# Grok-3 mini vs Solar Pro4

> Grok-3 mini and Solar Pro4 score almost the same on the Noometry Index (41.0 vs 41.5), so choose on price, context window or the category you care about most.

- Canonical page: https://noometry.com/compare/grok-3-mini-vs-solar-pro4
- Last updated: 2026-10-10
- Shared benchmarks: 17

## Summary

- They share 17 benchmarks with published results for both. Grok-3 mini scores higher in 4 categories and Solar Pro4 in 4 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Solar Pro4 leads 27.3 to 13.8.

## Snapshot

| | Grok-3 mini | Solar Pro4 |
|---|---|---|
| Provider | xAI | Upstage |
| Noometry Index | 41.0 | 41.5 |
| Rank | 130 | 123 |
| Context | — | 524K |
| Input $/M | — | $0.30 |
| Output $/M | — | $1.20 |
| Weights | Proprietary | Proprietary |

## Coding

- Grok-3 mini: 40.4 (#126)
- Solar Pro4: 39.9 (#135)

| Benchmark | Grok-3 mini | Solar Pro4 |
|---|---|---|
| LMArena Coding | 1380 | 1439 |
| Aider Polyglot | 49.3% | — |
| LMArena WebDev | — | 1371 |
| WeirdML | 42.6% | — |

## Reasoning

- Grok-3 mini: 13.8 (#323)
- Solar Pro4: 27.3 (#107)

| Benchmark | Grok-3 mini | Solar Pro4 |
|---|---|---|
| LMArena Hard Prompts | 1374 | 1398 |
| ARC-AGI-2 | 0.4% | — |
| Kagi LLM Benchmark | 61.3% | — |
| ARC-AGI-1 | 16.5% | — |
| Epoch Capabilities Index | 140.35 | — |

## Math

- Grok-3 mini: 40.3 (#78)
- Solar Pro4: 36.1 (#129)

| Benchmark | Grok-3 mini | Solar Pro4 |
|---|---|---|
| LMArena Math | 1386 | 1418 |
| OTIS Mock AIME 2024-2025 | 77.8% | — |
| Omni-MATH | 31.8% | — |
| MATH Level 5 | 90.9% | — |
| FrontierMath (Feb 2025 set) | 5.9% | — |

## Knowledge

- Grok-3 mini: 46.3 (#75)
- Solar Pro4: 39.0 (#128)

| Benchmark | Grok-3 mini | Solar Pro4 |
|---|---|---|
| LMArena Expert | 1395 | 1421 |
| GPQA Diamond | 76.3% | — |
| MMLU-Pro | 79.9% | — |
| Confabulations | 10.8% | — |
| GPQA (HELM) | 67.5% | — |

## Multilingual

- Grok-3 mini: 48.3 (#141)
- Solar Pro4: 49.0 (#134)

| Benchmark | Grok-3 mini | Solar Pro4 |
|---|---|---|
| LMArena Non-English | 1352 | 1362 |
| LMArena Chinese | 1387 | 1417 |
| LMArena French | 1357 | 1403 |
| LMArena German | 1350 | 1351 |
| LMArena Japanese | 1343 | 1300 |
| LMArena Korean | 1336 | 1383 |
| LMArena Russian | 1352 | 1360 |
| LMArena Spanish | 1379 | 1408 |

## Instruction Following

- Grok-3 mini: 78.7 (#8)
- Solar Pro4: 72.8 (#128)

| Benchmark | Grok-3 mini | Solar Pro4 |
|---|---|---|
| LMArena Instruction Following | 1356 | 1376 |
| IFEval | 95.1% | — |

## Long Context

- Grok-3 mini: 41.0 (#142)
- Solar Pro4: 42.0 (#125)

| Benchmark | Grok-3 mini | Solar Pro4 |
|---|---|---|
| LMArena Longer Query | 1372 | 1379 |
| Fiction.LiveBench | 66.7% | — |

## Writing & Preference

- Grok-3 mini: 52.7 (#163)
- Solar Pro4: 56.7 (#133)

| Benchmark | Grok-3 mini | Solar Pro4 |
|---|---|---|
| LMArena Text | 1370 | 1386 |
| LMArena Creative Writing | 1342 | 1313 |
| LMArena Multi-Turn | 1355 | 1391 |
| Short-Story Creative Writing | 73.5% | — |
| WildBench | 65.1% | — |

## FAQ

### Is Grok-3 mini better than Solar Pro4?

Grok-3 mini and Solar Pro4 score almost the same on the Noometry Index (41.0 vs 41.5), so choose on price, context window or the category you care about most.

### Is Grok-3 mini or Solar Pro4 better for coding?

They score almost the same on coding (40.4 vs 39.9); test both on your own repository before choosing.

### How many benchmarks do Grok-3 mini and Solar Pro4 share?

17 benchmarks have published results for both models. Grok-3 mini has 35 scored results on Noometry and Solar Pro4 has 18.