Model comparison
Llama 3.1-8B vs Qwen3-30B-A3B
Qwen3-30B-A3B is the stronger model overall, scoring 38.9 to 23.0 on the Noometry Index. Llama 3.1-8B costs 3.7× less per token, which makes it the better buy when Qwen3-30B-A3B's lead doesn't matter for your workload.
Last verified . 27 shared benchmarks.
Meta
Alibaba (Qwen)Summary
- They share 27 benchmarks with published results for both. Llama 3.1-8B scores higher in 1 category and Qwen3-30B-A3B in 8 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen3-30B-A3B leads 41.8 to 8.0.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 1.7% for Llama 3.1-8B and 70.3% for Qwen3-30B-A3B.
- Llama 3.1-8B is cheaper at $0.05 / $0.08 per million input/output tokens, against $0.12 / $0.50 for Qwen3-30B-A3B.
- Llama 3.1-8B accepts more context: 128K tokens versus 41K.
Side by side
| Llama 3.1-8B | Qwen3-30B-A3B | |
|---|---|---|
| Provider | Meta | Alibaba (Qwen) |
| Noometry Index | 23.0 | 38.9 |
| Released | 2024-07-23 | 2025-04-28 |
| Weights | Open | Open |
| Context window | 128K | 41K |
| Max output | 4K | 16K |
| Input $ / M tokens | $0.05 | $0.12 |
| Output $ / M tokens | $0.08 | $0.50 |
| Results tracked | 43 | 32 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3-30B-A3B leads
Llama 3.1-8B: 20.2 (#340), Qwen3-30B-A3B: 37.5 (#194)
| Benchmark | Llama 3.1-8B | Qwen3-30B-A3B |
|---|---|---|
| SciCode | 13.2% | 33.3% |
| WeirdML | 1.7% | 29.8% |
| LMArena Coding | 1195 | 1416 |
| BigCodeBench Instruct | 32.8% | — |
| BigCodeBench Complete | 40.5% | — |
| HumanEval+ | 62.8% | — |
| MBPP+ | 55.6% | — |
Agentic & Tool Use Qwen3-30B-A3B leads
Llama 3.1-8B: 22.5 (#131), Qwen3-30B-A3B: 29.8 (#82)
| Benchmark | Llama 3.1-8B | Qwen3-30B-A3B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 25.8% | 41.4% |
| BALROG | 15.1% | — |
Reasoning Qwen3-30B-A3B leads
Llama 3.1-8B: 14.9 (#321), Qwen3-30B-A3B: 22.2 (#204)
| Benchmark | Llama 3.1-8B | Qwen3-30B-A3B |
|---|---|---|
| CritPt | 0% | 0.3% |
| Chess Puzzles | 0% | 8% |
| LMArena Hard Prompts | 1175 | 1398 |
| DTBench | 50.9% | 69.3% |
| LMCA | 5.4% | 22.4% |
| Epoch Capabilities Index | 116.57 | 139.63 |
| Kagi LLM Benchmark | — | 54.9% |
| PIQA | 81.2% | — |
Math Qwen3-30B-A3B leads
Llama 3.1-8B: 10.2 (#317), Qwen3-30B-A3B: 37.4 (#157)
| Benchmark | Llama 3.1-8B | Qwen3-30B-A3B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 1.7% | 70.3% |
| LMArena Math | 1179 | 1394 |
| MathArena Final-Answer Competitions | — | 47.8% |
| Omni-MATH | 13.7% | — |
| MATH Level 5 | 22.9% | — |
| GSM8K | 82.4% | — |
Knowledge Qwen3-30B-A3B leads
Llama 3.1-8B: 8.0 (#307), Qwen3-30B-A3B: 41.8 (#105)
| Benchmark | Llama 3.1-8B | Qwen3-30B-A3B |
|---|---|---|
| GPQA Diamond | 27% | 70.1% |
| LMArena Expert | 1144 | 1396 |
| MMLU-Pro | 40.6% | — |
| Confabulations | — | 12.3% |
| GPQA (HELM) | 24.7% | — |
| BoolQ | 82.8% | — |
| MMLU | 56.1% | — |
Multilingual Qwen3-30B-A3B leads
Llama 3.1-8B: 34.0 (#249), Qwen3-30B-A3B: 49.5 (#132)
| Benchmark | Llama 3.1-8B | Qwen3-30B-A3B |
|---|---|---|
| LMArena Non-English | 1148 | 1372 |
| LMArena Chinese | 1151 | 1433 |
| LMArena French | 1177 | 1418 |
| LMArena German | 1144 | 1380 |
| LMArena Japanese | 1061 | 1337 |
| LMArena Korean | 1053 | 1331 |
| LMArena Russian | 1158 | 1370 |
| LMArena Spanish | 1169 | 1404 |
Instruction Following Qwen3-30B-A3B leads
Llama 3.1-8B: 58.9 (#258), Qwen3-30B-A3B: 72.0 (#142)
| Benchmark | Llama 3.1-8B | Qwen3-30B-A3B |
|---|---|---|
| LMArena Instruction Following | 1159 | 1363 |
| IFEval | 74.3% | — |
Long Context Llama 3.1-8B leads
Llama 3.1-8B: 35.8 (#238), Qwen3-30B-A3B: 31.0 (#283)
| Benchmark | Llama 3.1-8B | Qwen3-30B-A3B |
|---|---|---|
| LMArena Longer Query | 1182 | 1379 |
| Fiction.LiveBench | — | 40.6% |
Writing & Preference Qwen3-30B-A3B leads
Llama 3.1-8B: 29.7 (#290), Qwen3-30B-A3B: 55.6 (#143)
| Benchmark | Llama 3.1-8B | Qwen3-30B-A3B |
|---|---|---|
| LMArena Text | 1187 | 1384 |
| LMArena Creative Writing | 1154 | 1317 |
| LMArena Multi-Turn | 1172 | 1378 |
| Short-Story Creative Writing | — | 75.3% |
| EQ-Bench Creative Writing | 713 | — |
| WildBench | 68.7% | — |
Frequently asked questions
Is Llama 3.1-8B better than Qwen3-30B-A3B?
Qwen3-30B-A3B is the stronger model overall, scoring 38.9 to 23.0 on the Noometry Index. Llama 3.1-8B costs 3.7× less per token, which makes it the better buy when Qwen3-30B-A3B's lead doesn't matter for your workload.
Which is cheaper, Llama 3.1-8B or Qwen3-30B-A3B?
Llama 3.1-8B is cheaper. It lists at $0.05 per million input tokens and $0.08 per million output tokens; Qwen3-30B-A3B lists at $0.12 and $0.50.
Is Llama 3.1-8B or Qwen3-30B-A3B better for coding?
Qwen3-30B-A3B scores higher on coding benchmarks: 37.5 versus 20.2 in the Noometry coding category.
Which has the bigger context window?
Llama 3.1-8B does, with 128K tokens against 41K.
How many benchmarks do Llama 3.1-8B and Qwen3-30B-A3B share?
27 benchmarks have published results for both models. Llama 3.1-8B has 43 scored results on Noometry and Qwen3-30B-A3B has 32.