Grok 3 benchmarks, pricing and specs
Grok 3 is a xAI model released on February 19, 2025 that takes text input and produces text. It is now listed as a legacy model. Its price is not published. It scores 1411 Elo on Arena Text (Arena, measured October 8, 2026).
- Arena Text
- 1411 Elo
Data verified October 12, 2026 · Dataset 2026-10-12
Key facts
- Provider
- xAI
- Model family
- Grok 3
- Release date
- February 19, 2025
- Status
- Legacy
- Access
- API only
- API model id
- Not reported
- Context window
- Not reported
- Max output
- Not reported
- Input
- text
- Output
- text
- Task families
- text
- Declared capabilities
- reasoning
Grok 3 pricing
Independent benchmark results
Scores come from independent evaluators that ran the model themselves, pinned to a dated snapshot. Rank is among current models in the same snapshot. xAI's own launch figures are listed under strengths with the publisher named, because they are not measured the same way.
| Benchmark | Score | Rank | Measured | Source |
|---|---|---|---|---|
| Arena Text | 1411 Elo | Not ranked | October 8, 2026 | Arena · 2026-10-12 |
| GPQA Diamond | 75.8% | Not ranked | October 12, 2026 | Epoch AI · 2026-10-12 |
Strengths, cautions and best uses
Strengths
- Grok 3 records API access for text inputs
Cautions
- This record is marked legacy; confirm current availability and migration requirements before adoption
Best for
- Historical text API comparison where limits can be verified separately
Alternatives to Grok 3
The closest current textmodels by price. The cheapest model that scores as well or better is listed first; failing that, the cheapest one within 3% of the benchmark's scale.
DeepSeek-R1
- 13 points lower on Arena Text, 1398 vs 1411
- From DeepSeek
Gemini 2.5 Pro
- 34 points higher on Arena Text, 1445 vs 1411
- From Google
GPT-4.1
- 4 points higher on Arena Text, 1415 vs 1411
- From OpenAI
GPT-4.1 mini
- 28 points lower on Arena Text, 1383 vs 1411
- From OpenAI
Grok 3 FAQ
How does Grok 3 score on independent benchmarks?
Grok 3 scores 1411 Elo on Arena Text (Arena, measured October 8, 2026) and 75.8% on GPQA Diamond (Epoch AI, measured October 12, 2026). These are independent evaluations, not xAI's own launch figures.
Is Grok 3 open source or API only?
Grok 3 is available through xAI's API only; its weights are not published.
What are the best alternatives to Grok 3?
The closest current alternatives by price and measured performance are DeepSeek-R1 (13 points lower on Arena Text, 1398 vs 1411), Gemini 2.5 Pro (34 points higher on Arena Text, 1445 vs 1411), GPT-4.1 (4 points higher on Arena Text, 1415 vs 1411) and GPT-4.1 mini (28 points lower on Arena Text, 1383 vs 1411).
Sources
- Grok 3 Beta · xAI · official · verified August 6, 2026
- xAI models and pricing · xAI · official · verified October 11, 2026
- Grok model retirement on May 15, 2026 · SpaceXAI · official · verified August 7, 2026
- Epoch AI Benchmarking Hub data (benchmark_data.zip) · Epoch AI · independent · verified October 12, 2026 · CC-BY-4.0
- Arena leaderboard dataset (lmarena-ai/leaderboard-dataset) · Arena · independent · verified October 12, 2026 · CC-BY-4.0
Cite this page
Van Data Team. "Grok 3 Benchmarks, Pricing and Specs." AI Model Benchmark Dataset 2026-10-12. https://vandatateam.com/ai-model-benchmarks/grok-3
Reuse the data: JSON · CSV · or explore every model in the AI model benchmark comparison.
Production evaluation
Deciding whether Grok 3 fits your workload?
Public benchmarks narrow the shortlist. We test the finalists on your own tasks, data and cost limits, then build the routing and review controls to run the winner in production.
- Evaluation cases and acceptance thresholds tied to real work
- Model routing, fallbacks and cost controls