# ERNIE 5.1 vs Trinity Large Thinking

> ERNIE 5.1 is the stronger model overall, scoring 43.1 to 38.1 on the Noometry Index.

- Canonical page: https://noometry.com/compare/ernie-5-1-vs-trinity-large-thinking
- Last updated: 2026-10-10
- Shared benchmarks: 18

## Summary

- They share 18 benchmarks with published results for both. ERNIE 5.1 scores higher in 8 categories and Trinity Large Thinking in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where ERNIE 5.1 leads 65.3 to 54.0.
- The biggest single-benchmark swing is NYT Connections (extended): 23.4% for ERNIE 5.1 and 16.5% for Trinity Large Thinking.
- Trinity Large Thinking has downloadable open weights; the other is API-only.

## Snapshot

| | ERNIE 5.1 | Trinity Large Thinking |
|---|---|---|
| Provider | Baidu | Arcee AI |
| Noometry Index | 43.1 | 38.1 |
| Rank | 87 | 180 |
| Context | — | 262K |
| Input $/M | — | $0.25 |
| Output $/M | — | $0.80 |
| Weights | Proprietary | Open |

## Coding

- ERNIE 5.1: 43.4 (#78)
- Trinity Large Thinking: 33.8 (#238)

| Benchmark | ERNIE 5.1 | Trinity Large Thinking |
|---|---|---|
| LMArena Coding | 1488 | 1381 |
| LMArena WebDev | — | 1238 |
| SciCode | — | 36.1% |

## Agentic & Tool Use

- ERNIE 5.1: —
- Trinity Large Thinking: —

| Benchmark | ERNIE 5.1 | Trinity Large Thinking |
|---|---|---|
| LMArena Search | 1227 | — |

## Reasoning

- ERNIE 5.1: 20.9 (#209)
- Trinity Large Thinking: 16.3 (#298)

| Benchmark | ERNIE 5.1 | Trinity Large Thinking |
|---|---|---|
| NYT Connections (extended) | 23.4% | 16.5% |
| LMArena Hard Prompts | 1481 | 1350 |
| CritPt | — | 0.9% |
| Thematic Generalization | — | 41.6% |
| Surface Evolver Bench | — | 15.6% |

## Math

- ERNIE 5.1: 37.5 (#96)
- Trinity Large Thinking: 34.9 (#149)

| Benchmark | ERNIE 5.1 | Trinity Large Thinking |
|---|---|---|
| LMArena Math | 1481 | 1366 |

## Knowledge

- ERNIE 5.1: 41.2 (#103)
- Trinity Large Thinking: 40.3 (#107)

| Benchmark | ERNIE 5.1 | Trinity Large Thinking |
|---|---|---|
| LMArena Expert | 1491 | 1359 |
| Vectara Hallucination Rate | — | 6.9% |

## Multilingual

- ERNIE 5.1: 55.7 (#28)
- Trinity Large Thinking: 46.4 (#155)

| Benchmark | ERNIE 5.1 | Trinity Large Thinking |
|---|---|---|
| LMArena Non-English | 1455 | 1325 |
| LMArena Chinese | 1507 | 1372 |
| LMArena French | 1486 | 1374 |
| LMArena German | 1470 | 1356 |
| LMArena Japanese | 1422 | 1312 |
| LMArena Korean | 1428 | 1304 |
| LMArena Russian | 1459 | 1338 |
| LMArena Spanish | 1472 | 1356 |

## Instruction Following

- ERNIE 5.1: 76.9 (#35)
- Trinity Large Thinking: 70.7 (#157)

| Benchmark | ERNIE 5.1 | Trinity Large Thinking |
|---|---|---|
| LMArena Instruction Following | 1460 | 1334 |

## Long Context

- ERNIE 5.1: 44.7 (#56)
- Trinity Large Thinking: 41.2 (#139)

| Benchmark | ERNIE 5.1 | Trinity Large Thinking |
|---|---|---|
| LMArena Longer Query | 1462 | 1355 |

## Writing & Preference

- ERNIE 5.1: 65.3 (#50)
- Trinity Large Thinking: 54.0 (#152)

| Benchmark | ERNIE 5.1 | Trinity Large Thinking |
|---|---|---|
| LMArena Text | 1468 | 1340 |
| LMArena Creative Writing | 1440 | 1321 |
| LMArena Multi-Turn | 1471 | 1342 |

## FAQ

### Is ERNIE 5.1 better than Trinity Large Thinking?

ERNIE 5.1 is the stronger model overall, scoring 43.1 to 38.1 on the Noometry Index.

### Is ERNIE 5.1 or Trinity Large Thinking better for coding?

ERNIE 5.1 scores higher on coding benchmarks: 43.4 versus 33.8 in the Noometry coding category.

### How many benchmarks do ERNIE 5.1 and Trinity Large Thinking share?

18 benchmarks have published results for both models. ERNIE 5.1 has 19 scored results on Noometry and Trinity Large Thinking has 24.