# xAI Grok 3

xAI Grok 3 was last priced at $3.00 per million input tokens and $15.00 per million output tokens, as of October 22, 2026. None of the 6 coding benchmarks behind the index has measured it, so it has no coding index, but 41 benchmarks outside the index have a result below.

Page: https://llmbenchmark.ai/models/grok-3
Data from October 22, 2026. Every figure below names the board it was read from and the day.

- Maker: xAI
- Released: February 19, 2025
- Price per million input tokens: $3.00
- Price per million output tokens: $15.00
- Context window: 131K tokens
- Status: retired. No longer sold through the API. Retired on May 15, 2026; last list price shown.

Benchmark results (41 of 195):

- Aider polyglot: 53.3% (source: Aider polyglot leaderboard, read October 22, 2026)
- GPQA Diamond: 74.2% (source: GPQA (Vals AI), read October 22, 2026)
- AIME: 58.8% (source: AIME (Vals AI), read October 22, 2026)
- MMLU Pro: 80.0% (source: MMLU Pro (Vals AI), read October 22, 2026)
- Design Arena: websites: 1059 Elo (source: Design Arena, read October 22, 2026)
- Design Arena: UI components: 1034 Elo (source: Design Arena, read October 22, 2026)
- Design Arena: game dev: 1025 Elo (source: Design Arena, read October 22, 2026)
- Design Arena: data viz: 1030 Elo (source: Design Arena, read October 22, 2026)
- Design Arena: 3D: 1049 Elo (source: Design Arena, read October 22, 2026)
- Design Arena: all code categories: 1052 Elo (source: Design Arena, read October 22, 2026)
- Design Arena: SVG: 982 Elo (source: Design Arena, read October 22, 2026)
- LiveCodeBench (Vals AI): 52.9% (source: Vals AI boards, read October 22, 2026)
- MATH 500 (Vals AI): 89.8% (source: Vals AI boards, read October 22, 2026)
- MGSM (Vals AI): 91.3% (source: Vals AI boards, read October 22, 2026)
- LegalBench (Vals AI): 82.6% (source: Vals AI boards, read October 22, 2026)
- CorpFin (Vals AI): 59.7% (source: Vals AI boards, read October 22, 2026)
- TaxEval (Vals AI): 75.9% (source: Vals AI boards, read October 22, 2026)
- MedQA (Vals AI): 83.8% (source: Vals AI boards, read October 22, 2026)
- AA Math Index: 58.0 (source: Artificial Analysis, read October 22, 2026)
- GPQA Diamond (Artificial Analysis run): 69.3% (source: Artificial Analysis, read October 22, 2026)
- Humanity's Last Exam (Artificial Analysis run): 4.1% (source: Artificial Analysis, read October 22, 2026)
- MMLU Pro (Artificial Analysis run): 79.9% (source: Artificial Analysis, read October 22, 2026)
- LiveCodeBench (Artificial Analysis run): 42.5% (source: Artificial Analysis, read October 22, 2026)
- Terminal-Bench Hard (Artificial Analysis run): 11.4% (source: Artificial Analysis, read October 22, 2026)
- IFBench: 46.9% (source: Artificial Analysis, read October 22, 2026)
- Long context reasoning (AA-LCR): 58.0% (source: Artificial Analysis, read October 22, 2026)
- τ²-Bench Telecom: 48.8% (source: Artificial Analysis, read October 22, 2026)
- AIME 2025 (Artificial Analysis run): 58.0% (source: Artificial Analysis, read October 22, 2026)
- WeirdML: 37.2% (source: Epoch AI benchmarking hub, read October 22, 2026)
- BALROG: 29.5% (source: Epoch AI benchmarking hub, read October 22, 2026)
- GPQA Diamond (Epoch AI run): 75.8% (source: Epoch AI benchmarking hub, read October 22, 2026)
- ARC-AGI: 5.5% (source: Epoch AI benchmarking hub, read October 22, 2026)
- ARC-AGI-2: 0.0% (source: Epoch AI benchmarking hub, read October 22, 2026)
- SimpleBench: 36.1% (source: Epoch AI benchmarking hub, read October 22, 2026)
- OTIS Mock AIME: 55.6% (source: Epoch AI benchmarking hub, read October 22, 2026)
- MATH level 5: 88.7% (source: Epoch AI benchmarking hub, read October 22, 2026)
- Fiction.LiveBench: 58.3% (source: Epoch AI benchmarking hub, read October 22, 2026)
- Creative writing (Lech Mazur): 76.4% (source: Epoch AI benchmarking hub, read October 22, 2026)
- Epoch Capabilities Index: 138.2 (source: Epoch AI benchmarking hub, read October 22, 2026)
- Kagi LLM Benchmark: 61.3% (source: Kagi LLM Benchmarking Project, read October 22, 2026)
- SciCode: 1.5% (source: Kaggle Benchmarks, read October 22, 2026)
