The Model Index
Up to four models

Gemini 4 Argon vs Claude Sonnet 5.5

On the index (GPT-4 = 100), Gemini 4 Argon scores 191 and Claude Sonnet 5.5 187. 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 Gemini 4 Argon
Presets
Gemini 4 Argon
191176–207
WeightsClosed
ReleasedSep 2026
Price in / out$2.0 / $10
Context1.05M
Core tests taken6 of 9
Claude Sonnet 5.5
187171–203
WeightsClosed
ReleasedSep 2026
Price in / out$2.0 / $10
Context1M
Core tests taken7 of 9

Gemini 4 Argon and Claude Sonnet 5.5 are too close to call (5 points apart, within the uncertainty), ahead on 4 of 6 shared core tests, at a similar price.

Test by testthird-party results

Gemini 4 ArgonClaude Sonnet 5.5
0%25%50%75%100%REASONING & KNOWLEDGEGPQA Diamond (Epoch AI)GPQA Diamond (Epoch AI)SimpleBenchSimpleBenchSimpleQA VerifiedSimpleQA VerifiedMATHSFrontierMath (tiers 1-3)FrontierMath (tiers 1-3)AIME-style maths (OTIS mock)AIME-style maths (OTIS mock)ProofBench v1.1ProofBench v1.1Chess puzzlesChess puzzlesFrontierMath (tier 4)FrontierMath (tier 4)CODINGTerminal-Bench 4.0Terminal-Bench 4.0Code 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)EMBEMBHLAB-Vals-1.1HLAB-Vals-1.1Legal Research BenchLegal Research BenchMedCodeMedCodeMedScribeMedScribePublic Benefits Bench v1.1Public Benefits Bench v1.1SAGESAGETax Agent BenchTax Agent BenchNOVEL PROBLEMSARC-AGI-2ARC-AGI-2ARC-AGI-1ARC-AGI-1ARC-AGI-3ARC-AGI-3MysteryMechanismMysteryMechanism
Every result as a table
TestGemini 4 ArgonClaude Sonnet 5.5
Reasoning & knowledge
GPQA Diamond (Epoch AI)96.4%95.6%
SimpleBench91.7%75.9%
SimpleQA Verified76.0%46.5%
Maths
FrontierMath (tiers 1-3)86.0%88.8%
AIME-style maths (OTIS mock)100.0%100.0%
ProofBench v1.199.0%100.0%
Chess puzzles59.0%59.0%
FrontierMath (tier 4)78.0%80.5%
Coding
Terminal-Bench 4.057.6%64.1%
Code Migration68.2%69.8%
CyberBench v1.177.9%59.6%
IOI100.0%83.1%
ProgramBench2.5%6.5%
Vibe Code Bench v1.191.9%92.4%
FrontierSWE55.0%61.9%
MirrorCode58.9%97.8%
Agents
APEX-Agents82.4%75.5%
BioMysteryBench76.3%81.1%
SRE Bench44.3%30.1%
Terminal-Bench-Science44.3%47.1%
DTBench97.6%97.3%
Furniture assembly72.5%75.0%
LMCA63.7%68.3%
Mystery game puzzles64.0%65.0%
Professional work
Finance Agent (v2)65.4%58.1%
EMB75.2%75.7%
HLAB-Vals-1.127.1%10.4%
Legal Research Bench54.8%48.1%
MedCode58.8%52.9%
MedScribe87.4%91.1%
Public Benefits Bench v1.169.8%67.2%
SAGE89.5%88.0%
Tax Agent Bench49.2%42.0%
Novel problems
ARC-AGI-291.3%83.9%
ARC-AGI-198.5%96.5%
ARC-AGI-349.8%24.3%
MysteryMechanism45.5%49.1%

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

This page as a chartDownload PNG