The Model Index
Up to four models

Grok 4.3 Beta vs Claude Sonnet 4.5

On the index (GPT-4 = 100), Grok 4.3 Beta scores 146 and Claude Sonnet 4.5 144. 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 4.3 Beta
Presets
Grok 4.3 Beta
146129–163
WeightsClosed
ReleasedApr 2026
Price in / out–
Context–
Core tests taken2 of 9
Claude Sonnet 4.5
144129–160
WeightsClosed
ReleasedSep 2025
Price in / out$3.0 / $15
Context1M
Core tests taken6 of 9

Grok 4.3 Beta and Claude Sonnet 4.5 are too close to call (2 points apart, within the uncertainty), ahead on 2 of 2 shared core tests.

Test by testthird-party results

Grok 4.3 BetaClaude Sonnet 4.5
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)Chess puzzlesChess puzzlesFrontierMath (tier 4)FrontierMath (tier 4)CODINGWeirdMLWeirdMLAGENTSDTBenchDTBenchLMCALMCA
Every result as a table
TestGrok 4.3 BetaClaude Sonnet 4.5
Reasoning & knowledge
GPQA Diamond (Epoch AI)88.8%82.3%
GeoBench56.0%60.0%
SimpleQA Verified33.2%30.7%
Maths
FrontierMath (tiers 1-3)42.8%23.9%
AIME-style maths (OTIS mock)93.3%77.8%
Chess puzzles18.0%10.0%
FrontierMath (tier 4)14.6%2.4%
Coding
WeirdML49.9%47.7%
Agents
DTBench90.7%83.2%
LMCA38.3%38.8%
Task length · METR40 sec

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

This page as a chartDownload PNG