Grok-3 mini
| Released | 2025-04-09 |
|---|---|
| Price per 1M | Not listed |
| Overall score | 43.9 · rank 166 |
| Provider | xAI |
| Weights | Proprietary |
Scores
| Dimension | Score | Rank | Benchmarks |
|---|---|---|---|
| Overall: Balanced | 43.9 | 166 | 9 |
| Overall: Coding | 42.5 | 174 | 5 |
| Overall: Reasoning | 46.1 | 150 | 7 |
| Overall: Agentic work | 43.2 | 170 | 5 |
| Overall: Frontend | 42.1 | 165 | 1 |
| Coding | 42.1 | 170 | 1 |
| Reasoning | 45.1 | 152 | 4 |
| Math | 47.3 | 135 | 3 |
| General | 43.3 | 146 | 1 |
Configurations
| Configuration | Balanced | Benchmarks |
|---|---|---|
| Unspecified setting | 46.5 ±6.8 | 2 |
| High | 44.7 ±3.0 | 6 |
| Low | 41.6 ±3.4 | 7 |
Evidence
Coding 42.1 ±1.5
| Benchmark | Result | Source | Date |
|---|---|---|---|
| Aider Polyglot | 49.3% | Epoch AI | 2026-11-11 |
Reasoning 45.1 ±2.2
| Benchmark | Result | Source | Date |
|---|---|---|---|
| GPQA Diamond | 76.3% | Epoch AI | 2025-04-10 |
| ARC-AGI-2 | 0.4% | Epoch AI | 2026-11-11 |
| ARC-AGI-1 (ARC Prize verified) | 16.5% | ARC Prize | 2026-11-11 |
| ARC-AGI-2 (ARC Prize verified) | 0.4% | ARC Prize | 2026-11-11 |
| ARC-AGI-1 | 16.5% | Epoch AI | 2026-11-11 |
| Kagi Reasoning Benchmark | 61.3% | Kagi | 2026-11-11 |
Math 47.3 ±2.2
| Benchmark | Result | Source | Date |
|---|---|---|---|
| FrontierMath Tiers 1-3 (2025 set) | 5.9% | Epoch AI | 2025-04-10 |
| MATH Level 5 | 90.9% | Epoch AI | 2025-04-10 |
| OTIS Mock AIME 2024-2025 | 77.8% | Epoch AI | 2025-04-10 |
General 43.3 ±4.1
| Benchmark | Result | Source | Date |
|---|---|---|---|
| LMArena Text | 1,364 | LMArena | 2026-11-09 |
Results not used in the score
| Benchmark | Result | Source | Why not used |
|---|---|---|---|
| Aider Polyglot | 34.7% | Epoch AI | A stronger configuration result was used |
| FrontierMath Tiers 1-3 (2025 set) | 2.8% | Epoch AI | A stronger configuration result was used |
| GPQA Diamond | 75.5% | Epoch AI | A stronger configuration result was used |
| LMArena Text | 1,358 | LMArena | A stronger configuration result was used |
| MATH Level 5 | 88.1% | Epoch AI | A stronger configuration result was used |
| OTIS Mock AIME 2024-2025 | 62.2% | Epoch AI | A stronger configuration result was used |
Names matched to this model
grok-3-mini, grok-3-mini-beta