Grok 3

xAI · xai/grok-3

ProviderxAI
Familygrok
Typellm-chat
Statusactive
Released2025-02-17
Updated2025-02-17

Reported benchmark scores

These scores carry one collection date for the whole card (2026-04) and a source list rather than a source per score, so they cannot be attributed individually. They are shown as reported and are not verified evidence. Benchmark pages carry the reviewed, dated evidence where it exists.
BenchmarkCatalogue standingScore
Aider Polyglot Benchmarkunassessed53.3
Arena Elo — Codingunassessed1320.0
Arena Elo — Hard Promptsunassessed1426.2
Arena Elo — Mathunassessed1310.0
Arena Elo — Overall (Text)unassessed1330.0
Arena Elo — Style Controlunassessed1411.7
Artificial Analysis Intelligence Indexunassessed82.0
Artificial Analysis Output Speedunassessed65.0
GPQA Diamondunassessed62.8
HumanEvalunassessed86.5
IFEvalunassessed85.0
LiveCodeBenchunassessed79.4
MATH-500unassessed82.5
MedQAunassessed86.1
MMLU-Prounassessed76.0
MultiPL-E: C#unassessed78.5
MultiPL-E: Juliaunassessed60.2
MultiPL-E: Kotlin (unconfirmed)unassessed71.2
MultiPL-E: Luaunassessed53.5
MultiPL-E: Perlunassessed49.2
MultiPL-E: PHPunassessed76.2
MultiPL-E: Runassessed56.8
MultiPL-E: Rubyunassessed64.5
MultiPL-E: Scalaunassessed58.8
MultiPL-E: Swiftunassessed64.5
SWE-bench Verifiedunassessed48.5

Data

This card as JSON · Edit on GitHub