GROK

Grok 4.3

Grok / xAI

54scores
47benchmarks
$1.25 / $2.5 per 1M tokenscost in/out

Metadata

Grok Closed/API

Aliases: grok-4.3, grok-4.3-20260430, x-ai-grok-4.3, x-ai-grok-4.3-20260430, x-ai/grok-4.3, x-ai/grok-4.3-20260430

Benchmark Results

Benchmark Category Rank Score Sampled
Gert Labs Rankings Agentic 20 0.52 2026-05-11
ITBench-AA Agentic 14 32.7% 2026-05-28
LMArena Search Arena Agentic 10 1204.64 2026-05-06
Tau2-Bench Telecom Agentic 6 97.7% 2026-05-11
Tau2-Bench Telecom Agentic 150 65.8% 2026-05-11
Terminal-Bench Hard Agentic 48 37.9% 2026-05-11
Terminal-Bench Hard Agentic 150 18.9% 2026-05-11
Vending-Bench 2 Agentic 36 35.26 2026-05-28
OpenUGI Alignment 15 59.41 2026-05-06
scBench Biology 12 44.27% 2026-05-27
ALE-Bench Coding 30 944.17 2026-05-06
Arena AI Code Coding 30 1403 2026-05-06
BLXBench Coding 1 85.50 2026-05-06
IOI Coding 21 15.334% 2026-05-26
LiveCodeBench Coding 22 84.494% 2026-05-28
SciCode Coding 26 47.3% 2026-05-11
SciCode Coding 146 37.4% 2026-05-11
SWE-bench Verified Coding 26 71.4% 2026-05-28
Terminal-Bench 2.0 Coding 27 43.446% 2026-05-28
Vibe Code Bench v1.1 Coding 27 19.403% 2026-05-28
SAGE Education 54 19.736% 2026-05-28
AA-Omniscience Factuality 4 18.32 2026-05-11
CorpFin v2 Finance 1 68.532% 2026-05-28
Finance Agent v1.1 Finance 18 53.812% 2026-05-04
Finance Agent v2 Finance 15 37.708% 2026-05-28
MortgageTax Finance 64 48.252% 2026-05-28
TaxEval v2 Finance 61 70.81% 2026-05-28
InfiniteBM Heads-Up No-Limit Hold'em Game 8 1326.64 Elo / 6 games 2026-05-28
InfiniteBM Liar's Dice Game 6 1352.55 Elo / 6 games 2026-05-28
MedCode Healthcare 36 38.068% 2026-05-28
MedScribe Healthcare 39 74.399% 2026-05-28
AIIQ Composite IQ Intelligence 8 125 2026-05-12
Artificial Analysis Intelligence Index Intelligence 10 53.2 2026-05-11
Artificial Analysis Intelligence Index Intelligence 140 31.02 2026-05-11
GPQA Diamond Intelligence 8 91.414% 2026-05-28
Humanity's Last Exam Intelligence 14 35% 2026-05-11
Humanity's Last Exam Intelligence 226 6.5% 2026-05-11
LiveBench Intelligence 41 67.37 2026-05-05
MMLU Pro Intelligence 31 85.838% 2026-05-28
MMMU Pro Intelligence 18 83.064% 2026-05-28
Vals Index Intelligence 14 46.635% 2026-05-28
Vals Multimodal Index Intelligence 12 43.435% 2026-05-28
CaseLaw v2 Legal 1 79.314% 2026-05-04
LegalBench Legal 14 84.458% 2026-05-28
ProofBench Math 23 11% 2026-05-28
Blueprint-Bench 2 Multimodal 14 0.477 +/- 0.024 2026-05-28
Design Arena Multimodal 19 1289 2026-05-06
CAIS Text Capabilities Index Reasoning 19 24.7 2026-05-27
GPQA Diamond Reasoning 14 90.1% 2026-05-11
GPQA Diamond Reasoning 242 65.8% 2026-05-11
CAIS Risk Index Safety 4 38.5 2026-05-27
CritPt Science 22 8% 2026-05-11
CritPt Science 245 0% 2026-05-11
CAIS Vision Capabilities Index Vision 8 55.4 2026-05-27