Atlas

Compare Models

Grok 4.7 vs Inkling 2 Small

Grok 4.7 leads by 0.5 capability points (≈95% interval −1.6 to +2.6): statistically tied · P(higher) ≈ 67%

Wins 57 of 118 shared benchmarks (49 lost, 12 tied)

Capability vs. relative cost
Grok 4.7Inkling 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.

Grok 4.7vsInkling 2 Smallcapability vs. relative costData Nov 15, 2026Village LLM Atlasatlas.village.dev

Benchmark wins57 – 49 · 118 shared, 12 tied

Comparing matching setups only (51 benchmarks excluded) · suites counted once
← Grok 4.7Inkling 2 Small →

Grok 4.7vsInkling 2 Smallwins by categoryData Nov 15, 2026Data: Vals AI, Artificial Analysis, Surge AI and 12 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 Grok 4.7.

DeepSWE v1.1Code33.372.1+38.8
BrokenArXiv 09/2026 (Native Harnesses)Math27.763.2+35.5
HLAB-Vals-1.1 - Corporate GovernanceLegal0.030.0+30.0
AutomationBench-AA FinanceAgents72.743.9−28.8
BrokenArXiv 08/2026 (Native Harnesses)Math35.163.1+28.0
HANDBOOK.md Agents v1.1Professional Work44.017.8−26.2
FrontierMemory v1.1Agents37.860.0+22.2
ChartographyMultimodal14.736.7+22.0
ARC-AGI-2General QA61.481.7+20.3
HLAB-Vals-1.1 - Antitrust CompetitionLegal20.040.0+20.0
HLAB-Vals-1.1 - Data Privacy CybersecurityLegal40.020.0−20.0
HLAB-Vals-1.1 - ImmigrationLegal10.030.0+20.0
HLAB-Vals-1.1 - TaxLegal0.020.0+20.0
Legal Research Bench ImmigrationLegal45.527.3−18.2
AutomationBench-AA Operations, HR, Marketing, Sales and SupportAgents64.046.0−18.0
AutomationBench-AA Support and OperationsAgents72.454.8−17.6
Terminal-Bench 4.0Code28.812.6−16.2
ArXivMath 09/2026 (Native Harnesses)Math45.331.1−14.2
Terminal-Bench 4.0 (Artificial Analysis)Code25.813.1−12.6
Code Migration v1.1 (Vals Index v2.2 subset)Code51.839.5−12.4
DAYJOB: Finance (October 2026 rescoring)Finance & Accounting26.514.3−12.2
Finance Agent v2.1 - PrecedentsFinance & Accounting35.447.1+11.7
Artificial Analysis Strategy & Ops IndexIndexes54.843.5−11.4
Legal Research Bench CriminalLegal47.436.8−10.5
Finance Agent v2.1 - ComparablesFinance & Accounting54.965.0+10.1
HLAB-Vals-1.1 - Arbitration International Dispute ResolutionLegal20.030.0+10.0
HLAB-Vals-1.1 - Banking FinanceLegal0.010.0+10.0
HLAB-Vals-1.1 - Bankruptcy RestructuringLegal30.020.0−10.0
HLAB-Vals-1.1 - Capital MarketsLegal30.020.0−10.0
HLAB-Vals-1.1 - Energy Natural ResourcesLegal40.050.0+10.0
HLAB-Vals-1.1 - Funds Asset ManagementLegal40.030.0−10.0
HLAB-Vals-1.1 - Healthcare Life SciencesLegal20.030.0+10.0
HLAB-Vals-1.1 - International Trade SanctionsLegal10.020.0+10.0
HLAB-Vals-1.1 - Trusts Estates Private ClientLegal30.020.0−10.0
Finance Agent v2.1 - General Quantitative AnalysisFinance & Accounting69.479.2+9.8
ArXivMath 08/2026 (Native Harnesses)Math46.536.8−9.6
Finance Agent v2.1 - Disclosure AnalysisFinance & Accounting71.280.8+9.6
Finance Agent v2.1 - AdjustmentsFinance & Accounting58.567.4+8.9
Finance Agent v2.1 - General Qualitative AnalysisFinance & Accounting70.178.0+7.9
APEX-Agents 1.1Professional Work68.760.9−7.8
AA-Omniscience v1.1 IndexIndexes31.216.1−7.6
Legal Research Bench Civil LitigationLegal44.451.9+7.4
Artificial Analysis Finance & Accounting IndexIndexes51.744.3−7.3
Finance Agent v2.1 - All PassFinance & Accounting49.256.6+7.3
Terminal-Bench Science 0.1 (Vals)Science10.02.9−7.1
AA-Briefcase v1.1 EloAgents16571527−7.1
Excel Modeling Benchmark v1.1 M&AFinance & Accounting80.773.7−7.1
SWE-Marathon v1.1Code45.638.8−6.8
FrontierCode 2.0 - Pass RateCode32.325.5−6.8
APEX-Accounting 1.1Finance & Accounting55.362.0+6.7
Legal Research Bench HealthLegal76.770.0−6.7
CritPt v2 (agentic, avg@5)Science62.355.7−6.6
ARC-AGI-1 Semi-PrivateGeneral QA90.296.5+6.3
FrontierCode 2.0 - ScoreCode28.922.6−6.3
SAGE v1.1 - Partial Differential EquationsMath87.794.0+6.3
VIALS-AA (pass@3)Multimodal65.872.0+6.2
Legal Research Bench Administrative/RegulatoryLegal54.560.6+6.1
Artificial Analysis Healthcare & Medical IndexIndexes46.640.8−5.8
Terminal-Bench-Science 0.1Science11.45.7−5.7
Artificial Analysis Legal IndexIndexes47.241.6−5.6
SciCode 1.0.1 (Artificial Analysis)Code57.852.3−5.4
VIALS-AA (average of 3)Multimodal52.457.8+5.4
Finance Agent v2.1 - Financial ModelingFinance & Accounting37.242.4+5.2
Humanity's Last Exam DiamondGeneral QA23.628.7+5.1
AA-3D v1.0 EloCode9921027+5.1
Finance Agent v2.1 - Market AnalysisFinance & Accounting64.059.0−5.0
VIALS-AA (pass^3)Multimodal37.942.9+5.0
Excel Modeling Benchmark v1.1 LBOFinance & Accounting60.655.9−4.7
Vibe Code Bench v1.1Code86.281.5−4.6
Legal Research Bench FamilyLegal18.222.7+4.5
Finance Agent v2.1 - Earnings AnalysisFinance & Accounting84.588.9+4.4
ComplexConstraintsChat & Writing48.944.5−4.4
DeepFinanceFinance & Accounting34.129.8−4.3
GDPval-AA v2.1Professional Work17181630−3.9
AA-AnalystAgent (pass^5)Professional Work55.051.3−3.8
Terminal-Bench 2.1Code85.081.3−3.7
EnterpriseBench: CoreCraftProfessional Work68.271.8+3.6
Excel Modeling Benchmark v1.1 TemplateFinance & Accounting75.171.6−3.5
Arena Code WebDev — HTMLCode16361660+3.4
CyberBench v1.1 OverallCybersecurity69.572.7+3.3
Tax Agent BenchFinance & Accounting69.065.8−3.2
SWE-bench VerifiedCode79.182.2+3.1
SWE-bench MultilingualCode84.281.2−3.0
Artificial Analysis Engineering IndexIndexes41.838.9−2.9
Excel Modeling Benchmark v1.1 DCFFinance & Accounting65.162.2−2.9
Legal Research Bench Constitutional/Civil RightsLegal42.139.5−2.6
SAGE v1.1 - Linear AlgebraMath83.180.5−2.6
Legal Research Bench Business/CommercialLegal44.246.5+2.3
Artificial Analysis Economics IndexIndexes45.743.4−2.3
Vals Science IndexIndexes34.832.7−2.1
GDP.pdf (Artificial Analysis, All-pass)Professional Work23.225.2+2.0
SRE Bench — Fully SolvedCode3.81.9−1.9
sudo L7 (October 2026 rescoring)Code12.214.1+1.9
Legal Research Bench Weighted PassLegal86.687.9+1.3
SAGE v1.1 - Computer ScienceMath92.591.2−1.3
Excel Modeling Benchmark v1.1 DataroomFinance & Accounting84.683.4−1.2
Excel Modeling Benchmark v1.1 OperatingFinance & Accounting68.870.0+1.2
BioMysteryBench (Vals Terminus 2)Science69.370.0+0.7
Excel Modeling Benchmark v1.1 CompsFinance & Accounting72.473.1+0.7
Medical Long Context Reasoning (MLCR-AA, October 2026 methodology)Health & Medicine21.120.6−0.6
Arena Code WebDev — ReactCode16621659−0.5
Excel Modeling Benchmark v1.1 ScratchFinance & Accounting67.567.1−0.5
SWE-bench Multimodal (Vals v1, 480 Tasks)Code42.943.1+0.2
SWE Atlas v1.1 - OverallCode62.161.9−0.2
HLAB-Vals-1.1 - Criteria Pass RateLegal93.793.7+0.1
Excel Modeling Benchmark v1.1 MiscFinance & Accounting68.268.3+0.1
HLAB-Vals-1.1 - Corporate M&ALegal20.020.00.0
HLAB-Vals-1.1 - Emerging Companies Venture CapitalLegal20.020.00.0
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 - Intellectual PropertyLegal20.020.00.0
HLAB-Vals-1.1 - Litigation Dispute ResolutionLegal40.040.00.0
HLAB-Vals-1.1 - Real EstateLegal30.030.00.0
HLAB-Vals-1.1 - Structured Finance SecuritizationLegal20.020.00.0
HLAB-Vals-1.1 - White Collar Defense InvestigationsLegal0.00.00.0
MysteryMechanismScience25.225.20.0
ProgramBenchCode0.50.50.0

Grok 4.7vsInkling 2 Smallnormalised score marginsData Nov 15, 2026Data: Vals AI, Artificial Analysis, Surge AI and 12 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…