Grok-3 mini
Grok-3 mini is an API-only (closed weights) language model from xAI, released June 24, 2025. On the Epoch Capabilities Index it scores 139.9, rank 126 of 256 rated models.
Check it against your own PC →
Lab
xAI
Released
June 24, 2025
Weights
API-only (closed weights)
Parameters
–
Context
–
Price / M tokens
–
Epoch ECI
139.9 #126
Strengths by category
ModelTape's 0–100 fit on Epoch AI benchmark results.
| Category | Score | Based on |
|---|---|---|
| Math | 36.2 | MATH level 5, OTIS Mock AIME 2024-2025, FrontierMath-2025-02-28-Private |
Benchmark results
| Benchmark (Epoch AI) | Score |
|---|---|
| MATH level 5 | 90.9% |
| OTIS Mock AIME | 77.8% |
| GPQA Diamond | 71.2% |
| Aider Polyglot | 49.3% |
| FrontierMath-2025-02-28-Private | 10.3% |
Links
Models with a similar score
Qwen 3.5 Flash (hosted 35B-A3B) · Qwen 3.6 Flash · GLM-4.7 · Qwen3-235B-A22B-Thinking (Jul 2025) · Claude Opus 4 · Claude Haiku 4.5 · Qwen3-Max · Gemini 2.5 Flash (Sep 2025)
More from xAI
Grok 4.7 · Grok 4.6 · Grok 4.5 · Grok 4.3 Beta · Grok Build 0.1 · Grok 4.20 Multi-Agent · Grok 4.20 · Grok 4.1 Fast