Model comparison
Llama 2-70B vs Qwen3-30B-A3B
Qwen3-30B-A3B is the stronger model overall, scoring 38.5 to 24.1 on the Noometry Index.
Last verified . 21 shared benchmarks.
Meta
Alibaba (Qwen)Summary
- They share 21 benchmarks with published results for both. Llama 2-70B scores higher in 1 category and Qwen3-30B-A3B in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen3-30B-A3B leads 41.7 to 7.4.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 0% for Llama 2-70B and 70.3% for Qwen3-30B-A3B.
Side by side
| Llama 2-70B | Qwen3-30B-A3B | |
|---|---|---|
| Provider | Meta | Alibaba (Qwen) |
| Noometry Index | 24.1 | 38.5 |
| Released | 2023-07-18 | 2025-04-28 |
| Weights | Open | Open |
| Context window | — | 41K |
| Max output | — | 16K |
| Input $ / M tokens | — | $0.12 |
| Output $ / M tokens | — | $0.50 |
| Results tracked | 35 | 32 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3-30B-A3B leads
Llama 2-70B: 30.8 (#281), Qwen3-30B-A3B: 37.0 (#188)
| Benchmark | Llama 2-70B | Qwen3-30B-A3B |
|---|---|---|
| LMArena Coding | 1079 | 1416 |
| SciCode | — | 33.3% |
| WeirdML | — | 29.8% |
Agentic & Tool Use Not comparable
Llama 2-70B: —, Qwen3-30B-A3B: 29.5 (#75)
| Benchmark | Llama 2-70B | Qwen3-30B-A3B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 41.4% |
Reasoning Qwen3-30B-A3B leads
Llama 2-70B: 13.7 (#324), Qwen3-30B-A3B: 21.6 (#193)
| Benchmark | Llama 2-70B | Qwen3-30B-A3B |
|---|---|---|
| LMArena Hard Prompts | 1073 | 1398 |
| DTBench | 41.6% | 69.3% |
| Epoch Capabilities Index | 113.59 | 139.63 |
| Kagi LLM Benchmark | — | 54.9% |
| CritPt | — | 0.3% |
| Chess Puzzles | — | 8% |
| LMCA | — | 22.4% |
| BIG-Bench Hard | 64.9% | — |
| CommonsenseQA 2.0 | 50% | — |
| ForecastBench | 51.4 | — |
| HellaSwag | 85.3% | — |
| LAMBADA | 78.9% | — |
| PIQA | 82.8% | — |
| WinoGrande | 80.2% | — |
Math Qwen3-30B-A3B leads
Llama 2-70B: 7.5 (#320), Qwen3-30B-A3B: 36.0 (#133)
| Benchmark | Llama 2-70B | Qwen3-30B-A3B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 0% | 70.3% |
| LMArena Math | 1091 | 1394 |
| MathArena Final-Answer Competitions | — | 47.8% |
| MATH Level 5 | 3.3% | — |
| GSM8K | 69.6% | — |
Knowledge Qwen3-30B-A3B leads
Llama 2-70B: 7.4 (#305), Qwen3-30B-A3B: 41.7 (#96)
| Benchmark | Llama 2-70B | Qwen3-30B-A3B |
|---|---|---|
| GPQA Diamond | 26.3% | 70.1% |
| LMArena Expert | 1039 | 1395 |
| Confabulations | — | 12.3% |
| ARC (AI2) Challenge | 78.3% | — |
| BoolQ | 88.6% | — |
| MMLU | 69.9% | — |
| OpenBookQA | 60.2% | — |
| TriviaQA | 87.6% | — |
Multilingual Qwen3-30B-A3B leads
Llama 2-70B: 27.9 (#269), Qwen3-30B-A3B: 49.8 (#126)
| Benchmark | Llama 2-70B | Qwen3-30B-A3B |
|---|---|---|
| LMArena Non-English | 1045 | 1372 |
| LMArena Chinese | 994 | 1434 |
| LMArena French | 1089 | 1419 |
| LMArena German | 1041 | 1379 |
| LMArena Japanese | 927 | 1338 |
| LMArena Korean | 964 | 1333 |
| LMArena Russian | 1083 | 1369 |
| LMArena Spanish | 1142 | 1403 |
Instruction Following Qwen3-30B-A3B leads
Llama 2-70B: 55.1 (#273), Qwen3-30B-A3B: 72.2 (#137)
| Benchmark | Llama 2-70B | Qwen3-30B-A3B |
|---|---|---|
| LMArena Instruction Following | 1071 | 1364 |
Long Context Llama 2-70B leads
Llama 2-70B: 32.2 (#265), Qwen3-30B-A3B: 31.0 (#278)
| Benchmark | Llama 2-70B | Qwen3-30B-A3B |
|---|---|---|
| LMArena Longer Query | 1062 | 1379 |
| Fiction.LiveBench | — | 40.6% |
Writing & Preference Qwen3-30B-A3B leads
Llama 2-70B: 32.5 (#274), Qwen3-30B-A3B: 55.9 (#138)
| Benchmark | Llama 2-70B | Qwen3-30B-A3B |
|---|---|---|
| LMArena Text | 1115 | 1384 |
| LMArena Creative Writing | 1075 | 1318 |
| LMArena Multi-Turn | 1088 | 1378 |
| Short-Story Creative Writing | — | 75.3% |
Frequently asked questions
Is Llama 2-70B better than Qwen3-30B-A3B?
Qwen3-30B-A3B is the stronger model overall, scoring 38.5 to 24.1 on the Noometry Index.
Is Llama 2-70B or Qwen3-30B-A3B better for coding?
Qwen3-30B-A3B scores higher on coding benchmarks: 37.0 versus 30.8 in the Noometry coding category.
How many benchmarks do Llama 2-70B and Qwen3-30B-A3B share?
21 benchmarks have published results for both models. Llama 2-70B has 35 scored results on Noometry and Qwen3-30B-A3B has 32.