Atlas

Compare Models

Claude Opus 5.5 vs Inkling 2 Small

Claude Opus 5.5 leads by 7.6 capability points (≈95% interval +5.2 to +10.0): a clear lead over Inkling 2 Small · P(higher) ≈ 100%

Wins 56 of 81 shared benchmarks (18 lost, 7 tied)

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

Benchmark wins56 – 18 · 81 shared, 7 tied

Comparing matching setups only (59 benchmarks excluded) · suites counted once
← Claude Opus 5.5Inkling 2 Small →

Claude Opus 5.5vsInkling 2 Smallwins by categoryData Nov 15, 2026Data: Vals AI, Artificial Analysis, MathArena and 16 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 Opus 5.5.

Terminal-Bench-Science 0.1Science61.95.7−56.2
ArXivMath 10/2026 (Native Harnesses)Math79.827.7−52.1
ArXivMath 09/2026 (Native Harnesses)Math82.131.1−50.9
ArXivMath 08/2026 (Native Harnesses)Math86.036.8−49.1
Terminal-Bench 4.0 (Artificial Analysis)Code59.613.1−46.5
HLAB-Vals-1.1 - Antitrust CompetitionLegal0.040.0+40.0
HLAB-Vals-1.1 - Litigation Dispute ResolutionLegal0.040.0+40.0
HANDBOOK.md Agents v1.1Professional Work52.317.8−34.5
CrossSearch (pass^3)Search57.023.0−34.0
sudo L7 (October 2026 rescoring)Code45.614.1−31.5
HLAB-Vals-1.1 - Corporate GovernanceLegal0.030.0+30.0
DAYJOB: Finance (October 2026 rescoring)Finance & Accounting42.514.3−28.2
Arena Code WebDev — ReactCode18671659−27.8
SWE-bench Multimodal (Vals v1, 480 Tasks)Code70.243.1−27.1
FrontierCode 2.0 - Pass RateCode51.825.5−26.3
CritPt v2 (agentic, avg@5)Science81.755.7−26.0
Humanity's Last Exam DiamondGeneral QA54.628.7−25.9
AA-3D v1.0 EloCode12021027−25.4
DeepFinanceFinance & Accounting54.829.8−25.0
FrontierCode 2.0 - ScoreCode47.322.6−24.8
APEX-Agents 1.1Professional Work81.360.9−20.4
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 - Capital MarketsLegal0.020.0+20.0
HLAB-Vals-1.1 - ImmigrationLegal10.030.0+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 - TaxLegal0.020.0+20.0
AA-Briefcase v1.1 EloAgents18221527−16.2
SWE-bench VerifiedCode98.282.2−16.0
SWE Atlas v1.1 - OverallCode77.461.9−15.5
SciCode 1.0.1 (Artificial Analysis)Code66.952.3−14.6
BrokenArXiv 10/2026 (Native Harnesses)Math77.863.3−14.5
SWE-bench MultilingualCode95.581.2−14.3
BrokenArXiv 08/2026 (Native Harnesses)Math77.463.1−14.3
BrokenArXiv 09/2026 (Native Harnesses)Math76.763.2−13.5
FrontierMemory v1.1Agents73.360.0−13.3
Excel Modeling Benchmark v1.1 LBOFinance & Accounting68.355.9−12.5
PostTrainBench v1.2Indexes43.831.9−11.9
ARC-AGI-2General QA93.381.7−11.7
Humanity's Sixth SenseMultimodal44.633.3−11.3
FORTRESS Average Risk Score (ARS)Safety5.816.2−10.4
GDPval-AA v2.1Professional Work18661630−10.4
Arena Code WebDev — HTMLCode17321660−10.2
HLAB-Vals-1.1 - Banking FinanceLegal0.010.0+10.0
HLAB-Vals-1.1 - Data Privacy CybersecurityLegal30.020.0−10.0
HLAB-Vals-1.1 - Emerging Companies Venture CapitalLegal10.020.0+10.0
HLAB-Vals-1.1 - Funds Asset ManagementLegal20.030.0+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 - Structured Finance SecuritizationLegal10.020.0+10.0
Excel Modeling Benchmark v1.1 TemplateFinance & Accounting81.471.6−9.8
Excel Modeling Benchmark v1.1 M&AFinance & Accounting82.173.7−8.4
Excel Modeling Benchmark v1.1 OperatingFinance & Accounting77.770.0−7.8
Excel Modeling Benchmark v1.1 DCFFinance & Accounting69.962.2−7.6
SWE-Marathon v1.1Code46.338.8−7.5
Medical Long Context Reasoning (MLCR-AA, October 2026 methodology)Health & Medicine27.820.6−7.2
SAGE v1.1 - Linear AlgebraMath87.580.5−7.0
Chartography (with tools)Multimodal89.082.1−6.9
ComplexConstraintsChat & Writing49.944.5−5.4
AA-AnalystAgent (pass^5)Professional Work56.351.3−5.0
HLAB-Vals-1.1 - Criteria Pass RateLegal89.893.7+3.9
GDP.pdf (Artificial Analysis, All-pass)Professional Work28.825.2−3.6
APEX-Accounting 1.1Finance & Accounting65.562.0−3.5
Excel Modeling Benchmark v1.1 ScratchFinance & Accounting70.267.1−3.2
Excel Modeling Benchmark v1.1 DataroomFinance & Accounting86.283.4−2.8
Excel Modeling Benchmark v1.1 MiscFinance & Accounting71.068.3−2.7
EnterpriseBench: CoreCraftProfessional Work74.471.8−2.6
Excel Modeling Benchmark v1.1 CompsFinance & Accounting75.773.1−2.5
Terminal-Bench 2.1Code83.581.3−2.2
ARC-AGI-1 Semi-PrivateGeneral QA98.596.5−2.0
SAGE v1.1 - Computer ScienceMath92.891.2−1.5
SAGE v1.1 - Partial Differential EquationsMath93.494.0+0.6
DeepSWE v1.1Code72.372.1−0.2
HLAB-Vals-1.1 - Corporate M&ALegal20.020.00.0
HLAB-Vals-1.1 - Employment LaborLegal0.00.00.0
HLAB-Vals-1.1 - Energy Natural ResourcesLegal50.050.00.0
HLAB-Vals-1.1 - Environmental ESGLegal0.00.00.0
HLAB-Vals-1.1 - InsuranceLegal0.00.00.0
HLAB-Vals-1.1 - Trusts Estates Private ClientLegal20.020.00.0
HLAB-Vals-1.1 - White Collar Defense InvestigationsLegal0.00.00.0

Claude Opus 5.5vsInkling 2 Smallnormalised score marginsData Nov 15, 2026Data: Vals AI, Artificial Analysis, MathArena and 16 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…