# DeepSeek-V2.5 (Sep 2024) vs Trinity Large Thinking

> Trinity Large Thinking is the stronger model overall, scoring 38.1 to 37.0 on the Noometry Index.

- Canonical page: https://noometry.com/compare/deepseek-v2-5-vs-trinity-large-thinking
- Last updated: 2026-10-10
- Shared benchmarks: 17

## Summary

- They share 17 benchmarks with published results for both. DeepSeek-V2.5 (Sep 2024) scores higher in 1 category and Trinity Large Thinking in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where DeepSeek-V2.5 (Sep 2024) leads 24.5 to 16.3.

## Snapshot

| | DeepSeek-V2.5 (Sep 2024) | Trinity Large Thinking |
|---|---|---|
| Provider | DeepSeek | Arcee AI |
| Noometry Index | 37.0 | 38.1 |
| Rank | 197 | 180 |
| Context | — | 262K |
| Input $/M | — | $0.25 |
| Output $/M | — | $0.80 |
| Weights | Open | Open |

## Coding

- DeepSeek-V2.5 (Sep 2024): 31.3 (#274)
- Trinity Large Thinking: 33.8 (#238)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | Trinity Large Thinking |
|---|---|---|
| LMArena Coding | 1310 | 1381 |
| Aider Polyglot | 17.8% | — |
| LMArena WebDev | — | 1238 |
| SciCode | — | 36.1% |
| BigCodeBench Instruct | 48.6% | — |
| BigCodeBench Complete | 53.2% | — |
| HumanEval+ | 83.5% | — |
| MBPP+ | 74.1% | — |

## Reasoning

- DeepSeek-V2.5 (Sep 2024): 24.5 (#145)
- Trinity Large Thinking: 16.3 (#298)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | Trinity Large Thinking |
|---|---|---|
| LMArena Hard Prompts | 1289 | 1350 |
| NYT Connections (extended) | — | 16.5% |
| CritPt | — | 0.9% |
| Thematic Generalization | — | 41.6% |
| Surface Evolver Bench | — | 15.6% |

## Math

- DeepSeek-V2.5 (Sep 2024): 33.3 (#177)
- Trinity Large Thinking: 34.9 (#149)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | Trinity Large Thinking |
|---|---|---|
| LMArena Math | 1289 | 1366 |

## Knowledge

- DeepSeek-V2.5 (Sep 2024): 34.2 (#190)
- Trinity Large Thinking: 40.3 (#107)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | Trinity Large Thinking |
|---|---|---|
| LMArena Expert | 1266 | 1359 |
| Vectara Hallucination Rate | — | 6.9% |

## Multilingual

- DeepSeek-V2.5 (Sep 2024): 42.7 (#188)
- Trinity Large Thinking: 46.4 (#155)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | Trinity Large Thinking |
|---|---|---|
| LMArena Non-English | 1273 | 1325 |
| LMArena Chinese | 1317 | 1372 |
| LMArena French | 1288 | 1374 |
| LMArena German | 1258 | 1356 |
| LMArena Japanese | 1228 | 1312 |
| LMArena Korean | 1209 | 1304 |
| LMArena Russian | 1289 | 1338 |
| LMArena Spanish | 1248 | 1356 |

## Instruction Following

- DeepSeek-V2.5 (Sep 2024): 67.7 (#189)
- Trinity Large Thinking: 70.7 (#157)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | Trinity Large Thinking |
|---|---|---|
| LMArena Instruction Following | 1280 | 1334 |

## Long Context

- DeepSeek-V2.5 (Sep 2024): 39.5 (#169)
- Trinity Large Thinking: 41.2 (#139)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | Trinity Large Thinking |
|---|---|---|
| LMArena Longer Query | 1301 | 1355 |

## Writing & Preference

- DeepSeek-V2.5 (Sep 2024): 50.0 (#182)
- Trinity Large Thinking: 54.0 (#152)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | Trinity Large Thinking |
|---|---|---|
| LMArena Text | 1294 | 1340 |
| LMArena Creative Writing | 1285 | 1321 |
| LMArena Multi-Turn | 1297 | 1342 |

## FAQ

### Is DeepSeek-V2.5 (Sep 2024) better than Trinity Large Thinking?

Trinity Large Thinking is the stronger model overall, scoring 38.1 to 37.0 on the Noometry Index.

### Is DeepSeek-V2.5 (Sep 2024) or Trinity Large Thinking better for coding?

Trinity Large Thinking scores higher on coding benchmarks: 33.8 versus 31.3 in the Noometry coding category.

### How many benchmarks do DeepSeek-V2.5 (Sep 2024) and Trinity Large Thinking share?

17 benchmarks have published results for both models. DeepSeek-V2.5 (Sep 2024) has 22 scored results on Noometry and Trinity Large Thinking has 24.