Atlas

Compare Models

GPT-6.1 Sol vs Inkling 2 Small

GPT-6.1 Sol leads by 6.2 capability points (≈95% interval +3.8 to +8.5): a clear lead over Inkling 2 Small · P(higher) ≈ 100%

Wins 58 of 110 shared benchmarks (45 lost, 7 tied)

Capability vs. relative cost
GPT-6.1 SolInkling 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 SolvsInkling 2 Smallcapability vs. relative costData Nov 15, 2026Village LLM Atlasatlas.village.dev

Benchmark wins58 – 45 · 110 shared, 7 tied

Comparing matching setups only (63 benchmarks excluded) · suites counted once
← GPT-6.1 SolInkling 2 Small →

GPT-6.1 SolvsInkling 2 Smallwins by categoryData Nov 15, 2026Data: Vals AI, Artificial Analysis, Surge AI 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 GPT-6.1 Sol.

Terminal-Bench-Science 0.1Science58.15.7−52.4
Terminal-Bench Science 0.1 (Vals)Science52.92.9−50.0
SRE Bench — Fully SolvedCode50.81.9−48.9
Terminal-Bench 4.0Code58.212.6−45.6
Terminal-Bench 4.0 (Artificial Analysis)Code56.113.1−42.9
HLAB-Vals-1.1 - Litigation Dispute ResolutionLegal0.040.0+40.0
CrossSearch (pass^3)Search59.023.0−36.0
Code Migration v1.1 (Vals Index v2.2 subset)Code75.139.5−35.7
CyberBench v1.1 OverallCybersecurity39.372.7+33.5
Humanity's Last Exam DiamondGeneral QA58.828.7−30.1
HLAB-Vals-1.1 - Antitrust CompetitionLegal10.040.0+30.0
HLAB-Vals-1.1 - Arbitration International Dispute ResolutionLegal0.030.0+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
Vals Science IndexIndexes59.632.7−26.9
CritPt v2 (agentic, avg@5)Science82.655.7−26.9
ComplexConstraints (November 2026 rescoring)Chat & Writing70.147.6−22.5
Legal Research Bench Civil LitigationLegal29.651.9+22.2
EnterpriseBench: CoreCraftProfessional Work50.371.8+21.5
MysteryMechanismScience46.425.2−21.2
Artificial Analysis Engineering IndexIndexes59.438.9−20.5
AutomationBench-AA Support and OperationsAgents75.054.8−20.2
AutomationBench-AA Operations, HR, Marketing, Sales and SupportAgents66.146.0−20.1
HLAB-Vals-1.1 - Corporate GovernanceLegal10.030.0+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 - Energy Natural ResourcesLegal30.050.0+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
sudo L7 (October 2026 rescoring)Code33.914.1−19.8
DAYJOB: Finance (October 2026 rescoring)Finance & Accounting33.514.3−19.2
Medical Long Context Reasoning (MLCR-AA, October 2026 methodology)Health & Medicine38.320.6−17.8
VIALS-AA (pass^3)Multimodal59.042.9−16.1
AutomationBench-AA FinanceAgents59.243.9−15.3
FrontierCode 2.0 (Artificial Analysis)Code40.625.4−15.2
Finance Agent v2.1 - ComparablesFinance & Accounting50.165.0+14.9
Artificial Analysis Strategy & Ops IndexIndexes57.643.5−14.2
AA-3D v1.0 EloCode11211027−13.6
Finance Agent v2.1 - General Qualitative AnalysisFinance & Accounting64.578.0+13.5
Humanity's Sixth SenseMultimodal46.633.3−13.3
AA-Omniscience v1.1 IndexIndexes42.416.1−13.1
Artificial Analysis Economics IndexIndexes56.343.4−12.9
Finance Agent v2.1 - AdjustmentsFinance & Accounting54.767.4+12.7
Finance Agent v2.1 - Disclosure AnalysisFinance & Accounting68.380.8+12.5
ARC-AGI-2General QA94.281.7−12.5
APEX-Agents 1.1Professional Work73.260.9−12.3
Artificial Analysis Legal IndexIndexes53.741.6−12.1
Excel Modeling Benchmark v1.1 CompsFinance & Accounting61.273.1+11.9
Artificial Analysis Finance & Accounting IndexIndexes56.244.3−11.9
Artificial Analysis Healthcare & Medical IndexIndexes52.040.8−11.3
HANDBOOK.md Agents v1.1Professional Work28.617.8−10.8
Finance Agent v2.1 - Financial ModelingFinance & Accounting52.642.4−10.2
HLAB-Vals-1.1 - Bankruptcy RestructuringLegal10.020.0+10.0
HLAB-Vals-1.1 - Emerging Companies Venture CapitalLegal10.020.0+10.0
HLAB-Vals-1.1 - Intellectual PropertyLegal10.020.0+10.0
HLAB-Vals-1.1 - Trusts Estates Private ClientLegal10.020.0+10.0
BioMysteryBench (Vals Terminus 2)Science79.670.0−9.6
Excel Modeling Benchmark v1.1 M&AFinance & Accounting83.173.7−9.4
Legal Research Bench ImmigrationLegal18.227.3+9.1
FrontierMemory v1.1Agents51.160.0+8.9
Finance Agent v2.1 - All PassFinance & Accounting48.256.6+8.4
Excel Modeling Benchmark v1.1 LBOFinance & Accounting63.855.9−7.9
Legal Research Bench Constitutional/Civil RightsLegal31.639.5+7.9
Legal Research Bench Administrative/RegulatoryLegal53.060.6+7.6
Vibe Code Bench v1.1Code88.981.5−7.4
VIALS-AA (average of 3)Multimodal64.857.8−7.0
Legal Research Bench Business/CommercialLegal39.546.5+7.0
GDP.pdf (Artificial Analysis, All-pass)Professional Work32.025.2−6.8
Excel Modeling Benchmark v1.1 MiscFinance & Accounting61.568.3+6.8
SAGE v1.1 - Linear AlgebraMath87.280.5−6.7
Legal Research Bench HealthLegal76.770.0−6.7
SWE-bench VerifiedCode87.382.2−5.1
Finance Agent v2.1 - Earnings AnalysisFinance & Accounting83.988.9+5.1
Excel Modeling Benchmark v1.1 DCFFinance & Accounting67.162.2−4.9
Legal Research Bench FamilyLegal18.222.7+4.5
Excel Modeling Benchmark v1.1 OperatingFinance & Accounting74.470.0−4.4
Finance Agent v2.1 - PrecedentsFinance & Accounting42.747.1+4.3
Terminal-Bench 2.1Code85.481.3−4.1
SWE Atlas v1.1 - OverallCode65.961.9−4.0
SWE-bench MultilingualCode84.981.2−3.7
Legal Research Bench Weighted PassLegal84.387.9+3.6
Excel Modeling Benchmark v1.1 TemplateFinance & Accounting75.171.6−3.5
SciCode 1.0.1 (Artificial Analysis)Code55.852.3−3.5
Tax Agent BenchFinance & Accounting62.365.8+3.4
SAGE v1.1 - Partial Differential EquationsMath90.794.0+3.3
DeepSWE v1.1Code75.272.1−3.1
Excel Modeling Benchmark v1.1 DataroomFinance & Accounting86.583.4−3.1
ProgramBenchCode3.00.5−2.5
APEX-Accounting 1.1Finance & Accounting64.362.0−2.3
HLAB-Vals-1.1 - Criteria Pass RateLegal91.593.7+2.2
ARC-AGI-1 Semi-PrivateGeneral QA98.596.5−2.0
Finance Agent v2.1 - Market AnalysisFinance & Accounting61.059.0−2.0
Legal Research Bench CriminalLegal35.136.8+1.8
AA-Briefcase v1.1 EloAgents15551527−1.5
AA-AnalystAgent (pass^5)Professional Work50.051.3+1.2
VIALS-AA (pass@3)Multimodal70.872.0+1.2
SAGE v1.1 - Computer ScienceMath92.491.2−1.2
GDPval-AA v2.1Professional Work16071630+1.0
Finance Agent v2.1 - General Quantitative AnalysisFinance & Accounting78.679.2+0.6
SWE-bench Multimodal (Vals v1, 480 Tasks)Code43.543.1−0.4
Excel Modeling Benchmark v1.1 ScratchFinance & Accounting66.967.1+0.1
HLAB-Vals-1.1 - Banking FinanceLegal10.010.00.0
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 - Real EstateLegal30.030.00.0
HLAB-Vals-1.1 - White Collar Defense InvestigationsLegal0.00.00.0

GPT-6.1 SolvsInkling 2 Smallnormalised score marginsData Nov 15, 2026Data: Vals AI, Artificial Analysis, Surge AI 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…