# Llama 2-70B vs Trinity Large Thinking

> Trinity Large Thinking is the stronger model overall, scoring 38.6 to 24.4 on the Noometry Index.

- Canonical page: https://noometry.com/compare/llama-2-70b-vs-trinity-large-thinking
- Last updated: 2026-10-11
- Shared benchmarks: 17

## Summary

- They share 17 benchmarks with published results for both. Llama 2-70B scores higher in 0 categories and Trinity Large Thinking in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Trinity Large Thinking leads 40.9 to 7.4.

## Snapshot

| | Llama 2-70B | Trinity Large Thinking |
|---|---|---|
| Provider | Meta | Arcee AI |
| Noometry Index | 24.4 | 38.6 |
| Rank | 349 | 185 |
| Context | — | 262K |
| Input $/M | — | $0.25 |
| Output $/M | — | $0.80 |
| Weights | Open | Open |

## Coding

- Llama 2-70B: 31.4 (#286)
- Trinity Large Thinking: 34.1 (#244)

| Benchmark | Llama 2-70B | Trinity Large Thinking |
|---|---|---|
| LMArena Coding | 1079 | 1381 |
| LMArena WebDev | — | 1238 |
| SciCode | — | 36.1% |

## Reasoning

- Llama 2-70B: 14.4 (#325)
- Trinity Large Thinking: 16.9 (#298)

| Benchmark | Llama 2-70B | Trinity Large Thinking |
|---|---|---|
| LMArena Hard Prompts | 1073 | 1350 |
| NYT Connections (extended) | — | 16.5% |
| CritPt | — | 0.9% |
| Thematic Generalization | — | 41.6% |
| DTBench | 41.6% | — |
| Surface Evolver Bench | — | 15.6% |
| BIG-Bench Hard | 64.9% | — |
| CommonsenseQA 2.0 | 50% | — |
| Epoch Capabilities Index | 113.79 | — |
| ForecastBench | 51.4 | — |
| HellaSwag | 85.3% | — |
| LAMBADA | 78.9% | — |
| PIQA | 82.8% | — |
| WinoGrande | 80.2% | — |

## Math

- Llama 2-70B: 8.1 (#326)
- Trinity Large Thinking: 37.6 (#149)

| Benchmark | Llama 2-70B | Trinity Large Thinking |
|---|---|---|
| LMArena Math | 1091 | 1366 |
| OTIS Mock AIME 2024-2025 | 0% | — |
| MATH Level 5 | 3.3% | — |
| GSM8K | 69.6% | — |

## Knowledge

- Llama 2-70B: 7.4 (#310)
- Trinity Large Thinking: 40.9 (#113)

| Benchmark | Llama 2-70B | Trinity Large Thinking |
|---|---|---|
| LMArena Expert | 1039 | 1360 |
| GPQA Diamond | 26.3% | — |
| Vectara Hallucination Rate | — | 6.9% |
| ARC (AI2) Challenge | 78.3% | — |
| BoolQ | 88.6% | — |
| MMLU | 69.9% | — |
| OpenBookQA | 60.2% | — |
| TriviaQA | 87.6% | — |

## Multilingual

- Llama 2-70B: 27.7 (#274)
- Trinity Large Thinking: 46.2 (#160)

| Benchmark | Llama 2-70B | Trinity Large Thinking |
|---|---|---|
| LMArena Non-English | 1045 | 1325 |
| LMArena Chinese | 995 | 1373 |
| LMArena French | 1090 | 1374 |
| LMArena German | 1041 | 1356 |
| LMArena Japanese | 927 | 1311 |
| LMArena Korean | 964 | 1306 |
| LMArena Russian | 1083 | 1337 |
| LMArena Spanish | 1143 | 1357 |

## Instruction Following

- Llama 2-70B: 54.9 (#278)
- Trinity Large Thinking: 70.5 (#162)

| Benchmark | Llama 2-70B | Trinity Large Thinking |
|---|---|---|
| LMArena Instruction Following | 1071 | 1334 |

## Long Context

- Llama 2-70B: 32.3 (#270)
- Trinity Large Thinking: 41.3 (#144)

| Benchmark | Llama 2-70B | Trinity Large Thinking |
|---|---|---|
| LMArena Longer Query | 1062 | 1355 |

## Writing & Preference

- Llama 2-70B: 32.3 (#279)
- Trinity Large Thinking: 53.8 (#158)

| Benchmark | Llama 2-70B | Trinity Large Thinking |
|---|---|---|
| LMArena Text | 1115 | 1340 |
| LMArena Creative Writing | 1075 | 1320 |
| LMArena Multi-Turn | 1088 | 1342 |

## FAQ

### Is Llama 2-70B better than Trinity Large Thinking?

Trinity Large Thinking is the stronger model overall, scoring 38.6 to 24.4 on the Noometry Index.

### Is Llama 2-70B or Trinity Large Thinking better for coding?

Trinity Large Thinking scores higher on coding benchmarks: 34.1 versus 31.4 in the Noometry coding category.

### How many benchmarks do Llama 2-70B and Trinity Large Thinking share?

17 benchmarks have published results for both models. Llama 2-70B has 35 scored results on Noometry and Trinity Large Thinking has 24.