Atlas

Compare Models

DeepSeek V4.1 Flash 1017 vs Inkling 2 Small

DeepSeek V4.1 Flash 1017 leads by 0.8 capability points (≈95% interval −1.5 to +3.1): statistically tied · P(higher) ≈ 76%

Inkling 2 Small wins 60 of 101 shared benchmarks (31 lost, 10 tied)

Capability vs. relative cost
DeepSeek V4.1 Flash 1017Inkling 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.

DeepSeek V4.1 Flash 1017vsInkling 2 Smallcapability vs. relative costData Nov 15, 2026Village LLM Atlasatlas.village.dev

Benchmark wins31 – 60 · 101 shared, 10 tied

Comparing matching setups only (14 benchmarks excluded) · suites counted once
← DeepSeek V4.1 Flash 1017Inkling 2 Small →

DeepSeek V4.1 Flash 1017vsInkling 2 Smallwins by categoryData Nov 15, 2026Data: Vals AI, Artificial Analysis, MathArena and 8 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 DeepSeek V4.1 Flash 1017.

AutomationBench-AA FinanceAgents74.143.9−30.2
Code Migration v1.1 (Vals Index v2.2 subset)Code68.539.5−29.0
Terminal-Bench 4.0 (Artificial Analysis)Code33.813.1−20.7
HLAB-Vals-1.1 - Arbitration International Dispute ResolutionLegal10.030.0+20.0
HLAB-Vals-1.1 - Emerging Companies Venture CapitalLegal0.020.0+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 - Litigation Dispute ResolutionLegal20.040.0+20.0
HLAB-Vals-1.1 - Real EstateLegal10.030.0+20.0
Terminal-Bench 4.0Code31.812.6−19.2
AutomationBench-AA Operations, HR, Marketing, Sales and SupportAgents65.046.0−19.0
APEX-Agents 1.1Professional Work79.460.9−18.5
Finance Agent v2.1 - PrecedentsFinance & Accounting29.347.1+17.7
AutomationBench-AA Support and OperationsAgents72.154.8−17.3
PerceptionBenchMultimodal47.764.7+17.0
BrokenArXiv 08/2026 (Native Harnesses)Math46.763.1+16.4
Legal Research Bench Civil LitigationLegal37.051.9+14.8
ArXivMath 09/2026 (Native Harnesses)Math45.331.1−14.2
BrokenArXiv 10/2026 (Native Harnesses)Math49.763.3+13.6
BrokenArXiv 09/2026 (Native Harnesses)Math49.763.2+13.5
EnterpriseBench: CoreCraftProfessional Work58.571.8+13.3
ArXivMath 10/2026 (Native Harnesses)Math38.327.7−10.6
Finance Agent v2.1 - Disclosure AnalysisFinance & Accounting70.380.8+10.5
HLAB-Vals-1.1 - Antitrust CompetitionLegal30.040.0+10.0
HLAB-Vals-1.1 - Bankruptcy RestructuringLegal10.020.0+10.0
HLAB-Vals-1.1 - Corporate GovernanceLegal20.030.0+10.0
HLAB-Vals-1.1 - Data Privacy CybersecurityLegal10.020.0+10.0
HLAB-Vals-1.1 - Funds Asset ManagementLegal40.030.0−10.0
HLAB-Vals-1.1 - ImmigrationLegal20.030.0+10.0
HLAB-Vals-1.1 - Intellectual PropertyLegal10.020.0+10.0
HLAB-Vals-1.1 - TaxLegal10.020.0+10.0
Tax Agent BenchFinance & Accounting74.965.8−9.2
Legal Research Bench ImmigrationLegal36.427.3−9.1
CharXiv ReasoningMultimodal77.085.6+8.6
GDP.pdf (Artificial Analysis, All-pass)Professional Work17.225.2+8.0
Humanity's Last Exam DiamondGeneral QA20.828.7+7.9
AA-Omniscience v1.1 IndexIndexes1.516.1+7.3
Terminal-Bench-Science 0.1Science12.95.7−7.1
Finance Agent v2.1 - General Qualitative AnalysisFinance & Accounting71.078.0+7.0
ArXivMath 08/2026 (Native Harnesses)Math43.936.8−7.0
Excel Modeling Benchmark v1.1 LBOFinance & Accounting62.555.9−6.6
HANDBOOK.md Agents v1.1Professional Work24.017.8−6.2
Vibe Code Bench v1.1Code87.781.5−6.2
Medical Long Context Reasoning (MLCR-AA, October 2026 methodology)Health & Medicine26.720.6−6.1
AA-Briefcase v1.1 EloAgents14161527+6.1
Artificial Analysis Strategy & Ops IndexIndexes49.243.5−5.8
VIALS-AA (pass@3)Multimodal66.572.0+5.6
Artificial Analysis Openness IndexIndexes44.438.9−5.6
Finance Agent v2.1 - All PassFinance & Accounting51.356.6+5.2
Finance Agent v2.1 - ComparablesFinance & Accounting59.865.0+5.2
Arena Code WebDev — HTMLCode16961660−5.1
Artificial Analysis Economics IndexIndexes38.543.4+4.9
VIALS-AA (average of 3)Multimodal53.257.8+4.6
Legal Research Bench FamilyLegal27.322.7−4.5
Finance Agent v2.1 - Earnings AnalysisFinance & Accounting93.088.9−4.1
Excel Modeling Benchmark v1.1 OperatingFinance & Accounting66.070.0+4.0
Artificial Analysis Legal IndexIndexes37.741.6+3.8
ARC-AGI-2General QA78.181.7+3.6
SciCode 1.0.1 (Artificial Analysis)Code55.952.3−3.6
CritPt v2 (agentic, avg@5)Science52.355.7+3.4
Legal Research Bench HealthLegal66.770.0+3.3
Finance Agent v2.1 - General Quantitative AnalysisFinance & Accounting76.079.2+3.2
Humanity's Sixth SenseMultimodal30.133.3+3.2
Excel Modeling Benchmark v1.1 DataroomFinance & Accounting86.583.4−3.1
Finance Agent v2.1 - Financial ModelingFinance & Accounting39.642.4+2.8
APEX-Accounting 1.1Finance & Accounting59.362.0+2.7
Legal Research Bench Constitutional/Civil RightsLegal42.139.5−2.6
Excel Modeling Benchmark v1.1 MiscFinance & Accounting65.768.3+2.5
FrontierCode 2.0 - Pass RateCode23.025.5+2.5
Excel Modeling Benchmark v1.1 DCFFinance & Accounting59.762.2+2.5
VIALS-AA (pass^3)Multimodal40.442.9+2.5
FrontierCode 2.0 - ScoreCode20.222.6+2.4
Excel Modeling Benchmark v1.1 CompsFinance & Accounting70.873.1+2.3
Legal Research Bench Business/CommercialLegal44.246.5+2.3
Artificial Analysis Finance & Accounting IndexIndexes42.244.3+2.2
Arena Code WebDev — ReactCode16751659−2.1
ARC-AGI-1 Semi-PrivateGeneral QA94.596.5+2.0
DAYJOB: Finance (October 2026 rescoring)Finance & Accounting12.514.3+1.8
Legal Research Bench CriminalLegal35.136.8+1.8
Finance Agent v2.1 - Market AnalysisFinance & Accounting60.759.0−1.7
Legal Research Bench Weighted PassLegal86.387.9+1.6
Legal Research Bench Administrative/RegulatoryLegal59.160.6+1.5
Artificial Analysis Engineering IndexIndexes37.638.9+1.3
BabyVision with PythonMultimodal92.593.6+1.1
HLAB-Vals-1.1 - Criteria Pass RateLegal92.793.7+1.1
Chartography (with tools)Multimodal83.082.1−0.9
Excel Modeling Benchmark v1.1 TemplateFinance & Accounting70.871.6+0.8
Finance Agent v2.1 - AdjustmentsFinance & Accounting66.867.4+0.6
Excel Modeling Benchmark v1.1 M&AFinance & Accounting73.173.7+0.6
Artificial Analysis Healthcare & Medical IndexIndexes41.340.8−0.6
Excel Modeling Benchmark v1.1 ScratchFinance & Accounting67.367.1−0.2
HLAB-Vals-1.1 - Banking FinanceLegal10.010.00.0
HLAB-Vals-1.1 - Capital MarketsLegal20.020.00.0
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 - Healthcare Life SciencesLegal30.030.00.0
HLAB-Vals-1.1 - InsuranceLegal0.00.00.0
HLAB-Vals-1.1 - Structured Finance SecuritizationLegal20.020.00.0
HLAB-Vals-1.1 - Trusts Estates Private ClientLegal20.020.00.0
HLAB-Vals-1.1 - White Collar Defense InvestigationsLegal0.00.00.0

DeepSeek V4.1 Flash 1017vsInkling 2 Smallnormalised score marginsData Nov 15, 2026Data: Vals AI, Artificial Analysis, MathArena and 8 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…