GROK

Grok 4.20

Grok / xAI

90scores
63benchmarks
$1.25 / $2.5 per 1M tokenscost in/out

Metadata

Grok Closed/API

Aliases: grok-4.20, grok-4.20-20260309, x-ai-grok-4.20, x-ai-grok-4.20-20260309, x-ai/grok-4.20, x-ai/grok-4.20-20260309

Benchmark Results

Benchmark Category Rank Score Sampled
APEX-Agents-AA Agentic 12 14.2% 2026-05-11
ARC-AGI-1 Agentic 23 89.50 2026-05-05
ARC-AGI-2 Agentic 20 65.14 2026-05-05
ARC-AGI-3 Agentic 6 0.09 2026-05-05
AutoBench Agentic 11 3 2026-05-06
Gert Labs Rankings Agentic 39 0.44 2026-05-11
HiL-Bench Agentic 8 8% 2026-05-05
LMArena Search Arena Agentic 11 1202.96 2026-05-06
PinchBench Agentic 32 0.83 2026-05-06
Tau2-Bench Telecom Agentic 10 96.5% 2026-05-11
Tau2-Bench Telecom Agentic 40 93% 2026-05-11
Tau2-Bench Telecom Agentic 137 69.6% 2026-05-11
Tau2-Bench Telecom Agentic 162 59.9% 2026-05-11
Terminal-Bench Hard Agentic 36 40.9% 2026-05-11
Terminal-Bench Hard Agentic 47 37.9% 2026-05-11
Terminal-Bench Hard Agentic 137 22% 2026-05-11
Terminal-Bench Hard Agentic 169 16.7% 2026-05-11
TERMS-Bench Agentic 9 60.1% SE+ 2026-05-28
Vending-Bench 2 Agentic 14 4662.85 2026-05-28
WildClawBench Agentic 14 19.30 2026-05-06
OpenUGI Alignment 9 64.23 2026-05-06
OpenUGI Alignment 56 53.16 2026-05-06
OpenUGI Alignment 76 51.77 2026-05-06
OpenUGI Alignment 818 30.25 2026-05-06
scBench Biology 11 44.44% 2026-05-27
SpatialBench Biology 9 45.91% 2026-05-27
ALE-Bench Coding 20 1150.28 2026-05-06
Arena AI Code Coding 32 1399 2026-05-06
BLXBench Coding 6 79.10 2026-05-06
IOI Coding 9 30.166% 2026-05-26
LiveCodeBench Coding 23 84.265% 2026-05-28
SciCode Coding 40 45.6% 2026-05-11
SciCode Coding 44 44.7% 2026-05-11
SciCode Coding 226 32.8% 2026-05-11
SciCode Coding 229 32.2% 2026-05-11
SWE-bench Verified Coding 25 72.2% 2026-05-28
Terminal-Bench 2.0 Coding 31 40.449% 2026-05-28
Terminal-Bench 2.1 Coding 13 44.195% 2026-05-28
Vibe Code Bench v1.1 Coding 39 4.063% 2026-05-28
Arena AI Document Document AI 18 1426 2026-05-06
SAGE Education 33 38.242% 2026-05-28
CorpFin v2 Finance 26 63.675% 2026-05-28
Finance Agent v1.1 Finance 24 52.295% 2026-05-04
Finance Agent v2 Finance 19 28.492% 2026-05-28
MortgageTax Finance 65 45.35% 2026-05-28
TaxEval v2 Finance 24 74.121% 2026-05-28
BenchLM General Knowledge 38 65 2026-05-06
LMArena Text Arena Generalization 17 1455.12 2026-05-06
LMArena Text Arena Generalization 24 1448.62 2026-05-06
MedCode Healthcare 50 32.156% 2026-05-28
MedQA Healthcare 16 94.55% 2026-04-16
MedScribe Healthcare 57 63.412% 2026-05-28
PhysicianBench Healthcare 12 5.3 +/- 3.2 2026-05-27
HUMAINE Human Preference 17 3.60 2026-05-06
AIIQ Composite IQ Intelligence 9 123 2026-05-12
Artificial Analysis Intelligence Index Intelligence 25 49.33 2026-05-11
Artificial Analysis Intelligence Index Intelligence 30 48.48 2026-05-11
Artificial Analysis Intelligence Index Intelligence 151 29.69 2026-05-11
Artificial Analysis Intelligence Index Intelligence 156 28.99 2026-05-11
GPQA Diamond Intelligence 15 88.636% 2026-05-28
Humanity's Last Exam Intelligence 20 32.2% 2026-05-11
Humanity's Last Exam Intelligence 25 30% 2026-05-11
Humanity's Last Exam Intelligence 51 24.2% 2026-05-11
Humanity's Last Exam Intelligence 58 22.5% 2026-05-11
LiveBench Intelligence 34 68.99 2026-05-05
MMLU Pro Intelligence 25 86.254% 2026-05-28
MMMU Pro Intelligence 16 83.468% 2026-05-28
Vals Index Intelligence 18 39.11% 2026-05-28
Vals Multimodal Index Intelligence 15 38.704% 2026-05-28
CaseLaw v2 Legal 38 54.448% 2026-05-04
LegalBench Legal 74 77.738% 2026-05-28
AIME Math 6 96.458% 2026-04-16
ProofBench Math 21 14% 2026-05-28
Blueprint-Bench 2 Multimodal 13 0.170 +/- 0.011 2026-05-28
Design Arena Multimodal 26 1271 2026-05-06
Design Arena Multimodal 30 1248 2026-05-06
LMArena Vision Arena Multimodal 21 1255.16 2026-05-06
CAIS Text Capabilities Index Reasoning 12 32.5 2026-05-27
Context Arena Reasoning 49 28.75 2026-05-06
Context Arena Reasoning 68 14.49 2026-05-06
GPQA Diamond Reasoning 8 91.1% 2026-05-11
GPQA Diamond Reasoning 24 88.5% 2026-05-11
GPQA Diamond Reasoning 116 78.5% 2026-05-11
GPQA Diamond Reasoning 127 77.6% 2026-05-11
CAIS Risk Index Safety 6 38.8 2026-05-27
CritPt Science 28 6.6% 2026-05-11
CritPt Science 29 6% 2026-05-11
CritPt Science 133 0.3% 2026-05-11
CritPt Science 244 0% 2026-05-11
CAIS Vision Capabilities Index Vision 10 54.6 2026-05-27