Grok-2

Benchmarks, price, context and versions

Direct answer: Grok-2 is a model from xAI. 53.8% on GPQA Diamond, per Epoch AI.

✓ Good for

Not enough data in the open sources this section uses to build this block.

✕ Not the best for

technical reasoning on science topics (#135 of 198 on GPQA Diamond)
calculation and problems with an exact answer (#145 of 186 on OTIS Mock AIME)

This block follows a rule of this section, using source data: if the model is in the top 25% of the metric, the item goes under "Good for"; if it is in the bottom half, it goes under "Not the best for". The middle band appears in neither. Price and context use OpenRouter; scores use Epoch AI or OpenRouter Benchmarks, in the latest version we checked.

Benchmarks

GPQA Diamond

?what it is

53.8%

highest score on this metric 96.4%

135º / 198 · Epoch AI, latest version we checked

OTIS Mock AIME

11.5%

highest score on this metric 100%

145º / 186 · Epoch AI, latest version we checked

Key specs

Lab: xAI
Origin: the US
Family: Grok provisional data
Weights?: closed
License: no data
Input US$/1M?: no data
Output US$/1M: no data
Context?: no data
Parameters: no data
Input: no data
OpenRouter usage?: no data
Downloads (30 days)?: no data
Use cases provisional data: Text
Dates in sources: 2024, published, per Epoch AI

Version history

2026 SpaceXAI: Grok 4.7 OpenRouter, listed on OpenRouter
2026 SpaceXAI: Grok 4.6 OpenRouter, listed on OpenRouter
2026 SpaceXAI: Grok 4.5 OpenRouter, listed on OpenRouter
2026 SpaceXAI: Grok Build 0.1 OpenRouter, listed on OpenRouter
2026 SpaceXAI: Grok 4.3 OpenRouter, listed on OpenRouter
2026 SpaceXAI: Grok 4.20 OpenRouter, listed on OpenRouter
2026 SpaceXAI: Grok 4.20 Multi-Agent OpenRouter, listed on OpenRouter
2025 grok-2 Hugging Face Hub, Hugging Face repo created
2024 grok-1 Hugging Face Hub, Hugging Face repo created

Dates come from the sources: OpenRouter listing or Hugging Face repo creation, which may differ from the official launch.

FAQ

What is Grok-2?

Grok-2 is a model from xAI, with closed weights, used for text.

How much does Grok-2 cost?

No data in open sources.

What is the context window of Grok-2?

No data in open sources.

Is Grok-2 open source?

No. It is available through API only.

What is Grok-2's GPQA Diamond score?

53.8% on GPQA Diamond, per Epoch AI.

Is Grok-2 good for coding?

No data: there is no SWE-bench Verified measurement for it in open sources.

Who made Grok-2?

It was made by xAI, a lab from the US.

provisional data Questions under review: Semrush had no API balance during collection. Answers use source data only.

Models from xAI

See lab

Sources

Epoch AI, CC BY 4.0, latest version we checked.

Dates come from the sources: OpenRouter listing or Hugging Face repo creation, which may differ from the official launch. Family and version were grouped by rule from the name.