Model comparison
Llama 3.1-8B vs Qwen3 8B
Qwen3 8B is the stronger model overall, scoring 33.3 to 22.8 on the Noometry Index. Llama 3.1-8B costs 5.4× less per token, which makes it the better buy when Qwen3 8B's lead doesn't matter for your workload.
Last verified . 9 shared benchmarks.
Meta
Alibaba (Qwen)Summary
- They share 9 benchmarks with published results for both. Llama 3.1-8B scores higher in 0 categories and Qwen3 8B in 6 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen3 8B leads 36.1 to 8.0.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 1.7% for Llama 3.1-8B and 56.1% for Qwen3 8B.
- Llama 3.1-8B is cheaper at $0.05 / $0.08 per million input/output tokens, against $0.18 / $0.70 for Qwen3 8B.
- Qwen3 8B accepts more context: 131K tokens versus 128K.
Side by side
| Llama 3.1-8B | Qwen3 8B | |
|---|---|---|
| Provider | Meta | Alibaba (Qwen) |
| Noometry Index | 22.8 | 33.3 |
| Released | 2024-07-23 | 2025-04 |
| Weights | Open | Open |
| Context window | 128K | 131K |
| Max output | 4K | 8K |
| Input $ / M tokens | $0.05 | $0.18 |
| Output $ / M tokens | $0.08 | $0.70 |
| Results tracked | 43 | 11 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3 8B leads
Llama 3.1-8B: 19.9 (#335), Qwen3 8B: 33.4 (#245)
| Benchmark | Llama 3.1-8B | Qwen3 8B |
|---|---|---|
| SciCode | 13.2% | 22.6% |
| WeirdML | 1.7% | — |
| BigCodeBench Instruct | 32.8% | — |
| LMArena Coding | 1195 | — |
| BigCodeBench Complete | 40.5% | — |
| HumanEval+ | 62.8% | — |
| MBPP+ | 55.6% | — |
Agentic & Tool Use Qwen3 8B leads
Llama 3.1-8B: 22.3 (#123), Qwen3 8B: 29.9 (#71)
| Benchmark | Llama 3.1-8B | Qwen3 8B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 25.8% | 42.6% |
| BALROG | 15.1% | — |
Reasoning Qwen3 8B leads
Llama 3.1-8B: 14.5 (#316), Qwen3 8B: 16.1 (#299)
| Benchmark | Llama 3.1-8B | Qwen3 8B |
|---|---|---|
| CritPt | 0% | 0% |
| Chess Puzzles | 0% | 5% |
| DTBench | 50.9% | 59.7% |
| LMCA | 5.4% | 8.8% |
| Epoch Capabilities Index | 116.48 | 136.17 |
| LMArena Hard Prompts | 1175 | — |
| PIQA | 81.2% | — |
Math Qwen3 8B leads
Llama 3.1-8B: 9.5 (#311), Qwen3 8B: 33.3 (#176)
| Benchmark | Llama 3.1-8B | Qwen3 8B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 1.7% | 56.1% |
| Omni-MATH | 13.7% | — |
| LMArena Math | 1179 | — |
| MATH Level 5 | 22.9% | — |
| GSM8K | 82.4% | — |
Knowledge Qwen3 8B leads
Llama 3.1-8B: 8.0 (#302), Qwen3 8B: 36.1 (#164)
| Benchmark | Llama 3.1-8B | Qwen3 8B |
|---|---|---|
| GPQA Diamond | 27% | 56.8% |
| MMLU-Pro | 40.6% | — |
| Vectara Hallucination Rate | — | 4.8% |
| GPQA (HELM) | 24.7% | — |
| LMArena Expert | 1144 | — |
| BoolQ | 82.8% | — |
| MMLU | 56.1% | — |
Multilingual Not comparable
Llama 3.1-8B: 34.2 (#244), Qwen3 8B: —
| Benchmark | Llama 3.1-8B | Qwen3 8B |
|---|---|---|
| LMArena Non-English | 1148 | — |
| LMArena Chinese | 1151 | — |
| LMArena French | 1176 | — |
| LMArena German | 1144 | — |
| LMArena Japanese | 1061 | — |
| LMArena Korean | 1053 | — |
| LMArena Russian | 1158 | — |
| LMArena Spanish | 1169 | — |
Instruction Following Not comparable
Llama 3.1-8B: 59.1 (#253), Qwen3 8B: —
| Benchmark | Llama 3.1-8B | Qwen3 8B |
|---|---|---|
| IFEval | 74.3% | — |
| LMArena Instruction Following | 1159 | — |
Long Context Qwen3 8B leads
Llama 3.1-8B: 35.8 (#233), Qwen3 8B: 37.8 (#205)
| Benchmark | Llama 3.1-8B | Qwen3 8B |
|---|---|---|
| Fiction.LiveBench | — | 62.1% |
| LMArena Longer Query | 1182 | — |
Writing & Preference Not comparable
Llama 3.1-8B: 29.9 (#285), Qwen3 8B: —
| Benchmark | Llama 3.1-8B | Qwen3 8B |
|---|---|---|
| LMArena Text | 1187 | — |
| LMArena Creative Writing | 1154 | — |
| EQ-Bench Creative Writing | 713 | — |
| WildBench | 68.7% | — |
| LMArena Multi-Turn | 1172 | — |
Frequently asked questions
Is Llama 3.1-8B better than Qwen3 8B?
Qwen3 8B is the stronger model overall, scoring 33.3 to 22.8 on the Noometry Index. Llama 3.1-8B costs 5.4× less per token, which makes it the better buy when Qwen3 8B's lead doesn't matter for your workload.
Which is cheaper, Llama 3.1-8B or Qwen3 8B?
Llama 3.1-8B is cheaper. It lists at $0.05 per million input tokens and $0.08 per million output tokens; Qwen3 8B lists at $0.18 and $0.70.
Is Llama 3.1-8B or Qwen3 8B better for coding?
Qwen3 8B scores higher on coding benchmarks: 33.4 versus 19.9 in the Noometry coding category.
Which has the bigger context window?
Qwen3 8B does, with 131K tokens against 128K.
How many benchmarks do Llama 3.1-8B and Qwen3 8B share?
9 benchmarks have published results for both models. Llama 3.1-8B has 43 scored results on Noometry and Qwen3 8B has 11.