Grok-3 vs Grok-3 Mini: Specs & Benchmark Comparison
Grok-3 and Grok-3 Mini both come from xAI, and both were released in February 2025.
The two models share 4 published benchmarks. They split them evenly, 2 to 2. The widest gaps are on AIME 2024, where Grok-3 Mini scores 96.0% against 93.0%; AIME 2025, where Grok-3 scores 93.3% against 91.0%. Averaged across everything we track, Grok-3 sits at 85.7% and Grok-3 Mini at 87.8%.
Grok-3 Mini is the cheaper API at $0.30 per million input tokens and $0.50 per million output tokens, roughly 10 times cheaper than Grok-3 at $3 and $15. Both accept a context window of about 128K tokens. Both accept text and images as input.
| Characteristic | Grok-3 | Grok-3 Mini |
|---|---|---|
| Company | xAI | xAI |
| Release Date | February 16, 2025 | February 16, 2025 |
| Parameters | — | — |
| Multimodal | Yes | Yes |
| Context (input) | 128K | 128K |
| Context (output) | 8K | 8K |
| Input Price / 1M | $3.00 | $0.30 |
| Output Price / 1M | $15.00 | $0.50 |
| Average Score | 85.7% | 87.8% |
| Benchmarks | ||
| AIME 2024 | 93.0% | 96.0% |
| AIME 2025 | 93.3% | 91.0% |
| GPQA | 85.0% | 84.0% |
| LiveCodeBench | 79.0% | 80.0% |
Visual Benchmark Comparison
Verdict
Grok-3 Mini leads in 1 out of 4 comparison categories.
Both models show comparable average scores: Grok-3 — 0.9, Grok-3 Mini — 0.9.
Grok-3 Mini is 22.5x cheaper: input $0.30/1M vs $3.00/1M tokens.
Same context size: 128K tokens.
Both models were released around the same time: 2/16/2025 and 2/16/2025.
More About These Models
Related Comparisons
Frequently Asked Questions
Which is better for coding — Grok-3 or Grok-3 Mini?
Which model is cheaper — Grok-3 or Grok-3 Mini?
Which has a larger context window — Grok-3 or Grok-3 Mini?
The Grok-3 and Grok-3 Mini comparison is updated for 2026. Data includes benchmark results, API pricing, context window size and other specifications. For more detailed information, visit the Grok-3 or Grok-3 Mini page. See also the complete list of AI model comparisons.