov 15, 2026Data: Vals AI, Artificial Analysis, Mercor and 9 othersVillage LLM Atlasatlas.village.dev

Margins

Each benchmark scaled 0–100% (its declared range, else the field’s range); Δ is Inkling 2 Small minus Claude Haiku 5.5.

HLAB-Vals-1.1 - Antitrust CompetitionLegal0.040.0+40.0
HLAB-Vals-1.1 - Energy Natural ResourcesLegal10.050.0+40.0
HLAB-Vals-1.1 - Corporate GovernanceLegal0.030.0+30.0
HLAB-Vals-1.1 - Funds Asset ManagementLegal0.030.0+30.0
HLAB-Vals-1.1 - ImmigrationLegal0.030.0+30.0
HLAB-Vals-1.1 - Litigation Dispute ResolutionLegal10.040.0+30.0
Terminal-Bench 4.0Code36.412.6−23.7
ARC-AGI-2General QA61.381.7+20.4
HLAB-Vals-1.1 - Arbitration International Dispute ResolutionLegal10.030.0+20.0
HLAB-Vals-1.1 - Bankruptcy RestructuringLegal0.020.0+20.0
HLAB-Vals-1.1 - Corporate M&ALegal0.020.0+20.0
HLAB-Vals-1.1 - Data Privacy CybersecurityLegal0.020.0+20.0
HLAB-Vals-1.1 - Emerging Companies Venture CapitalLegal0.020.0+20.0
HLAB-Vals-1.1 - International Trade SanctionsLegal0.020.0+20.0
HLAB-Vals-1.1 - Structured Finance SecuritizationLegal0.020.0+20.0
HLAB-Vals-1.1 - TaxLegal0.020.0+20.0
HLAB-Vals-1.1 - Trusts Estates Private ClientLegal0.020.0+20.0
Terminal-Bench 4.0 (Artificial Analysis)Code32.813.1−19.7
AutomationBench-AA Support and OperationsAgents36.554.8+18.3
Finance Agent v2.1 - General Qualitative AnalysisFinance & Accounting63.678.0+14.5
Medical Long Context Reasoning (MLCR-AA, October 2026 methodology)Health & Medicine35.020.6−14.4
Terminal-Bench-Science 0.1Science20.05.7−14.3
Arena Code WebDev — HTMLCode15631660+13.6
AutomationBench-AA Operations, HR, Marketing, Sales and SupportAgents33.746.0+12.3
DeepSWE v1.1Code59.972.1+12.2
Excel Modeling Benchmark v1.1 MiscFinance & Accounting57.068.3+11.3
SWE-Marathon v1.1Code50.038.8−11.2
Legal Research Bench Civil LitigationLegal40.751.9+11.1
Code Migration v1.1 (Vals Index v2.2 subset)Code50.239.5−10.7
Excel Modeling Benchmark v1.1 M&AFinance & Accounting62.973.7+10.7
Legal Research Bench Administrative/RegulatoryLegal50.060.6+10.6
CritPt v2 (agentic, avg@5)Science66.355.7−10.6
DeepFinanceFinance & Accounting40.029.8−10.2
HLAB-Vals-1.1 - Banking FinanceLegal0.010.0+10.0
HLAB-Vals-1.1 - Healthcare Life SciencesLegal20.030.0+10.0
HLAB-Vals-1.1 - Intellectual PropertyLegal10.020.0+10.0
HLAB-Vals-1.1 - Real EstateLegal20.030.0+10.0
MysteryMechanismScience35.125.2−9.9
Excel Modeling Benchmark v1.1 ScratchFinance & Accounting57.767.1+9.4
Finance Agent v2.1 - Financial ModelingFinance & Accounting51.542.4−9.1
Legal Research Bench ImmigrationLegal36.427.3−9.1
Finance Agent v2.1 - Disclosure AnalysisFinance & Accounting71.880.8+9.0
Vibe Code Bench v1.1Code90.481.5−8.9
Finance Agent v2.1 - General Quantitative AnalysisFinance & Accounting87.879.2−8.6
Finance Agent v2.1 - ComparablesFinance & Accounting57.065.0+8.0
ARC-AGI-1 Semi-PrivateGeneral QA89.096.5+7.5
APEX-Agents 1.1Professional Work68.360.9−7.4
Excel Modeling Benchmark v1.1 OperatingFinance & Accounting62.770.0+7.2
Terminal-Bench Science 0.1 (Vals)Science10.02.9−7.1
Excel Modeling Benchmark v1.1 LBOFinance & Accounting49.155.9+6.7
SWE-bench VerifiedCode88.982.2−6.7
FrontierCode 2.0 - ScoreCode28.922.6−6.4
FrontierCode 2.0 - Pass RateCode31.925.5−6.4
SAGE v1.1 - Linear AlgebraMath86.880.5−6.3
VIALS-AA (pass^3)Multimodal49.142.9−6.2
Arena Code WebDev — ReactCode16151659+5.9
Vals Science IndexIndexes38.532.7−5.8
Legal Research Bench Constitutional/Civil RightsLegal44.739.5−5.3
Legal Research Bench CriminalLegal42.136.8−5.3
Finance Agent v2.1 - All PassFinance & Accounting51.856.6+4.8
Excel Modeling Benchmark v1.1 CompsFinance & Accounting77.773.1−4.6
Finance Agent v2.1 - Earnings AnalysisFinance & Accounting84.588.9+4.4
GDP.pdf (Artificial Analysis, All-pass)Professional Work20.825.2+4.4
Artificial Analysis Strategy & Ops IndexIndexes39.143.5+4.3
AA-3D v1.0 EloCode9981027+4.2
SAGE v1.1 - Partial Differential EquationsMath89.994.0+4.1
Finance Agent v2.1 - PrecedentsFinance & Accounting43.147.1+4.0
SWE-bench MultilingualCode85.181.2−3.9
SRE Bench — Fully SolvedCode5.71.9−3.8
Terminal-Bench 2.1Code85.081.3−3.7
Artificial Analysis Engineering IndexIndexes42.538.9−3.7
HLAB-Vals-1.1 - Criteria Pass RateLegal90.193.7+3.6
Tax Agent BenchFinance & Accounting62.265.8+3.5
Legal Research Bench HealthLegal66.770.0+3.3
Artificial Analysis Healthcare & Medical IndexIndexes37.540.8+3.3
Legal Research Bench Weighted PassLegal84.887.9+3.1
Artificial Analysis Legal IndexIndexes38.741.6+2.9
CyberBench v1.1 OverallCybersecurity75.572.7−2.7
VIALS-AA (average of 3)Multimodal60.557.8−2.7
SciCode 1.0.1 (Artificial Analysis)Code55.052.3−2.7
AA-AnalystAgent (pass^5)Professional Work53.851.3−2.5
SWE Atlas v1.1 - OverallCode59.461.9+2.5
AA-Briefcase v1.1 EloAgents15731527−2.5
Finance Agent v2.1 - Market AnalysisFinance & Accounting61.459.0−2.4
Excel Modeling Benchmark v1.1 DataroomFinance & Accounting85.883.4−2.4
Legal Research Bench Business/CommercialLegal44.246.5+2.3
ProgramBenchCode2.50.5−2.0
AA-Omniscience v1.1 IndexIndexes12.316.1+1.9
Excel Modeling Benchmark v1.1 TemplateFinance & Accounting73.471.6−1.8
Humanity's Last Exam DiamondGeneral QA29.628.7−0.9
Excel Modeling Benchmark v1.1 DCFFinance & Accounting63.162.2−0.9
SWE-bench Multimodal (Vals v1, 480 Tasks)Code44.043.1−0.8
Artificial Analysis Finance & Accounting IndexIndexes43.644.3+0.8
AutomationBench-AA FinanceAgents43.243.9+0.7
Artificial Analysis Economics IndexIndexes42.743.4+0.7
VIALS-AA (pass@3)Multimodal71.472.0+0.6
SAGE v1.1 - Computer ScienceMath91.691.2−0.4
BioMysteryBench (Vals Terminus 2)Science70.470.0−0.4
Finance Agent v2.1 - AdjustmentsFinance & Accounting67.767.4−0.2
APEX-Accounting 1.1Finance & Accounting62.262.0−0.2
GDPval-AA v2.1Professional Work16291630+0.1
HLAB-Vals-1.1 - Capital MarketsLegal20.020.00.0
HLAB-Vals-1.1 - Employment LaborLegal0.00.00.0
HLAB-Vals-1.1 - Environmental ESGLegal0.00.00.0
HLAB-Vals-1.1 - InsuranceLegal0.00.00.0
HLAB-Vals-1.1 - White Collar Defense InvestigationsLegal0.00.00.0
Legal Research Bench FamilyLegal22.722.70.0

Claude Haiku 5.5vsInkling 2 Smallnormalised score marginsData Nov 15, 2026Data: Vals AI, Artificial Analysis, Mercor and 9 othersVillage LLM Atlasatlas.village.dev

Win counts use each benchmark’s declared score direction. Represented suite slices and the derived Capability score are excluded from headline totals. Missing or incompatible setups are excluded, never counted as losses.
Loading Atlas data…