# Grok-3 mini vs Trinity Large Thinking

> Grok-3 mini is the stronger model overall, scoring 41.2 to 38.6 on the Noometry Index.

- Canonical page: https://noometry.com/compare/grok-3-mini-vs-trinity-large-thinking
- Last updated: 2026-10-11
- Shared benchmarks: 17

## Summary

- They share 17 benchmarks with published results for both. Grok-3 mini scores higher in 5 categories and Trinity Large Thinking in 3 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in instruction following, where Grok-3 mini leads 78.5 to 70.5.
- Trinity Large Thinking has downloadable open weights; the other is API-only.

## Snapshot

| | Grok-3 mini | Trinity Large Thinking |
|---|---|---|
| Provider | xAI | Arcee AI |
| Noometry Index | 41.2 | 38.6 |
| Rank | 141 | 185 |
| Context | — | 262K |
| Input $/M | — | $0.25 |
| Output $/M | — | $0.80 |
| Weights | Proprietary | Open |

## Coding

- Grok-3 mini: 40.8 (#131)
- Trinity Large Thinking: 34.1 (#244)

| Benchmark | Grok-3 mini | Trinity Large Thinking |
|---|---|---|
| LMArena Coding | 1379 | 1381 |
| Aider Polyglot | 49.3% | — |
| LMArena WebDev | — | 1238 |
| SciCode | — | 36.1% |
| WeirdML | 42.6% | — |

## Reasoning

- Grok-3 mini: 13.6 (#334)
- Trinity Large Thinking: 16.9 (#298)

| Benchmark | Grok-3 mini | Trinity Large Thinking |
|---|---|---|
| LMArena Hard Prompts | 1375 | 1350 |
| ARC-AGI-2 | 0.4% | — |
| Kagi LLM Benchmark | 61.3% | — |
| NYT Connections (extended) | — | 16.5% |
| ARC-AGI-1 | 16.5% | — |
| CritPt | — | 0.9% |
| Thematic Generalization | — | 41.6% |
| Surface Evolver Bench | — | 15.6% |
| Epoch Capabilities Index | 140.35 | — |

## Math

- Grok-3 mini: 42.1 (#85)
- Trinity Large Thinking: 37.6 (#149)

| Benchmark | Grok-3 mini | Trinity Large Thinking |
|---|---|---|
| LMArena Math | 1386 | 1366 |
| 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: 46.4 (#81)
- Trinity Large Thinking: 40.9 (#113)

| Benchmark | Grok-3 mini | Trinity Large Thinking |
|---|---|---|
| LMArena Expert | 1395 | 1360 |
| GPQA Diamond | 76.3% | — |
| MMLU-Pro | 79.9% | — |
| Confabulations | 10.8% | — |
| Vectara Hallucination Rate | — | 6.9% |
| GPQA (HELM) | 67.5% | — |

## Multilingual

- Grok-3 mini: 48.1 (#145)
- Trinity Large Thinking: 46.2 (#160)

| Benchmark | Grok-3 mini | Trinity Large Thinking |
|---|---|---|
| LMArena Non-English | 1352 | 1325 |
| LMArena Chinese | 1387 | 1373 |
| LMArena French | 1357 | 1374 |
| LMArena German | 1349 | 1356 |
| LMArena Japanese | 1342 | 1311 |
| LMArena Korean | 1335 | 1306 |
| LMArena Russian | 1353 | 1337 |
| LMArena Spanish | 1381 | 1357 |

## Instruction Following

- Grok-3 mini: 78.5 (#9)
- Trinity Large Thinking: 70.5 (#162)

| Benchmark | Grok-3 mini | Trinity Large Thinking |
|---|---|---|
| LMArena Instruction Following | 1357 | 1334 |
| IFEval | 95.1% | — |

## Long Context

- Grok-3 mini: 41.0 (#147)
- Trinity Large Thinking: 41.3 (#144)

| Benchmark | Grok-3 mini | Trinity Large Thinking |
|---|---|---|
| LMArena Longer Query | 1372 | 1355 |
| Fiction.LiveBench | 66.7% | — |

## Writing & Preference

- Grok-3 mini: 52.5 (#169)
- Trinity Large Thinking: 53.8 (#158)

| Benchmark | Grok-3 mini | Trinity Large Thinking |
|---|---|---|
| LMArena Text | 1370 | 1340 |
| LMArena Creative Writing | 1342 | 1320 |
| LMArena Multi-Turn | 1355 | 1342 |
| Short-Story Creative Writing | 73.5% | — |
| WildBench | 65.1% | — |

## FAQ

### Is Grok-3 mini better than Trinity Large Thinking?

Grok-3 mini is the stronger model overall, scoring 41.2 to 38.6 on the Noometry Index.

### Is Grok-3 mini or Trinity Large Thinking better for coding?

Grok-3 mini scores higher on coding benchmarks: 40.8 versus 34.1 in the Noometry coding category.

### How many benchmarks do Grok-3 mini and Trinity Large Thinking share?

17 benchmarks have published results for both models. Grok-3 mini has 35 scored results on Noometry and Trinity Large Thinking has 24.