# Qwen2-72B vs Qwen3 8B

> Qwen3 8B is the stronger model overall, scoring 33.3 to 29.5 on the Noometry Index.

- Canonical page: https://noometry.com/compare/qwen2-72b-vs-qwen3-8b
- Last updated: 2026-10-10
- Shared benchmarks: 2

## Summary

- They share 2 benchmarks with published results for both. Qwen2-72B scores higher in 1 category and Qwen3 8B in 5 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen3 8B leads 36.1 to 21.2.
- The biggest single-benchmark swing is GPQA Diamond: 40.8% for Qwen2-72B and 56.8% for Qwen3 8B.

## Snapshot

| | Qwen2-72B | Qwen3 8B |
|---|---|---|
| Provider | Alibaba (Qwen) | Alibaba (Qwen) |
| Noometry Index | 29.5 | 33.3 |
| Rank | 294 | 237 |
| Context | — | 131K |
| Input $/M | — | $0.18 |
| Output $/M | — | $0.70 |
| Weights | Open | Open |

## Coding

- Qwen2-72B: 28.7 (#303)
- Qwen3 8B: 33.4 (#245)

| Benchmark | Qwen2-72B | Qwen3 8B |
|---|---|---|
| SciCode | — | 22.6% |
| WeirdML | 11.3% | — |
| BigCodeBench Instruct | 38.5% | — |
| LMArena Coding | 1196 | — |
| BigCodeBench Complete | 54% | — |

## Agentic & Tool Use

- Qwen2-72B: 16.9 (#138)
- Qwen3 8B: 29.9 (#71)

| Benchmark | Qwen2-72B | Qwen3 8B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 42.6% |
| TheAgentCompany | 1.1% | — |
| METR Time Horizons | 29.9% | — |

## Reasoning

- Qwen2-72B: 22.2 (#184)
- Qwen3 8B: 16.1 (#299)

| Benchmark | Qwen2-72B | Qwen3 8B |
|---|---|---|
| Epoch Capabilities Index | 125.27 | 136.17 |
| CritPt | — | 0% |
| Chess Puzzles | — | 5% |
| LMArena Hard Prompts | 1191 | — |
| DTBench | — | 59.7% |
| LMCA | — | 8.8% |

## Math

- Qwen2-72B: 27.9 (#232)
- Qwen3 8B: 33.3 (#176)

| Benchmark | Qwen2-72B | Qwen3 8B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 56.1% |
| LMArena Math | 1235 | — |
| MATH Level 5 | 39.1% | — |

## Knowledge

- Qwen2-72B: 21.2 (#270)
- Qwen3 8B: 36.1 (#164)

| Benchmark | Qwen2-72B | Qwen3 8B |
|---|---|---|
| GPQA Diamond | 40.8% | 56.8% |
| Vectara Hallucination Rate | — | 4.8% |
| LMArena Expert | 1171 | — |
| MMLU | 82.4% | — |

## Multilingual

- Qwen2-72B: 36.0 (#239)
- Qwen3 8B: —

| Benchmark | Qwen2-72B | Qwen3 8B |
|---|---|---|
| LMArena Non-English | 1176 | — |
| LMArena Chinese | 1240 | — |
| LMArena French | 1169 | — |
| LMArena German | 1151 | — |
| LMArena Japanese | 1111 | — |
| LMArena Korean | 1083 | — |
| LMArena Russian | 1169 | — |
| LMArena Spanish | 1168 | — |

## Instruction Following

- Qwen2-72B: 62.0 (#236)
- Qwen3 8B: —

| Benchmark | Qwen2-72B | Qwen3 8B |
|---|---|---|
| LMArena Instruction Following | 1181 | — |

## Long Context

- Qwen2-72B: 36.1 (#230)
- Qwen3 8B: 37.8 (#205)

| Benchmark | Qwen2-72B | Qwen3 8B |
|---|---|---|
| Fiction.LiveBench | — | 62.1% |
| LMArena Longer Query | 1193 | — |

## Writing & Preference

- Qwen2-72B: 41.0 (#236)
- Qwen3 8B: —

| Benchmark | Qwen2-72B | Qwen3 8B |
|---|---|---|
| LMArena Text | 1203 | — |
| LMArena Creative Writing | 1181 | — |
| LMArena Multi-Turn | 1195 | — |

## FAQ

### Is Qwen2-72B better than Qwen3 8B?

Qwen3 8B is the stronger model overall, scoring 33.3 to 29.5 on the Noometry Index.

### Is Qwen2-72B or Qwen3 8B better for coding?

Qwen3 8B scores higher on coding benchmarks: 33.4 versus 28.7 in the Noometry coding category.

### How many benchmarks do Qwen2-72B and Qwen3 8B share?

2 benchmarks have published results for both models. Qwen2-72B has 26 scored results on Noometry and Qwen3 8B has 11.