The Model Index
Up to four models

Grok 4.5 vs Grok 4.3

On the index (GPT-4 = 100), Grok 4.5 scores 161 and Grok 4.3 135. 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 4.5
Presets
Grok 4.5
161145–177
WeightsClosed
ReleasedJul 2026
Price in / out$2.0 / $6.0
Context500K
Core tests taken6 of 9
Grok 4.3
135115–156
WeightsClosed
ReleasedApr 2026
Price in / out$1.25 / $2.5
Context1M
Core tests taken1 of 9

Grok 4.5 leads Grok 4.3 by 26 points, ahead on 1 of 1 shared core tests, at 1.9× the price.

Test by testthird-party results

Grok 4.5Grok 4.3
0%25%50%75%100%REASONING & KNOWLEDGELiveBench Data AnalysisLiveBench Data AnalysisLiveBench IFLiveBench IFLiveBench LanguageLiveBench LanguageLiveBench ReasoningLiveBench ReasoningGPQA Diamond (Vals AI)GPQA Diamond (Vals AI)MMLU ProMMLU ProMMMU ProMMMU ProMATHSLiveBench MathematicsLiveBench MathematicsCODINGLiveBench Agentic CodingLiveBench Agentic CodingLiveBench CodingLiveBench CodingCode MigrationCode MigrationLiveCodeBenchLiveCodeBenchProgramBenchProgramBenchSWE-benchSWE-benchVibe Code Bench v1.1Vibe Code Bench v1.1AGENTSSkillsBenchSkillsBenchPROFESSIONAL WORKFinance Agent (v2)Finance Agent (v2)CorpFin v2CorpFin v2EMBEMBLegalBenchLegalBenchLegal Research BenchLegal Research BenchMedCodeMedCodeMedScribeMedScribeMortgageTaxMortgageTaxTax Agent BenchTax Agent BenchTaxEval v2TaxEval v2
Every result as a table
TestGrok 4.5Grok 4.3
Reasoning & knowledge
LiveBench Data Analysis73.0%55.8%
LiveBench IF71.5%62.7%
LiveBench Language82.8%73.6%
LiveBench Reasoning87.2%70.8%
GPQA Diamond (Vals AI)92.9%91.4%
MMLU Pro89.2%85.8%
MMMU Pro61.8%83.1%
Maths
LiveBench Mathematics90.8%84.3%
Coding
LiveBench Agentic Coding56.5%18.5%
LiveBench Coding68.6%69.9%
Code Migration36.6%6.8%
LiveCodeBench87.4%84.5%
ProgramBench0.0%0.0%
SWE-bench86.6%71.4%
Vibe Code Bench v1.169.0%19.4%
Agents
SkillsBench66.0%40.6%
Professional work
Finance Agent (v2)48.4%37.7%
CorpFin v267.4%68.5%
EMB52.9%18.4%
LegalBench86.0%84.5%
Legal Research Bench38.0%15.4%
MedCode43.3%38.1%
MedScribe86.9%74.4%
MortgageTax61.8%48.3%
Tax Agent Bench24.9%6.2%
TaxEval v271.7%70.8%

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

This page as a chartDownload PNG