Inference
EN
xAI

Grok 2

Grok 2 is a standard model from xAI. 11 benchmarks count toward its index, in 4 categories.

  • Closed weights
  • Standard
  • Input: text
  • Released 2024-08
RankedEnough results for an index.
IndexAll categories, out of 100.29.1±9.4Median 51.0
CoverageIndex weight that has results.55%
SpeedOutput tokens per second.—Median 67/s
First tokenSeconds to the first output token.—Median 1.3 s
Input / 1MUS dollars per 1M input tokens.—Median $0.60
Output / 1MUS dollars per 1M output tokens.—Median $2.55
ContextMaximum tokens in one request.—Median 262K
EloLMArena rating and rank.1305±4 #250Median 1422

Capabilities

Index per category, out of 100.
Out of 100
AgenticMulti-step tasks with tools.None counted——
CodingCode writing and repair.2 counted25.2203 / 209
ReasoningLogic problems and puzzles.None counted——
MultimodalTasks with images and text.1 counted33.5—
KnowledgeFacts and expert knowledge.3 counted34.0230 / 268
MultilingualTasks in many languages.None counted——
InstructionTasks with strict prompt rules.None counted——
MathMath problems.5 counted25.0152 / 168

Results

11 counted
BenchmarkThe benchmark name.ResultThe score from the source.PlacePlace among results on this benchmark.
Massive Multitask Language UnderstandingKnowledge87.5%10 / 34
Evaluating Large Language Models Trained on CodeCoding88.4%8 / 22
MATH level 5Math63.5% ±1.339 / 88
GPQA diamond · Epoch AIKnowledge53.8% ±2.7139 / 217
Massive Multitask Language Understanding ProfessionalKnowledge75.5%50 / 75
MATH 500Math78.4% ±3.642 / 59
Massive Multi-discipline Multimodal UnderstandingMultimodal66.1%20 / 28
OTIS Mock AIME 2024-2025Math11.5% ±3.4153 / 200
MMLU ProKnowledge75.5% ±0.4108 / 135
Graduate-Level Google-Proof Q&AKnowledge56.0%118 / 141
GPQA Diamond · Vals AIKnowledge50.8% ±2.5118 / 135
AIMEMath15.2% ±0.884 / 95
FrontierMath-2025-02-28-PrivateMath0.7% ±0.562 / 69
LiveCodeBenchCoding38.7% ±1.0130 / 142
MedQAHealthcare92.3% ±0.533 / 95
FrontierMath-2025-02-28-PublicMath0.0%33 / 64
TaxEval v2Finance67.0% ±0.9109 / 143
CorpFin v2Finance51.1% ±1.0104 / 131
MGSMMultilingual86.1% ±2.064 / 74

Sources

BenchLMCC BY-NC 4.0Vals AINo licence statedEpoch AICC BY

History

5 releases
Index30.0 → 29.1
23 Oct 202612 Nov 2026

Questions

How good is Grok 2?
Its index is 29.1 out of 100. That is place 253 of 283 ranked models.
What is Grok 2 best at?
Knowledge: 34.0 out of 100, place 230 of 268.
Is Grok 2 open source?
No. Its weights are not published.
When was Grok 2 released?
August 2024.

Badge

Grok 2 on Inference360: place 253 of 283, index 29.1
HTML
<a href="https://inference360.ai/models/grok-2"><img src="https://inference360.ai/badges/grok-2.svg" alt="Grok 2 on Inference360: place 253 of 283, index 29.1" height="20"></a>
Markdown
[![Grok 2 on Inference360: place 253 of 283, index 29.1](https://inference360.ai/badges/grok-2.svg)](https://inference360.ai/models/grok-2)

Compare with

Gemini 2.0 Flash29.5GPT-4o28.7Llama 3.3 70B28.2Grok 3 Mini44.3

More from xAI

All models
Grok 2 miniUnrankedGrok 3 Mini44.3Grok 3 [Beta]39.3Grok 450.0Grok Code Fast 141.2