The Model Index
Up to four models

Claude Opus 5 vs Inkling-Small

On the index (GPT-4 = 100), Claude Opus 5 scores 185 and Inkling-Small 153. Side by side on the same third-party tests, with price and context. The link in your address bar shares this exact comparison.

Next to Claude Opus 5
Presets
Claude Opus 5
185169–201
WeightsClosed
ReleasedJul 2026
Price in / out$5.0 / $25
Context1M
Core tests taken6 of 9
Inkling-Small
153137–169
WeightsOpen
ReleasedJul 2026
Price in / out$0.45 / $1.2
Context524K
Core tests taken5 of 9

Claude Opus 5 leads Inkling-Small by 32 points, ahead on 5 of 5 shared core tests, at 16× the price.

Test by testthird-party results

Claude Opus 5Inkling-Small
0%25%50%75%100%REASONING & KNOWLEDGEGPQA Diamond (Epoch AI)GPQA Diamond (Epoch AI)TMGPQA Diamond (Vals AI)GPQA Diamond (Vals AI)TMMMLU ProMMLU ProTMSimpleQA VerifiedSimpleQA VerifiedTMMATHSFrontierMath (tiers 1-3)FrontierMath (tiers 1-3)TMAIME-style maths (OTIS mock)AIME-style maths (OTIS mock)TMProofBench v1.1ProofBench v1.1TMFrontierMath (tier 4)FrontierMath (tier 4)TMCODINGTerminal-Bench 4.0Terminal-Bench 4.0TMCode MigrationCode MigrationTMCyberBench v1.1CyberBench v1.1TMIOIIOITMLiveCodeBenchLiveCodeBenchTMProgramBenchProgramBenchTMSWE-benchSWE-benchTMVibe Code Bench v1.1Vibe Code Bench v1.1TMAGENTSSkillsBenchSkillsBenchTMMystery game puzzlesMystery game puzzlesTMPROFESSIONAL WORKFinance Agent (v2)Finance Agent (v2)TMCorpFin v2CorpFin v2TMEMBEMBTMLegalBenchLegalBenchTMLegal Research BenchLegal Research BenchTMMedCodeMedCodeTMMedScribeMedScribeTMMortgageTaxMortgageTaxTMPublic Benefits Bench v1.1Public Benefits Bench v1.1TMTax Agent BenchTax Agent BenchTMTaxEval v2TaxEval v2TMNOVEL PROBLEMSARC-AGI-2ARC-AGI-2TMARC-AGI-1ARC-AGI-1TM
Every result as a table
TestClaude Opus 5Inkling-Small
Reasoning & knowledge
GPQA Diamond (Epoch AI)93.9%88.5%
GPQA Diamond (Vals AI)93.4%83.6%
MMLU Pro91.6%85.6%
SimpleQA Verified59.9%19.1%
Maths
FrontierMath (tiers 1-3)85.6%46.3%
AIME-style maths (OTIS mock)98.9%90.0%
ProofBench v1.199.0%6.0%
FrontierMath (tier 4)73.2%17.1%
Coding
Terminal-Bench 4.053.5%0.0%
Code Migration57.5%13.7%
CyberBench v1.165.4%64.1%
IOI84.3%9.3%
LiveCodeBench89.0%85.9%
ProgramBench3.0%0.5%
SWE-bench97.0%82.2%
Vibe Code Bench v1.188.4%19.1%
Agents
SkillsBench60.4%33.6%
Mystery game puzzles59.0%6.0%
Professional work
Finance Agent (v2)58.6%41.3%
CorpFin v273.2%69.6%
EMB73.6%31.8%
LegalBench87.0%83.0%
Legal Research Bench55.3%25.5%
MedCode63.6%37.9%
MedScribe91.0%84.1%
MortgageTax72.1%62.3%
Public Benefits Bench v1.176.9%59.4%
Tax Agent Bench47.1%15.4%
TaxEval v275.1%75.5%
Novel problems
ARC-AGI-290.4%40.1%
ARC-AGI-197.5%84.0%

Tests at least two of these models have taken. Bold rows are the core tests.

This page as a chartDownload PNG