# Qwen2-72B vs Trinity Large Thinking

> Trinity Large Thinking is the stronger model overall, scoring 38.1 to 29.5 on the Noometry Index.

- Canonical page: https://noometry.com/compare/qwen2-72b-vs-trinity-large-thinking
- Last updated: 2026-10-10
- Shared benchmarks: 17

## Summary

- They share 17 benchmarks with published results for both. Qwen2-72B scores higher in 1 category and Trinity Large Thinking in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Trinity Large Thinking leads 40.3 to 21.2.

## Snapshot

| | Qwen2-72B | Trinity Large Thinking |
|---|---|---|
| Provider | Alibaba (Qwen) | Arcee AI |
| Noometry Index | 29.5 | 38.1 |
| Rank | 294 | 180 |
| Context | — | 262K |
| Input $/M | — | $0.25 |
| Output $/M | — | $0.80 |
| Weights | Open | Open |

## Coding

- Qwen2-72B: 28.7 (#303)
- Trinity Large Thinking: 33.8 (#238)

| Benchmark | Qwen2-72B | Trinity Large Thinking |
|---|---|---|
| LMArena Coding | 1196 | 1381 |
| LMArena WebDev | — | 1238 |
| SciCode | — | 36.1% |
| WeirdML | 11.3% | — |
| BigCodeBench Instruct | 38.5% | — |
| BigCodeBench Complete | 54% | — |

## Agentic & Tool Use

- Qwen2-72B: 16.9 (#138)
- Trinity Large Thinking: —

| Benchmark | Qwen2-72B | Trinity Large Thinking |
|---|---|---|
| TheAgentCompany | 1.1% | — |
| METR Time Horizons | 29.9% | — |

## Reasoning

- Qwen2-72B: 22.2 (#184)
- Trinity Large Thinking: 16.3 (#298)

| Benchmark | Qwen2-72B | Trinity Large Thinking |
|---|---|---|
| LMArena Hard Prompts | 1191 | 1350 |
| NYT Connections (extended) | — | 16.5% |
| CritPt | — | 0.9% |
| Thematic Generalization | — | 41.6% |
| Surface Evolver Bench | — | 15.6% |
| Epoch Capabilities Index | 125.27 | — |

## Math

- Qwen2-72B: 27.9 (#232)
- Trinity Large Thinking: 34.9 (#149)

| Benchmark | Qwen2-72B | Trinity Large Thinking |
|---|---|---|
| LMArena Math | 1235 | 1366 |
| MATH Level 5 | 39.1% | — |

## Knowledge

- Qwen2-72B: 21.2 (#270)
- Trinity Large Thinking: 40.3 (#107)

| Benchmark | Qwen2-72B | Trinity Large Thinking |
|---|---|---|
| LMArena Expert | 1171 | 1359 |
| GPQA Diamond | 40.8% | — |
| Vectara Hallucination Rate | — | 6.9% |
| MMLU | 82.4% | — |

## Multilingual

- Qwen2-72B: 36.0 (#239)
- Trinity Large Thinking: 46.4 (#155)

| Benchmark | Qwen2-72B | Trinity Large Thinking |
|---|---|---|
| LMArena Non-English | 1176 | 1325 |
| LMArena Chinese | 1240 | 1372 |
| LMArena French | 1169 | 1374 |
| LMArena German | 1151 | 1356 |
| LMArena Japanese | 1111 | 1312 |
| LMArena Korean | 1083 | 1304 |
| LMArena Russian | 1169 | 1338 |
| LMArena Spanish | 1168 | 1356 |

## Instruction Following

- Qwen2-72B: 62.0 (#236)
- Trinity Large Thinking: 70.7 (#157)

| Benchmark | Qwen2-72B | Trinity Large Thinking |
|---|---|---|
| LMArena Instruction Following | 1181 | 1334 |

## Long Context

- Qwen2-72B: 36.1 (#230)
- Trinity Large Thinking: 41.2 (#139)

| Benchmark | Qwen2-72B | Trinity Large Thinking |
|---|---|---|
| LMArena Longer Query | 1193 | 1355 |

## Writing & Preference

- Qwen2-72B: 41.0 (#236)
- Trinity Large Thinking: 54.0 (#152)

| Benchmark | Qwen2-72B | Trinity Large Thinking |
|---|---|---|
| LMArena Text | 1203 | 1340 |
| LMArena Creative Writing | 1181 | 1321 |
| LMArena Multi-Turn | 1195 | 1342 |

## FAQ

### Is Qwen2-72B better than Trinity Large Thinking?

Trinity Large Thinking is the stronger model overall, scoring 38.1 to 29.5 on the Noometry Index.

### Is Qwen2-72B or Trinity Large Thinking better for coding?

Trinity Large Thinking scores higher on coding benchmarks: 33.8 versus 28.7 in the Noometry coding category.

### How many benchmarks do Qwen2-72B and Trinity Large Thinking share?

17 benchmarks have published results for both models. Qwen2-72B has 26 scored results on Noometry and Trinity Large Thinking has 24.