Benchmark Almanac

Grok 4.3

Grok 4.3 ranks first on CaseLaw v2.

xAI Released April 30th, 2026 Family Grok 4 The lab's model card Compare with others
119
Benchmarks with a score
1
Ranked first, out of five or more models
1
In the top three
xAI Apr 2026

Grok 4.3

Closed weights Flagship

No Epoch Capabilities Index score yet
  • Agents' Last Exam 7.24% #29 /31
  • ZeroBench 13% #31 /76
  • SkillsBench 41.7% #17 /22

Where it ranks

Its best score on each benchmark, and where that ranks among every model with a score there. We rank each model once, at its best setting.

Knowledge and language

BenchmarkScoreRankSource
BullshitBench 61.8% #17 of 107 Official leaderboard
LMArena (Elo) 1,442 #75 of 335 Official leaderboard
Wer wird Millionär? LLM Benchmark 76200.0 #22 of 77 Official leaderboard
BullshitBench V2 50% #50 of 129 Official leaderboard
Phare 68.6% #26 of 62 Official leaderboard
Judgemark v4 49.6 #26 of 40 Official leaderboard
Extended NYT Connections 55.2% #68 of 103 Official leaderboard
DesignArena ASCII Art 1,121 #60 of 77 Official leaderboard
Antidote 950 #30 of 36 Official leaderboard
StudyArena Text 1,187 #72 of 85 Official leaderboard
EQ-Bench 4 1,065 #29 of 32 Official leaderboard
OpenAI MRCR v2 6.64% #45 of 47 Official leaderboard
Lech Mazur Creative Writing -4.30 #49 of 50 Official leaderboard

Math and science

BenchmarkScoreRankSource
DTBench 90.7% #47 of 180 Official leaderboard
ForecastBench 0.13 #24 of 82 Official leaderboard
FrontierMath Tiers 1-3 v2 42.8% #58 of 86 Official leaderboard
ProofBench 11% #42 of 59 Official leaderboard
FrontierMath Tier 4 v2 14.6% #53 of 68 Official leaderboard
Leipzig Benchmark 6.00% #18 of 19 Official leaderboard
ResearchClawBench 12.4 #23 of 23 Official leaderboard

Coding

BenchmarkScoreRankSource
WeirdML 49.9% #47 of 112 Official leaderboard
IOI (Vals) 15.3% #28 of 55 Official leaderboard
DesignArena Website 1,187 #81 of 151 Official leaderboard
DesignArena Code 1,176 #79 of 143 Official leaderboard
DesignArena UI Component 1,186 #77 of 139 Official leaderboard
DesignArena Game Dev 1,161 #81 of 143 Official leaderboard
DesignArena Data Visualization 1,177 #74 of 118 Official leaderboard
ALE-Bench 1,211 #82 of 126 Official leaderboard
DesignArena 3D Design 1,107 #91 of 136 Official leaderboard
DesignArena Agentic Image to HTML 1,177 #8 of 11 Official leaderboard
Vibe Code Bench 19.4% #90 of 120 Official leaderboard
DesignArena SVG 1,072 #78 of 103 Official leaderboard
DesignArena Frontend Web App 1,108 #41 of 53 Official leaderboard
DesignArena Image to Frontend 1,128 #24 of 31 Official leaderboard
Code Arena 1,357 #100 of 128 Official leaderboard
DesignArena Agentic Overall 1,035 #63 of 74 Official leaderboard
Code Migration 6.79% #68 of 78 Official leaderboard
Image-to-WebDev Arena 1,376 #52 of 55 Official leaderboard
DesignArena Full Stack 986 #47 of 49 Official leaderboard
DesignArena React Native 1,052 #54 of 56 Official leaderboard
DesignArena Image to HTML 1,071 #50 of 51 Official leaderboard
DesignArena Android (Kotlin) 955 #46 of 46 Official leaderboard
DesignArena Agentic Game Dev 956 #27 of 27 Official leaderboard
DesignArena Godot Game Dev 919 #24 of 24 Official leaderboard

Agents and tools

BenchmarkScoreRankSource
LLM Chess 179 #57 of 123 Official leaderboard
PinchBench 2.0 73.7% #28 of 57 Official leaderboard
Pencil Puzzle Bench 3.30% #29 of 53 Official leaderboard
LMArena Search Arena 1,194 #22 of 37 Official leaderboard
Clocktower Radio 1,530 #14 of 23 Official leaderboard
Game Arena Coin Game 283 #27 of 39 Official leaderboard
PACT 1,504 #18 of 26 Official leaderboard
Game Arena Five in a Row 367 #15 of 20 Official leaderboard
Game Arena Chess 595 #32 of 42 Official leaderboard
SkillsBench 41.7% #17 of 22 Official leaderboard
Game Arena Word Association 108 #31 of 40 Official leaderboard
Game Arena Poker -16.53 #25 of 31 Official leaderboard
RuneBench 3.66 #63 of 76 Official leaderboard
Game Arena Four in a Row 195 #36 of 43 Official leaderboard
Game Arena Lines of Action 184 #35 of 39 Official leaderboard
Game Arena Ultimate Tic-Tac-Toe 29 #35 of 39 Official leaderboard
Game Arena Dots and Boxes 559 #36 of 40 Official leaderboard
Game Arena Bargaining 125 #36 of 39 Official leaderboard
Game Arena Dark Hex 67 #38 of 41 Official leaderboard
Kaggle Game Arena 153 #39 of 42 Official leaderboard
Game Arena Go 130 #37 of 39 Official leaderboard
Game Arena Nine Men's Morris 11 #38 of 39 Official leaderboard
Game Arena Reversi 14 #38 of 39 Official leaderboard
Game Arena Word Art 2 #38 of 39 Official leaderboard
Game Arena Checkers 0 #41 of 41 Official leaderboard
Game Arena Clobber 0 #39 of 39 Official leaderboard

Professional work

BenchmarkScoreRankSource
CaseLaw v2 79.3% #1 of 53 Official leaderboard
CorpFin v2 68.5% #8 of 119 Official leaderboard
LegalBench 84.5% #32 of 138 Official leaderboard
Vals Finance Agent 53.8% #18 of 49 Official leaderboard
FoodTruck Bench $27,880 #24 of 59 Official leaderboard
Vals Index v1 52.5% #19 of 34 Official leaderboard
TaxEval v2 70.8% #81 of 129 Official leaderboard
PolicyBench 80.3% #34 of 50 Official leaderboard
MedCode 38.1% #68 of 96 Official leaderboard
ProfBench 43.3% #53 of 72 Official leaderboard
MedScribe 74.4% #75 of 97 Official leaderboard
Harvey LAB (Legal Agent Benchmark) 0.42% #62 of 80 Official leaderboard
Legal Research Bench 15.4% #75 of 93 Official leaderboard
Vals Finance Agent v2 37.7% #66 of 80 Official leaderboard
MortgageTax 48.3% #77 of 87 Official leaderboard
Vals Index v2 24.3% #58 of 65 Official leaderboard
Public Benefits Bench 51.7% #45 of 50 Official leaderboard
Vending-Bench 2 $35 #62 of 67 Official leaderboard
Tax Agent Bench 6.18% #78 of 84 Official leaderboard
Excel Modeling Benchmark 18.4% #71 of 76 Official leaderboard
Agents' Last Exam 7.24% #29 of 31 Official leaderboard
DesignArena Spreadsheet 964 #34 of 35 Official leaderboard
DesignArena PDF 928 #37 of 37 Official leaderboard
DesignArena Python-PPTX Slides 970 #36 of 36 Official leaderboard
DesignArena HTML Slides 905 #28 of 28 Official leaderboard
CHI-Bench 5.80% #23 of 23 Official leaderboard
Workspace-Bench-Lite 36.9% #9 of 9 Official leaderboard

Vision, audio and robotics

BenchmarkScoreRankSource
Vision Arena 1,242 #54 of 136 Official leaderboard
ZeroBench 13% #31 of 76 Official leaderboard
MineBench 1,147 #59 of 75 Official leaderboard
GeoBench 56% #39 of 48 Official leaderboard
Chartography 12.9% #35 of 43 Official leaderboard
BVB 56.6 #40 of 45 Official leaderboard
Blueprint-Bench 2 0% #38 of 38 Official leaderboard
DesignArena Code to Video 896 #29 of 29 Official leaderboard

Safety and security

BenchmarkScoreRankSource
nocot-bench (NCRI) 69.2 #104 of 185 Official leaderboard
PCT (Polarized Contrastive Pairs) 51.6% #35 of 46 Official leaderboard
Dictatorship Eval 37.9% #16 of 20 Official leaderboard
CyberBench (Vals) 47.5% #22 of 26 Official leaderboard
GeneBench Pro 1.47% #12 of 12 Official leaderboard
LifeSciBench 39.9% #4 of 4 Official leaderboard

Other

BenchmarkScoreRankSource
Conceptual Reasoning Index 52.9 #60 of 151 Official leaderboard
LMCA 38.3% #63 of 147 Official leaderboard
ACCoRD 65.3 #74 of 152 Official leaderboard
CAIS Vision Capabilities Index 48.4 #29 of 53 Official leaderboard
CAIS Risk Index 54.5 #42 of 67 Official leaderboard
CAIS Text Capabilities Index 23.4 #47 of 68 Official leaderboard
Vals Multimodal Index 43.3% #29 of 33 Official leaderboard
SAGE (Vals) 19.7% #81 of 81 Official leaderboard