# DeepSeek LLM 67B vs Trinity Large Thinking

> Trinity Large Thinking is the stronger model overall, scoring 38.6 to 24.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/deepseek-llm-67b-vs-trinity-large-thinking
- Last updated: 2026-10-10
- Shared benchmarks: 10

## Summary

- They share 10 benchmarks with published results for both. DeepSeek LLM 67B scores higher in 0 categories and Trinity Large Thinking in 8 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Trinity Large Thinking leads 40.9 to 7.0.

## Snapshot

| | DeepSeek LLM 67B | Trinity Large Thinking |
|---|---|---|
| Provider | DeepSeek | Arcee AI |
| Noometry Index | 24.9 | 38.6 |
| Rank | 347 | 185 |
| Context | — | 262K |
| Input $/M | — | $0.25 |
| Output $/M | — | $0.80 |
| Weights | Open | Open |

## Coding

- DeepSeek LLM 67B: 31.9 (#278)
- Trinity Large Thinking: 34.1 (#244)

| Benchmark | DeepSeek LLM 67B | Trinity Large Thinking |
|---|---|---|
| LMArena Coding | 1096 | 1381 |
| LMArena WebDev | — | 1238 |
| SciCode | — | 36.1% |

## Reasoning

- DeepSeek LLM 67B: 16.5 (#304)
- Trinity Large Thinking: 16.9 (#298)

| Benchmark | DeepSeek LLM 67B | Trinity Large Thinking |
|---|---|---|
| LMArena Hard Prompts | 1070 | 1350 |
| NYT Connections (extended) | — | 16.5% |
| CritPt | — | 0.9% |
| Chess Puzzles | 0% | — |
| Thematic Generalization | — | 41.6% |
| Surface Evolver Bench | — | 15.6% |
| Epoch Capabilities Index | 110.5 | — |

## Math

- DeepSeek LLM 67B: 8.7 (#324)
- Trinity Large Thinking: 37.6 (#149)

| Benchmark | DeepSeek LLM 67B | Trinity Large Thinking |
|---|---|---|
| LMArena Math | 1108 | 1366 |
| OTIS Mock AIME 2024-2025 | 0.8% | — |
| MATH Level 5 | 6.4% | — |

## Knowledge

- DeepSeek LLM 67B: 7.0 (#313)
- Trinity Large Thinking: 40.9 (#113)

| Benchmark | DeepSeek LLM 67B | Trinity Large Thinking |
|---|---|---|
| GPQA Diamond | 24.6% | — |
| Vectara Hallucination Rate | — | 6.9% |
| LMArena Expert | — | 1360 |

## Multilingual

- DeepSeek LLM 67B: 29.4 (#267)
- Trinity Large Thinking: 46.2 (#160)

| Benchmark | DeepSeek LLM 67B | Trinity Large Thinking |
|---|---|---|
| LMArena Non-English | 1073 | 1325 |
| LMArena Chinese | 1132 | 1373 |
| LMArena French | — | 1374 |
| LMArena German | — | 1356 |
| LMArena Japanese | — | 1311 |
| LMArena Korean | — | 1306 |
| LMArena Russian | — | 1337 |
| LMArena Spanish | — | 1357 |

## Instruction Following

- DeepSeek LLM 67B: 55.4 (#277)
- Trinity Large Thinking: 70.5 (#162)

| Benchmark | DeepSeek LLM 67B | Trinity Large Thinking |
|---|---|---|
| LMArena Instruction Following | 1079 | 1334 |

## Long Context

- DeepSeek LLM 67B: 33.1 (#265)
- Trinity Large Thinking: 41.3 (#144)

| Benchmark | DeepSeek LLM 67B | Trinity Large Thinking |
|---|---|---|
| LMArena Longer Query | 1092 | 1355 |

## Writing & Preference

- DeepSeek LLM 67B: 31.6 (#282)
- Trinity Large Thinking: 53.8 (#158)

| Benchmark | DeepSeek LLM 67B | Trinity Large Thinking |
|---|---|---|
| LMArena Text | 1105 | 1340 |
| LMArena Creative Writing | 1067 | 1320 |
| LMArena Multi-Turn | 1082 | 1342 |

## FAQ

### Is DeepSeek LLM 67B better than Trinity Large Thinking?

Trinity Large Thinking is the stronger model overall, scoring 38.6 to 24.9 on the Noometry Index.

### Is DeepSeek LLM 67B or Trinity Large Thinking better for coding?

Trinity Large Thinking scores higher on coding benchmarks: 34.1 versus 31.9 in the Noometry coding category.

### How many benchmarks do DeepSeek LLM 67B and Trinity Large Thinking share?

10 benchmarks have published results for both models. DeepSeek LLM 67B has 15 scored results on Noometry and Trinity Large Thinking has 24.