# Llama 3-70B vs Trinity Large Thinking

> Trinity Large Thinking is the stronger model overall, scoring 38.6 to 28.8 on the Noometry Index.

- Canonical page: https://noometry.com/compare/llama-3-70b-vs-trinity-large-thinking
- Last updated: 2026-10-10
- Shared benchmarks: 17

## Summary

- They share 17 benchmarks with published results for both. Llama 3-70B scores higher in 2 categories and Trinity Large Thinking in 6 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Trinity Large Thinking leads 37.6 to 12.8.

## Snapshot

| | Llama 3-70B | Trinity Large Thinking |
|---|---|---|
| Provider | Meta | Arcee AI |
| Noometry Index | 28.8 | 38.6 |
| Rank | 323 | 185 |
| Context | — | 262K |
| Input $/M | — | $0.25 |
| Output $/M | — | $0.80 |
| Weights | Open | Open |

## Coding

- Llama 3-70B: 35.8 (#218)
- Trinity Large Thinking: 34.1 (#244)

| Benchmark | Llama 3-70B | Trinity Large Thinking |
|---|---|---|
| LMArena Coding | 1206 | 1381 |
| LMArena WebDev | — | 1238 |
| SciCode | — | 36.1% |
| BigCodeBench Instruct | 43.6% | — |
| BigCodeBench Complete | 54.5% | — |
| HumanEval+ | 72% | — |
| MBPP+ | 69% | — |

## Agentic & Tool Use

- Llama 3-70B: 21.1 (#139)
- Trinity Large Thinking: —

| Benchmark | Llama 3-70B | Trinity Large Thinking |
|---|---|---|
| Cybench | 5% | — |

## Reasoning

- Llama 3-70B: 18.0 (#288)
- Trinity Large Thinking: 16.9 (#298)

| Benchmark | Llama 3-70B | Trinity Large Thinking |
|---|---|---|
| LMArena Hard Prompts | 1195 | 1350 |
| Kagi LLM Benchmark | 35.1% | — |
| NYT Connections (extended) | — | 16.5% |
| CritPt | — | 0.9% |
| Thematic Generalization | — | 41.6% |
| DTBench | 54.2% | — |
| Surface Evolver Bench | — | 15.6% |
| Epoch Capabilities Index | 122.93 | — |
| ForecastBench | 57.1 | — |
| WinoGrande | 83.5% | — |

## Math

- Llama 3-70B: 12.8 (#305)
- Trinity Large Thinking: 37.6 (#149)

| Benchmark | Llama 3-70B | Trinity Large Thinking |
|---|---|---|
| LMArena Math | 1218 | 1366 |
| OTIS Mock AIME 2024-2025 | 4.3% | — |
| MATH Level 5 | 22.6% | — |

## Knowledge

- Llama 3-70B: 20.8 (#277)
- Trinity Large Thinking: 40.9 (#113)

| Benchmark | Llama 3-70B | Trinity Large Thinking |
|---|---|---|
| LMArena Expert | 1149 | 1360 |
| GPQA Diamond | 40.6% | — |
| Vectara Hallucination Rate | — | 6.9% |
| MMLU | 79.3% | — |

## Multilingual

- Llama 3-70B: 33.6 (#251)
- Trinity Large Thinking: 46.2 (#160)

| Benchmark | Llama 3-70B | Trinity Large Thinking |
|---|---|---|
| LMArena Non-English | 1142 | 1325 |
| LMArena Chinese | 1114 | 1373 |
| LMArena French | 1232 | 1374 |
| LMArena German | 1169 | 1356 |
| LMArena Japanese | 1017 | 1311 |
| LMArena Korean | 1017 | 1306 |
| LMArena Russian | 1159 | 1337 |
| LMArena Spanish | 1241 | 1357 |

## Instruction Following

- Llama 3-70B: 62.5 (#238)
- Trinity Large Thinking: 70.5 (#162)

| Benchmark | Llama 3-70B | Trinity Large Thinking |
|---|---|---|
| LMArena Instruction Following | 1194 | 1334 |

## Long Context

- Llama 3-70B: 35.6 (#240)
- Trinity Large Thinking: 41.3 (#144)

| Benchmark | Llama 3-70B | Trinity Large Thinking |
|---|---|---|
| LMArena Longer Query | 1174 | 1355 |

## Writing & Preference

- Llama 3-70B: 42.8 (#231)
- Trinity Large Thinking: 53.8 (#158)

| Benchmark | Llama 3-70B | Trinity Large Thinking |
|---|---|---|
| LMArena Text | 1221 | 1340 |
| LMArena Creative Writing | 1210 | 1320 |
| LMArena Multi-Turn | 1223 | 1342 |

## FAQ

### Is Llama 3-70B better than Trinity Large Thinking?

Trinity Large Thinking is the stronger model overall, scoring 38.6 to 28.8 on the Noometry Index.

### Is Llama 3-70B or Trinity Large Thinking better for coding?

Llama 3-70B scores higher on coding benchmarks: 35.8 versus 34.1 in the Noometry coding category.

### How many benchmarks do Llama 3-70B and Trinity Large Thinking share?

17 benchmarks have published results for both models. Llama 3-70B has 31 scored results on Noometry and Trinity Large Thinking has 24.