The Model Index
Up to four models

GPT-5.4 Mini vs Grok 4.3 Beta

On the index (GPT-4 = 100), GPT-5.4 Mini scores 147 and Grok 4.3 Beta 146. 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 GPT-5.4 Mini
Presets
GPT-5.4 Mini
147131–163
WeightsClosed
ReleasedMar 2026
Price in / out$0.75 / $4.5
Context400K
Core tests taken5 of 9
Grok 4.3 Beta
146129–163
WeightsClosed
ReleasedApr 2026
Price in / out–
Context–
Core tests taken2 of 9

GPT-5.4 Mini and Grok 4.3 Beta are too close to call (1 point apart, within the uncertainty), ahead on 1 of 2 shared core tests.

Test by testthird-party results

GPT-5.4 MiniGrok 4.3 Beta
0%25%50%75%100%REASONING & KNOWLEDGEGPQA Diamond (Epoch AI)GPQA Diamond (Epoch AI)SimpleQA 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
TestGPT-5.4 MiniGrok 4.3 Beta
Reasoning & knowledge
GPQA Diamond (Epoch AI)86.9%88.8%
SimpleQA Verified29.4%33.2%
Maths
FrontierMath (tiers 1-3)51.2%42.8%
AIME-style maths (OTIS mock)88.9%93.3%
Chess puzzles23.0%18.0%
FrontierMath (tier 4)9.8%14.6%
Coding
WeirdML60.3%49.9%
Agents
DTBench80.0%90.7%
LMCA40.8%38.3%

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

This page as a chartDownload PNG