# Trinity Large Thinking vs Yi-Lightning

> Trinity Large Thinking is the stronger model overall, scoring 38.1 to 36.5 on the Noometry Index.

- Canonical page: https://noometry.com/compare/trinity-large-thinking-vs-yi-lightning
- Last updated: 2026-10-10
- Shared benchmarks: 17

## Summary

- They share 17 benchmarks with published results for both. Trinity Large Thinking scores higher in 7 categories and Yi-Lightning in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Yi-Lightning leads 24.9 to 16.3.
- Trinity Large Thinking has downloadable open weights; the other is API-only.

## Snapshot

| | Trinity Large Thinking | Yi-Lightning |
|---|---|---|
| Provider | Arcee AI | 01.AI |
| Noometry Index | 38.1 | 36.5 |
| Rank | 180 | 206 |
| Context | 262K | — |
| Input $/M | $0.25 | — |
| Output $/M | $0.80 | — |
| Weights | Open | Proprietary |

## Coding

- Trinity Large Thinking: 33.8 (#238)
- Yi-Lightning: 27.0 (#315)

| Benchmark | Trinity Large Thinking | Yi-Lightning |
|---|---|---|
| LMArena Coding | 1381 | 1313 |
| Aider Polyglot | — | 12.9% |
| LMArena WebDev | 1238 | — |
| SciCode | 36.1% | — |

## Reasoning

- Trinity Large Thinking: 16.3 (#298)
- Yi-Lightning: 24.9 (#137)

| Benchmark | Trinity Large Thinking | Yi-Lightning |
|---|---|---|
| LMArena Hard Prompts | 1350 | 1302 |
| NYT Connections (extended) | 16.5% | — |
| CritPt | 0.9% | — |
| Thematic Generalization | 41.6% | — |
| Surface Evolver Bench | 15.6% | — |

## Math

- Trinity Large Thinking: 34.9 (#149)
- Yi-Lightning: 33.5 (#173)

| Benchmark | Trinity Large Thinking | Yi-Lightning |
|---|---|---|
| LMArena Math | 1366 | 1300 |

## Knowledge

- Trinity Large Thinking: 40.3 (#107)
- Yi-Lightning: 34.8 (#182)

| Benchmark | Trinity Large Thinking | Yi-Lightning |
|---|---|---|
| LMArena Expert | 1359 | 1286 |
| Vectara Hallucination Rate | 6.9% | — |

## Multilingual

- Trinity Large Thinking: 46.4 (#155)
- Yi-Lightning: 42.4 (#191)

| Benchmark | Trinity Large Thinking | Yi-Lightning |
|---|---|---|
| LMArena Non-English | 1325 | 1269 |
| LMArena Chinese | 1372 | 1320 |
| LMArena French | 1374 | 1304 |
| LMArena German | 1356 | 1267 |
| LMArena Japanese | 1312 | 1228 |
| LMArena Korean | 1304 | 1192 |
| LMArena Russian | 1338 | 1255 |
| LMArena Spanish | 1356 | 1315 |

## Instruction Following

- Trinity Large Thinking: 70.7 (#157)
- Yi-Lightning: 67.6 (#191)

| Benchmark | Trinity Large Thinking | Yi-Lightning |
|---|---|---|
| LMArena Instruction Following | 1334 | 1278 |

## Long Context

- Trinity Large Thinking: 41.2 (#139)
- Yi-Lightning: 39.4 (#176)

| Benchmark | Trinity Large Thinking | Yi-Lightning |
|---|---|---|
| LMArena Longer Query | 1355 | 1297 |

## Writing & Preference

- Trinity Large Thinking: 54.0 (#152)
- Yi-Lightning: 50.4 (#178)

| Benchmark | Trinity Large Thinking | Yi-Lightning |
|---|---|---|
| LMArena Text | 1340 | 1302 |
| LMArena Creative Writing | 1321 | 1280 |
| LMArena Multi-Turn | 1342 | 1311 |

## FAQ

### Is Trinity Large Thinking better than Yi-Lightning?

Trinity Large Thinking is the stronger model overall, scoring 38.1 to 36.5 on the Noometry Index.

### Is Trinity Large Thinking or Yi-Lightning better for coding?

Trinity Large Thinking scores higher on coding benchmarks: 33.8 versus 27.0 in the Noometry coding category.

### How many benchmarks do Trinity Large Thinking and Yi-Lightning share?

17 benchmarks have published results for both models. Trinity Large Thinking has 24 scored results on Noometry and Yi-Lightning has 18.