# Llama 13b vs Qwen3-30B-A3B

> Qwen3-30B-A3B is the stronger model overall, scoring 38.9 to 24.4 on the Noometry Index.

- Canonical page: https://noometry.com/compare/llama-13b-vs-qwen3-30b-a3b
- Last updated: 2026-10-10
- Shared benchmarks: 9

## Summary

- They share 9 benchmarks with published results for both. Llama 13b scores higher in 0 categories and Qwen3-30B-A3B in 6 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Qwen3-30B-A3B leads 55.6 to 13.8.

## Snapshot

| | Llama 13b | Qwen3-30B-A3B |
|---|---|---|
| Provider | Meta | Alibaba (Qwen) |
| Noometry Index | 24.4 | 38.9 |
| Rank | 348 | 179 |
| Context | — | 41K |
| Input $/M | — | $0.12 |
| Output $/M | — | $0.50 |
| Weights | Open | Open |

## Coding

- Llama 13b: 21.4 (#337)
- Qwen3-30B-A3B: 37.5 (#194)

| Benchmark | Llama 13b | Qwen3-30B-A3B |
|---|---|---|
| LMArena Coding | 683 | 1416 |
| SciCode | — | 33.3% |
| WeirdML | — | 29.8% |

## Agentic & Tool Use

- Llama 13b: —
- Qwen3-30B-A3B: 29.8 (#82)

| Benchmark | Llama 13b | Qwen3-30B-A3B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 41.4% |

## Reasoning

- Llama 13b: 14.0 (#329)
- Qwen3-30B-A3B: 22.2 (#204)

| Benchmark | Llama 13b | Qwen3-30B-A3B |
|---|---|---|
| LMArena Hard Prompts | 728 | 1398 |
| Epoch Capabilities Index | 100.58 | 139.63 |
| Kagi LLM Benchmark | — | 54.9% |
| CritPt | — | 0.3% |
| Chess Puzzles | — | 8% |
| DTBench | — | 69.3% |
| LMCA | — | 22.4% |
| BIG-Bench Hard | 37.9% | — |
| HellaSwag | 79.2% | — |
| LAMBADA | 75.2% | — |
| PIQA | 80.1% | — |
| WinoGrande | 73% | — |

## Math

- Llama 13b: 26.7 (#256)
- Qwen3-30B-A3B: 37.4 (#157)

| Benchmark | Llama 13b | Qwen3-30B-A3B |
|---|---|---|
| LMArena Math | 838 | 1394 |
| MathArena Final-Answer Competitions | — | 47.8% |
| OTIS Mock AIME 2024-2025 | — | 70.3% |
| GSM8K | 20.6% | — |

## Knowledge

- Llama 13b: —
- Qwen3-30B-A3B: 41.8 (#105)

| Benchmark | Llama 13b | Qwen3-30B-A3B |
|---|---|---|
| GPQA Diamond | — | 70.1% |
| Confabulations | — | 12.3% |
| LMArena Expert | — | 1396 |
| ARC (AI2) Challenge | 52.7% | — |
| BoolQ | 78.7% | — |
| MMLU | 47.7% | — |
| OpenBookQA | 56.4% | — |
| TriviaQA | 77.9% | — |

## Multimodal

- Llama 13b: —
- Qwen3-30B-A3B: —

| Benchmark | Llama 13b | Qwen3-30B-A3B |
|---|---|---|
| ScienceQA | 43.3% | — |

## Multilingual

- Llama 13b: 16.6 (#297)
- Qwen3-30B-A3B: 49.5 (#132)

| Benchmark | Llama 13b | Qwen3-30B-A3B |
|---|---|---|
| LMArena Non-English | 819 | 1372 |
| LMArena Chinese | — | 1433 |
| LMArena French | — | 1418 |
| LMArena German | — | 1380 |
| LMArena Japanese | — | 1337 |
| LMArena Korean | — | 1331 |
| LMArena Russian | — | 1370 |
| LMArena Spanish | — | 1404 |

## Instruction Following

- Llama 13b: 36.7 (#305)
- Qwen3-30B-A3B: 72.0 (#142)

| Benchmark | Llama 13b | Qwen3-30B-A3B |
|---|---|---|
| LMArena Instruction Following | 781 | 1363 |

## Long Context

- Llama 13b: —
- Qwen3-30B-A3B: 31.0 (#283)

| Benchmark | Llama 13b | Qwen3-30B-A3B |
|---|---|---|
| Fiction.LiveBench | — | 40.6% |
| LMArena Longer Query | — | 1379 |

## Writing & Preference

- Llama 13b: 13.8 (#312)
- Qwen3-30B-A3B: 55.6 (#143)

| Benchmark | Llama 13b | Qwen3-30B-A3B |
|---|---|---|
| LMArena Text | 834 | 1384 |
| LMArena Creative Writing | 794 | 1317 |
| LMArena Multi-Turn | 753 | 1378 |
| Short-Story Creative Writing | — | 75.3% |

## FAQ

### Is Llama 13b better than Qwen3-30B-A3B?

Qwen3-30B-A3B is the stronger model overall, scoring 38.9 to 24.4 on the Noometry Index.

### Is Llama 13b or Qwen3-30B-A3B better for coding?

Qwen3-30B-A3B scores higher on coding benchmarks: 37.5 versus 21.4 in the Noometry coding category.

### How many benchmarks do Llama 13b and Qwen3-30B-A3B share?

9 benchmarks have published results for both models. Llama 13b has 21 scored results on Noometry and Qwen3-30B-A3B has 32.