# Llama 2-7B vs Qwen3-30B-A3B

> Qwen3-30B-A3B is the stronger model overall, scoring 38.9 to 29.1 on the Noometry Index.

- Canonical page: https://noometry.com/compare/llama-2-7b-vs-qwen3-30b-a3b
- Last updated: 2026-10-10
- Shared benchmarks: 17

## Summary

- They share 17 benchmarks with published results for both. Llama 2-7B scores higher in 0 categories and Qwen3-30B-A3B in 8 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Qwen3-30B-A3B leads 55.6 to 28.0.
- The biggest single-benchmark swing is Chess Puzzles: 0% for Llama 2-7B and 8% for Qwen3-30B-A3B.

## Snapshot

| | Llama 2-7B | Qwen3-30B-A3B |
|---|---|---|
| Provider | Meta | Alibaba (Qwen) |
| Noometry Index | 29.1 | 38.9 |
| Rank | 317 | 179 |
| Context | — | 41K |
| Input $/M | — | $0.12 |
| Output $/M | — | $0.50 |
| Weights | Open | Open |

## Coding

- Llama 2-7B: 29.2 (#307)
- Qwen3-30B-A3B: 37.5 (#194)

| Benchmark | Llama 2-7B | Qwen3-30B-A3B |
|---|---|---|
| LMArena Coding | 1002 | 1416 |
| SciCode | — | 33.3% |
| WeirdML | — | 29.8% |

## Agentic & Tool Use

- Llama 2-7B: —
- Qwen3-30B-A3B: 29.8 (#82)

| Benchmark | Llama 2-7B | Qwen3-30B-A3B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 41.4% |

## Reasoning

- Llama 2-7B: 15.7 (#312)
- Qwen3-30B-A3B: 22.2 (#204)

| Benchmark | Llama 2-7B | Qwen3-30B-A3B |
|---|---|---|
| Chess Puzzles | 0% | 8% |
| LMArena Hard Prompts | 1009 | 1398 |
| Epoch Capabilities Index | 99.06 | 139.63 |
| Kagi LLM Benchmark | — | 54.9% |
| CritPt | — | 0.3% |
| DTBench | — | 69.3% |
| LMCA | — | 22.4% |
| BIG-Bench Hard | 39.2% | — |
| HellaSwag | 77.2% | — |
| LAMBADA | 73.3% | — |
| PIQA | 78.8% | — |
| WinoGrande | 69.2% | — |

## Math

- Llama 2-7B: 30.7 (#233)
- Qwen3-30B-A3B: 37.4 (#157)

| Benchmark | Llama 2-7B | Qwen3-30B-A3B |
|---|---|---|
| LMArena Math | 1042 | 1394 |
| MathArena Final-Answer Competitions | — | 47.8% |
| OTIS Mock AIME 2024-2025 | — | 70.3% |
| GSM8K | 16.7% | — |

## Knowledge

- Llama 2-7B: 28.2 (#248)
- Qwen3-30B-A3B: 41.8 (#105)

| Benchmark | Llama 2-7B | Qwen3-30B-A3B |
|---|---|---|
| LMArena Expert | 1036 | 1396 |
| GPQA Diamond | — | 70.1% |
| Confabulations | — | 12.3% |
| ARC (AI2) Challenge | 45.9% | — |
| BoolQ | 77.9% | — |
| MMLU | 45.8% | — |
| OpenBookQA | 58.6% | — |
| TriviaQA | 73.7% | — |

## Multimodal

- Llama 2-7B: —
- Qwen3-30B-A3B: —

| Benchmark | Llama 2-7B | Qwen3-30B-A3B |
|---|---|---|
| ScienceQA | 43.1% | — |

## Multilingual

- Llama 2-7B: 23.8 (#293)
- Qwen3-30B-A3B: 49.5 (#132)

| Benchmark | Llama 2-7B | Qwen3-30B-A3B |
|---|---|---|
| LMArena Non-English | 973 | 1372 |
| LMArena Chinese | 973 | 1433 |
| LMArena French | 970 | 1418 |
| LMArena German | 978 | 1380 |
| LMArena Russian | 995 | 1370 |
| LMArena Spanish | 1007 | 1404 |
| LMArena Japanese | — | 1337 |
| LMArena Korean | — | 1331 |

## Instruction Following

- Llama 2-7B: 50.8 (#298)
- Qwen3-30B-A3B: 72.0 (#142)

| Benchmark | Llama 2-7B | Qwen3-30B-A3B |
|---|---|---|
| LMArena Instruction Following | 1006 | 1363 |

## Long Context

- Llama 2-7B: 30.4 (#287)
- Qwen3-30B-A3B: 31.0 (#283)

| Benchmark | Llama 2-7B | Qwen3-30B-A3B |
|---|---|---|
| LMArena Longer Query | 999 | 1379 |
| Fiction.LiveBench | — | 40.6% |

## Writing & Preference

- Llama 2-7B: 28.0 (#298)
- Qwen3-30B-A3B: 55.6 (#143)

| Benchmark | Llama 2-7B | Qwen3-30B-A3B |
|---|---|---|
| LMArena Text | 1053 | 1384 |
| LMArena Creative Writing | 1033 | 1317 |
| LMArena Multi-Turn | 1029 | 1378 |
| Short-Story Creative Writing | — | 75.3% |

## FAQ

### Is Llama 2-7B better than Qwen3-30B-A3B?

Qwen3-30B-A3B is the stronger model overall, scoring 38.9 to 29.1 on the Noometry Index.

### Is Llama 2-7B or Qwen3-30B-A3B better for coding?

Qwen3-30B-A3B scores higher on coding benchmarks: 37.5 versus 29.2 in the Noometry coding category.

### How many benchmarks do Llama 2-7B and Qwen3-30B-A3B share?

17 benchmarks have published results for both models. Llama 2-7B has 29 scored results on Noometry and Qwen3-30B-A3B has 32.