Model comparison
Llama 3.1-70B vs Qwen3-30B-A3B
Qwen3-30B-A3B is the stronger model overall, scoring 38.9 to 29.6 on the Noometry Index.
Last verified . 23 shared benchmarks.
Meta
Alibaba (Qwen)Summary
- They share 23 benchmarks with published results for both. Llama 3.1-70B scores higher in 1 category and Qwen3-30B-A3B in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3-30B-A3B leads 37.4 to 13.5.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 3.6% for Llama 3.1-70B and 70.3% for Qwen3-30B-A3B.
- Qwen3-30B-A3B is cheaper at $0.12 / $0.50 per million input/output tokens, against $0.40 / $0.40 for Llama 3.1-70B.
- Llama 3.1-70B accepts more context: 128K tokens versus 41K.
Side by side
| Llama 3.1-70B | Qwen3-30B-A3B | |
|---|---|---|
| Provider | Meta | Alibaba (Qwen) |
| Noometry Index | 29.6 | 38.9 |
| Released | 2024-07-23 | 2025-04-28 |
| Weights | Open | Open |
| Context window | 128K | 41K |
| Max output | 4K | 16K |
| Input $ / M tokens | $0.40 | $0.12 |
| Output $ / M tokens | $0.40 | $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 3.1-70B: 30.3 (#296), Qwen3-30B-A3B: 37.5 (#194)
| Benchmark | Llama 3.1-70B | Qwen3-30B-A3B |
|---|---|---|
| WeirdML | 9% | 29.8% |
| LMArena Coding | 1260 | 1416 |
| SciCode | — | 33.3% |
| BigCodeBench Instruct | 46.1% | — |
| BigCodeBench Complete | 54.8% | — |
Agentic & Tool Use Qwen3-30B-A3B leads
Llama 3.1-70B: 25.1 (#112), Qwen3-30B-A3B: 29.8 (#82)
| Benchmark | Llama 3.1-70B | Qwen3-30B-A3B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 41.4% |
| TheAgentCompany | 6.9% | — |
| BALROG | 27.9% | — |
Reasoning Too close to call
Llama 3.1-70B: 21.6 (#220), Qwen3-30B-A3B: 22.2 (#204)
| Benchmark | Llama 3.1-70B | Qwen3-30B-A3B |
|---|---|---|
| LMArena Hard Prompts | 1241 | 1398 |
| DTBench | 60% | 69.3% |
| LMCA | 14.8% | 22.4% |
| Epoch Capabilities Index | 125.92 | 139.63 |
| Kagi LLM Benchmark | — | 54.9% |
| CritPt | — | 0.3% |
| Chess Puzzles | — | 8% |
Math Qwen3-30B-A3B leads
Llama 3.1-70B: 13.5 (#304), Qwen3-30B-A3B: 37.4 (#157)
| Benchmark | Llama 3.1-70B | Qwen3-30B-A3B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 3.6% | 70.3% |
| LMArena Math | 1252 | 1394 |
| MathArena Final-Answer Competitions | — | 47.8% |
| Omni-MATH | 21% | — |
| MATH Level 5 | 36.7% | — |
Knowledge Qwen3-30B-A3B leads
Llama 3.1-70B: 24.2 (#269), Qwen3-30B-A3B: 41.8 (#105)
| Benchmark | Llama 3.1-70B | Qwen3-30B-A3B |
|---|---|---|
| GPQA Diamond | 44.2% | 70.1% |
| LMArena Expert | 1209 | 1396 |
| MMLU-Pro | 65.3% | — |
| Confabulations | — | 12.3% |
| GPQA (HELM) | 42.6% | — |
| MMLU | 80.1% | — |
Multilingual Qwen3-30B-A3B leads
Llama 3.1-70B: 38.8 (#225), Qwen3-30B-A3B: 49.5 (#132)
| Benchmark | Llama 3.1-70B | Qwen3-30B-A3B |
|---|---|---|
| LMArena Non-English | 1219 | 1372 |
| LMArena Chinese | 1215 | 1433 |
| LMArena French | 1261 | 1418 |
| LMArena German | 1222 | 1380 |
| LMArena Japanese | 1132 | 1337 |
| LMArena Korean | 1140 | 1331 |
| LMArena Russian | 1234 | 1370 |
| LMArena Spanish | 1253 | 1404 |
Instruction Following Qwen3-30B-A3B leads
Llama 3.1-70B: 65.3 (#223), Qwen3-30B-A3B: 72.0 (#142)
| Benchmark | Llama 3.1-70B | Qwen3-30B-A3B |
|---|---|---|
| LMArena Instruction Following | 1231 | 1363 |
| IFEval | 82.1% | — |
Long Context Llama 3.1-70B leads
Llama 3.1-70B: 37.6 (#214), Qwen3-30B-A3B: 31.0 (#283)
| Benchmark | Llama 3.1-70B | Qwen3-30B-A3B |
|---|---|---|
| LMArena Longer Query | 1241 | 1379 |
| Fiction.LiveBench | — | 40.6% |
Writing & Preference Qwen3-30B-A3B leads
Llama 3.1-70B: 35.4 (#267), Qwen3-30B-A3B: 55.6 (#143)
| Benchmark | Llama 3.1-70B | Qwen3-30B-A3B |
|---|---|---|
| LMArena Text | 1261 | 1384 |
| LMArena Creative Writing | 1232 | 1317 |
| LMArena Multi-Turn | 1256 | 1378 |
| Short-Story Creative Writing | — | 75.3% |
| EQ-Bench Creative Writing | 784 | — |
| WildBench | 75.8% | — |
Frequently asked questions
Is Llama 3.1-70B better than Qwen3-30B-A3B?
Qwen3-30B-A3B is the stronger model overall, scoring 38.9 to 29.6 on the Noometry Index.
Which is cheaper, Llama 3.1-70B or Qwen3-30B-A3B?
Qwen3-30B-A3B is cheaper. It lists at $0.12 per million input tokens and $0.50 per million output tokens; Llama 3.1-70B lists at $0.40 and $0.40.
Is Llama 3.1-70B or Qwen3-30B-A3B better for coding?
Qwen3-30B-A3B scores higher on coding benchmarks: 37.5 versus 30.3 in the Noometry coding category.
Which has the bigger context window?
Llama 3.1-70B does, with 128K tokens against 41K.
How many benchmarks do Llama 3.1-70B and Qwen3-30B-A3B share?
23 benchmarks have published results for both models. Llama 3.1-70B has 35 scored results on Noometry and Qwen3-30B-A3B has 32.