# Grok 3 Thinking: AI model fact sheet

- **Provider:** xai
- **Released:** 2025-02-19
- **Context window:** 128,000 tokens
- **Parameters:** 2.7T
- **Capabilities:** conversation, reasoning, code-generation, analysis

Grok 3 Thinking exposes the full chain-of-thought process during problem-solving, including error backtracking and alternative solution exploration. Scores 84.6% on GPQA Diamond benchmark for expert-level Q&A.

## Benchmarks

| Benchmark | Score |
| --- | --- |
| MMLU | 86.2% |
| GPQA Diamond | 84.6% |
| MATH | 80.5% |
| LiveCodeBench | 79.4% |

Source: real side-by-side outputs, pricing and specs at https://rival.tips/models/grok-3-thinking