Atlas

Compare Models

GPT-6.1 Terra vs Inkling 2 Small

GPT-6.1 Terra leads by 5.2 capability points (≈95% interval +2.9 to +7.4): a clear lead over Inkling 2 Small · P(higher) ≈ 100%

Inkling 2 Small wins 46 of 85 shared benchmarks (34 lost, 5 tied)

Capability vs. relative cost
GPT-6.1 TerraInkling 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.

GPT-6.1 TerravsInkling 2 Smallcapability vs. relative costData Nov 15, 2026Village LLM Atlasatlas.village.dev

Benchmark wins34 – 46 · 85 shared, 5 tied

Comparing matching setups only (15 benchmarks excluded) · suites counted once
← GPT-6.1 TerraInkling 2 Small →

GPT-6.1 TerravsInkling 2 Smallwins by categoryData Nov 15, 2026Data: Vals AI, Artificial Analysis, Mercor and 5 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 GPT-6.1 Terra.

Terminal-Bench-Science 0.1Science58.35.7−52.6
HLAB-Vals-1.1 - Energy Natural ResourcesLegal0.050.0+50.0
Terminal-Bench 4.0 (Artificial Analysis)Code55.613.1−42.4
HLAB-Vals-1.1 - Antitrust CompetitionLegal0.040.0+40.0
HLAB-Vals-1.1 - Litigation Dispute ResolutionLegal0.040.0+40.0
Legal Research Bench Civil LitigationLegal14.851.9+37.0
Terminal-Bench 4.0Code49.512.6−36.9
Code Migration v1.1 (Vals Index v2.2 subset)Code72.239.5−32.7
Legal Research Bench Business/CommercialLegal16.346.5+30.2
HLAB-Vals-1.1 - Arbitration International Dispute ResolutionLegal0.030.0+30.0
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 - Healthcare Life SciencesLegal0.030.0+30.0
HLAB-Vals-1.1 - ImmigrationLegal0.030.0+30.0
ChartographyMultimodal63.236.7−26.5
CritPt v2 (agentic, avg@5)Science81.455.7−25.7
Finance Agent v2.1 - PrecedentsFinance & Accounting25.847.1+21.3
HLAB-Vals-1.1 - Bankruptcy RestructuringLegal0.020.0+20.0
HLAB-Vals-1.1 - Capital MarketsLegal0.020.0+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 - Intellectual PropertyLegal0.020.0+20.0
HLAB-Vals-1.1 - International Trade SanctionsLegal0.020.0+20.0
HLAB-Vals-1.1 - Real EstateLegal10.030.0+20.0
HLAB-Vals-1.1 - Structured Finance SecuritizationLegal0.020.0+20.0
HLAB-Vals-1.1 - TaxLegal0.020.0+20.0
Legal Research Bench CriminalLegal17.536.8+19.3
Humanity's Last Exam DiamondGeneral QA47.328.7−18.6
APEX-Agents 1.1Professional Work79.360.9−18.4
Legal Research Bench FamilyLegal4.522.7+18.2
Legal Research Bench ImmigrationLegal9.127.3+18.2
VIALS-AA (pass^3)Multimodal60.242.9−17.4
FrontierCode 2.0 (Artificial Analysis)Code42.325.4−16.9
Finance Agent v2.1 - AdjustmentsFinance & Accounting50.667.4+16.8
Finance Agent v2.1 - Disclosure AnalysisFinance & Accounting64.280.8+16.6
Artificial Analysis Engineering IndexIndexes54.738.9−15.9
Legal Research Bench Constitutional/Civil RightsLegal23.739.5+15.8
AutomationBench-AA Operations, HR, Marketing, Sales and SupportAgents61.546.0−15.5
AutomationBench-AA Support and OperationsAgents70.054.8−15.2
Legal Research Bench Administrative/RegulatoryLegal45.560.6+15.2
Finance Agent v2.1 - ComparablesFinance & Accounting50.465.0+14.5
Finance Agent v2.1 - General Qualitative AnalysisFinance & Accounting63.878.0+14.2
Finance Agent v2.1 - All PassFinance & Accounting42.656.6+14.0
FrontierMemory v1.1Agents46.760.0+13.3
Legal Research Bench HealthLegal56.770.0+13.3
Tax Agent BenchFinance & Accounting55.065.8+10.7
AutomationBench-AA FinanceAgents54.443.9−10.5
HLAB-Vals-1.1 - Banking FinanceLegal0.010.0+10.0
HLAB-Vals-1.1 - Trusts Estates Private ClientLegal10.020.0+10.0
Medical Long Context Reasoning (MLCR-AA, October 2026 methodology)Health & Medicine30.620.6−10.0
Legal Research Bench Weighted PassLegal78.787.9+9.2
VIALS-AA (average of 3)Multimodal66.057.8−8.3
Excel Modeling Benchmark v1.1 LBOFinance & Accounting64.155.9−8.2
Finance Agent v2.1 - Financial ModelingFinance & Accounting35.142.4+7.3
Excel Modeling Benchmark v1.1 M&AFinance & Accounting80.773.7−7.0
AA-Briefcase v1.1 EloAgents14011527+6.9
GDPval-AA v2.1Professional Work14761630+6.8
AA-Omniscience v1.1 IndexIndexes29.616.1−6.7
Artificial Analysis Strategy & Ops IndexIndexes50.043.5−6.6
HLAB-Vals-1.1 - Criteria Pass RateLegal87.293.7+6.5
Finance Agent v2.1 - Earnings AnalysisFinance & Accounting83.088.9+5.9
Artificial Analysis Economics IndexIndexes48.543.4−5.1
Excel Modeling Benchmark v1.1 OperatingFinance & Accounting74.870.0−4.9
Artificial Analysis Legal IndexIndexes46.441.6−4.8
Finance Agent v2.1 - General Quantitative AnalysisFinance & Accounting74.479.2+4.8
Excel Modeling Benchmark v1.1 TemplateFinance & Accounting76.371.6−4.7
Artificial Analysis Finance & Accounting IndexIndexes49.044.3−4.7
SWE Atlas v1.1 - OverallCode57.761.9+4.2
Artificial Analysis Healthcare & Medical IndexIndexes44.740.8−4.0
GDP.pdf (Artificial Analysis, All-pass)Professional Work28.625.2−3.4
Excel Modeling Benchmark v1.1 ScratchFinance & Accounting70.367.1−3.3
Excel Modeling Benchmark v1.1 DataroomFinance & Accounting86.383.4−2.9
SciCode 1.0.1 (Artificial Analysis)Code55.152.3−2.8
Finance Agent v2.1 - Market AnalysisFinance & Accounting56.359.0+2.7
Excel Modeling Benchmark v1.1 CompsFinance & Accounting75.673.1−2.5
Vibe Code Bench v1.1Code84.081.5−2.5
Excel Modeling Benchmark v1.1 DCFFinance & Accounting64.362.2−2.1
APEX-Accounting 1.1Finance & Accounting63.762.0−1.7
Excel Modeling Benchmark v1.1 MiscFinance & Accounting67.568.3+0.8
VIALS-AA (pass@3)Multimodal71.472.0+0.6
HLAB-Vals-1.1 - Corporate M&ALegal20.020.00.0
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

GPT-6.1 TerravsInkling 2 Smallnormalised score marginsData Nov 15, 2026Data: Vals AI, Artificial Analysis, Mercor and 5 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…