The Model Index
Up to four models

Claude Sonnet 5.5 vs Claude Opus 5

On the index (GPT-4 = 100), Claude Sonnet 5.5 scores 187 and Claude Opus 5 185. 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 Sonnet 5.5
Presets
Claude Sonnet 5.5
187171–203
WeightsClosed
ReleasedSep 2026
Price in / out$2.0 / $10
Context1M
Core tests taken7 of 9
Claude Opus 5
185169–201
WeightsClosed
ReleasedJul 2026
Price in / out$5.0 / $25
Context1M
Core tests taken6 of 9

Claude Sonnet 5.5 and Claude Opus 5 are too close to call (2 points apart, within the uncertainty), ahead on 4 of 6 shared core tests, and costs 2.5× less.

Test by testthird-party results

Claude Sonnet 5.5Claude Opus 5
0%25%50%75%100%REASONING & KNOWLEDGEGPQA Diamond (Epoch AI)GPQA Diamond (Epoch AI)LiveBench Data AnalysisLiveBench Data AnalysisLiveBench IFLiveBench IFLiveBench LanguageLiveBench LanguageLiveBench ReasoningLiveBench ReasoningSimpleBenchSimpleBenchSimpleQA VerifiedSimpleQA VerifiedMATHSFrontierMath (tiers 1-3)FrontierMath (tiers 1-3)AIME-style maths (OTIS mock)AIME-style maths (OTIS mock)LiveBench MathematicsLiveBench MathematicsProofBench v1.1ProofBench v1.1Chess puzzlesChess puzzlesFrontierMath (tier 4)FrontierMath (tier 4)CODINGTerminal-Bench 4.0Terminal-Bench 4.0LiveBench Agentic CodingLiveBench Agentic CodingLiveBench CodingLiveBench CodingCode MigrationCode MigrationCyberBench v1.1CyberBench v1.1IOIIOIProgramBenchProgramBenchVibe Code Bench v1.1Vibe Code Bench v1.1FrontierSWEFrontierSWEMirrorCodeMirrorCodeAGENTSAPEX-AgentsAPEX-AgentsBioMysteryBenchBioMysteryBenchSRE BenchSRE BenchTerminal-Bench-ScienceTerminal-Bench-ScienceDTBenchDTBenchFurniture assemblyFurniture assemblyLMCALMCAMystery game puzzlesMystery game puzzlesPROFESSIONAL WORKFinance Agent (v2)Finance Agent (v2)EMBEMBLegal Research BenchLegal Research BenchMedCodeMedCodeMedScribeMedScribePublic Benefits Bench v1.1Public Benefits Bench v1.1Tax Agent BenchTax Agent BenchNOVEL PROBLEMSARC-AGI-2ARC-AGI-2ARC-AGI-1ARC-AGI-1ARC-AGI-3ARC-AGI-3MysteryMechanismMysteryMechanism
Every result as a table
TestClaude Sonnet 5.5Claude Opus 5
Reasoning & knowledge
GPQA Diamond (Epoch AI)95.6%93.9%
LiveBench Data Analysis78.6%74.6%
LiveBench IF70.5%63.8%
LiveBench Language83.4%88.7%
LiveBench Reasoning91.6%91.2%
SimpleBench75.9%80.6%
SimpleQA Verified46.5%59.9%
Maths
FrontierMath (tiers 1-3)88.8%85.6%
AIME-style maths (OTIS mock)100.0%98.9%
LiveBench Mathematics96.7%95.7%
ProofBench v1.1100.0%99.0%
Chess puzzles59.0%43.0%
FrontierMath (tier 4)80.5%73.2%
Coding
Terminal-Bench 4.064.1%53.5%
LiveBench Agentic Coding56.3%65.2%
LiveBench Coding91.4%81.5%
Code Migration69.8%57.5%
CyberBench v1.159.6%65.4%
IOI83.1%84.3%
ProgramBench6.5%3.0%
Vibe Code Bench v1.192.4%88.4%
FrontierSWE61.9%52.0%
MirrorCode97.8%87.8%
Agents
APEX-Agents75.5%65.8%
BioMysteryBench81.1%79.3%
SRE Bench30.1%12.2%
Terminal-Bench-Science47.1%27.1%
DTBench97.3%97.9%
Furniture assembly75.0%60.8%
LMCA68.3%64.5%
Mystery game puzzles65.0%59.0%
Professional work
Finance Agent (v2)58.1%58.6%
EMB75.7%73.6%
Legal Research Bench48.1%55.3%
MedCode52.9%63.6%
MedScribe91.1%91.0%
Public Benefits Bench v1.167.2%76.9%
Tax Agent Bench42.0%47.1%
Novel problems
ARC-AGI-283.9%90.4%
ARC-AGI-196.5%97.5%
ARC-AGI-324.3%30.2%
MysteryMechanism49.1%37.4%

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

This page as a chartDownload PNG