# Muse Spark vs Trinity Large Thinking

> Muse Spark is the stronger model overall, scoring 50.6 to 38.6 on the Noometry Index.

- Canonical page: https://noometry.com/compare/muse-spark-vs-trinity-large-thinking
- Last updated: 2026-10-12
- Shared benchmarks: 18

## Summary

- They share 18 benchmarks with published results for both. Muse Spark scores higher in 8 categories and Trinity Large Thinking in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Muse Spark leads 65.7 to 40.9.
- The biggest single-benchmark swing is SciCode: 51.5% for Muse Spark and 36.1% for Trinity Large Thinking.
- Trinity Large Thinking has downloadable open weights; the other is API-only.

## Snapshot

| | Muse Spark | Trinity Large Thinking |
|---|---|---|
| Provider | Meta | Arcee AI |
| Noometry Index | 50.6 | 38.6 |
| Rank | 46 | 185 |
| Context | — | 262K |
| Input $/M | — | $0.25 |
| Output $/M | — | $0.80 |
| Weights | Proprietary | Open |

## Coding

- Muse Spark: 46.2 (#69)
- Trinity Large Thinking: 34.1 (#244)

| Benchmark | Muse Spark | Trinity Large Thinking |
|---|---|---|
| SciCode | 51.5% | 36.1% |
| LMArena Coding | 1481 | 1381 |
| LMArena WebDev | — | 1238 |

## Reasoning

- Muse Spark: 35.9 (#67)
- Trinity Large Thinking: 16.9 (#298)

| Benchmark | Muse Spark | Trinity Large Thinking |
|---|---|---|
| CritPt | 11.3% | 0.9% |
| LMArena Hard Prompts | 1474 | 1350 |
| NYT Connections (extended) | — | 16.5% |
| Thematic Generalization | — | 41.6% |
| Surface Evolver Bench | — | 15.6% |
| Epoch Capabilities Index | 152.04 | — |

## Math

- Muse Spark: 47.8 (#66)
- Trinity Large Thinking: 37.6 (#149)

| Benchmark | Muse Spark | Trinity Large Thinking |
|---|---|---|
| LMArena Math | 1455 | 1366 |
| OTIS Mock AIME 2024-2025 | 88.9% | — |
| ProofBench | 17% | — |
| FrontierMath (Feb 2025 set) | 39% | — |
| FrontierMath Tier 4 (v1) | 14.6% | — |

## Knowledge

- Muse Spark: 65.7 (#13)
- Trinity Large Thinking: 40.9 (#113)

| Benchmark | Muse Spark | Trinity Large Thinking |
|---|---|---|
| LMArena Expert | 1457 | 1360 |
| GPQA Diamond | 89.8% | — |
| Humanity's Last Exam | 40.6% | — |
| Vectara Hallucination Rate | — | 6.9% |

## Multimodal

- Muse Spark: 43.4 (#24)
- Trinity Large Thinking: —

| Benchmark | Muse Spark | Trinity Large Thinking |
|---|---|---|
| LMArena Vision | 1306 | — |
| LMArena Document | 1444 | — |

## Multilingual

- Muse Spark: 56.1 (#24)
- Trinity Large Thinking: 46.2 (#160)

| Benchmark | Muse Spark | Trinity Large Thinking |
|---|---|---|
| LMArena Non-English | 1464 | 1325 |
| LMArena Chinese | 1509 | 1373 |
| LMArena French | 1497 | 1374 |
| LMArena German | 1497 | 1356 |
| LMArena Korean | 1459 | 1306 |
| LMArena Russian | 1466 | 1337 |
| LMArena Spanish | 1472 | 1357 |
| LMArena Japanese | — | 1311 |

## Instruction Following

- Muse Spark: 75.9 (#51)
- Trinity Large Thinking: 70.5 (#162)

| Benchmark | Muse Spark | Trinity Large Thinking |
|---|---|---|
| LMArena Instruction Following | 1442 | 1334 |

## Long Context

- Muse Spark: 44.4 (#69)
- Trinity Large Thinking: 41.3 (#144)

| Benchmark | Muse Spark | Trinity Large Thinking |
|---|---|---|
| LMArena Longer Query | 1451 | 1355 |

## Writing & Preference

- Muse Spark: 66.0 (#39)
- Trinity Large Thinking: 53.8 (#158)

| Benchmark | Muse Spark | Trinity Large Thinking |
|---|---|---|
| LMArena Text | 1474 | 1340 |
| LMArena Creative Writing | 1459 | 1320 |
| LMArena Multi-Turn | 1477 | 1342 |

## FAQ

### Is Muse Spark better than Trinity Large Thinking?

Muse Spark is the stronger model overall, scoring 50.6 to 38.6 on the Noometry Index.

### Is Muse Spark or Trinity Large Thinking better for coding?

Muse Spark scores higher on coding benchmarks: 46.2 versus 34.1 in the Noometry coding category.

### How many benchmarks do Muse Spark and Trinity Large Thinking share?

18 benchmarks have published results for both models. Muse Spark has 27 scored results on Noometry and Trinity Large Thinking has 24.