The Model Index
Up to four models

Grok 4.7 vs Claude Sonnet 5

On the index (GPT-4 = 100), Grok 4.7 scores 164 and Claude Sonnet 5 164. 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 Grok 4.7
Presets
Grok 4.7
164149–180
WeightsClosed
ReleasedSep 2026
Price in / out$2.0 / $6.0
Context500K
Core tests taken6 of 9
Claude Sonnet 5
164148–180
WeightsClosed
ReleasedJun 2026
Price in / out$2.0 / $10
Context1M
Core tests taken5 of 9

Grok 4.7 and Claude Sonnet 5 are too close to call (0 points apart, within the uncertainty), ahead on 3 of 5 shared core tests, and costs 1.3× less.

Test by testthird-party results

Grok 4.7Claude Sonnet 5
0%25%50%75%100%REASONING & KNOWLEDGEGPQA Diamond (Epoch AI)GPQA Diamond (Epoch AI)GeoBenchGeoBenchSimpleQA 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 v1.1MirrorCodeMirrorCodeAGENTSAPEX-AgentsAPEX-AgentsSRE BenchSRE BenchTerminal-Bench-ScienceTerminal-Bench-ScienceDTBenchDTBenchLMCALMCAMystery game puzzlesMystery game puzzlesPROFESSIONAL WORKFinance Agent (v2)Finance Agent (v2)EMBEMBLegalBenchLegalBenchLegal Research BenchLegal Research BenchMedCodeMedCodeMedScribeMedScribePublic Benefits Bench v1.1Public Benefits Bench v1.1Tax Agent BenchTax Agent Bench
Every result as a table
TestGrok 4.7Claude Sonnet 5
Reasoning & knowledge
GPQA Diamond (Epoch AI)92.7%90.5%
GeoBench61.0%74.0%
SimpleQA Verified56.0%33.7%
Maths
FrontierMath (tiers 1-3)53.0%65.6%
AIME-style maths (OTIS mock)98.1%94.7%
ProofBench v1.126.0%77.0%
Chess puzzles41.0%45.0%
FrontierMath (tier 4)17.1%29.3%
Coding
Terminal-Bench 4.028.8%10.6%
Code Migration44.8%44.4%
CyberBench v1.169.5%70.3%
IOI57.7%45.0%
ProgramBench0.5%0.0%
Vibe Code Bench v1.186.2%81.3%
MirrorCode54.4%63.3%
Agents
APEX-Agents70.0%54.5%
SRE Bench3.8%0.4%
Terminal-Bench-Science10.0%5.7%
DTBench96.0%92.5%
LMCA49.4%50.0%
Mystery game puzzles29.0%35.0%
Professional work
Finance Agent (v2)52.3%53.9%
EMB67.0%66.3%
LegalBench84.4%83.9%
Legal Research Bench47.1%41.8%
MedCode49.5%47.5%
MedScribe89.4%76.0%
Public Benefits Bench v1.165.6%66.0%
Tax Agent Bench35.8%29.4%

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

This page as a chartDownload PNG