Model comparison
Llama 3.1-8B vs Qwen Plus
Qwen Plus is the stronger model overall, scoring 37.1 to 23.0 on the Noometry Index. Llama 3.1-8B costs 10× less per token, which makes it the better buy when Qwen Plus's lead doesn't matter for your workload.
Last verified . 18 shared benchmarks.
Meta
Alibaba (Qwen)Summary
- They share 18 benchmarks with published results for both. Llama 3.1-8B scores higher in 0 categories and Qwen Plus in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Qwen Plus leads 52.2 to 29.7.
- The biggest single-benchmark swing is MATH Level 5: 22.9% for Llama 3.1-8B and 65.3% for Qwen Plus.
- Llama 3.1-8B is cheaper at $0.05 / $0.08 per million input/output tokens, against $0.40 / $1.20 for Qwen Plus.
- Qwen Plus accepts more context: 1M tokens versus 128K.
- Llama 3.1-8B has downloadable open weights; the other is API-only.
Side by side
| Llama 3.1-8B | Qwen Plus | |
|---|---|---|
| Provider | Meta | Alibaba (Qwen) |
| Noometry Index | 23.0 | 37.1 |
| Released | 2024-07-23 | 2024-01-25 |
| Weights | Open | Proprietary |
| Context window | 128K | 1M |
| Max output | 4K | 33K |
| Input $ / M tokens | $0.05 | $0.40 |
| Output $ / M tokens | $0.08 | $1.20 |
| Results tracked | 43 | 20 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen Plus leads
Llama 3.1-8B: 20.2 (#340), Qwen Plus: 38.9 (#167)
| Benchmark | Llama 3.1-8B | Qwen Plus |
|---|---|---|
| LMArena Coding | 1195 | 1328 |
| SciCode | 13.2% | — |
| WeirdML | 1.7% | — |
| BigCodeBench Instruct | 32.8% | — |
| BigCodeBench Complete | 40.5% | — |
| HumanEval+ | 62.8% | — |
| MBPP+ | 55.6% | — |
Agentic & Tool Use Not comparable
Llama 3.1-8B: 22.5 (#131), Qwen Plus: —
| Benchmark | Llama 3.1-8B | Qwen Plus |
|---|---|---|
| Berkeley Function Calling Leaderboard | 25.8% | — |
| BALROG | 15.1% | — |
Reasoning Qwen Plus leads
Llama 3.1-8B: 14.9 (#321), Qwen Plus: 28.4 (#107)
| Benchmark | Llama 3.1-8B | Qwen Plus |
|---|---|---|
| LMArena Hard Prompts | 1175 | 1317 |
| DTBench | 50.9% | 81.1% |
| LMCA | 5.4% | 24% |
| Kagi LLM Benchmark | — | 63.3% |
| CritPt | 0% | — |
| Chess Puzzles | 0% | — |
| Epoch Capabilities Index | 116.57 | — |
| PIQA | 81.2% | — |
Math Qwen Plus leads
Llama 3.1-8B: 10.2 (#317), Qwen Plus: 23.3 (#271)
| Benchmark | Llama 3.1-8B | Qwen Plus |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 1.7% | 17.8% |
| LMArena Math | 1179 | 1326 |
| MATH Level 5 | 22.9% | 65.3% |
| Omni-MATH | 13.7% | — |
| FrontierMath (Feb 2025 set) | — | 1.7% |
| GSM8K | 82.4% | — |
Knowledge Qwen Plus leads
Llama 3.1-8B: 8.0 (#307), Qwen Plus: 27.4 (#251)
| Benchmark | Llama 3.1-8B | Qwen Plus |
|---|---|---|
| GPQA Diamond | 27% | 48.1% |
| LMArena Expert | 1144 | 1328 |
| MMLU-Pro | 40.6% | — |
| GPQA (HELM) | 24.7% | — |
| BoolQ | 82.8% | — |
| MMLU | 56.1% | — |
Multilingual Qwen Plus leads
Llama 3.1-8B: 34.0 (#249), Qwen Plus: 45.1 (#175)
| Benchmark | Llama 3.1-8B | Qwen Plus |
|---|---|---|
| LMArena Non-English | 1148 | 1310 |
| LMArena Chinese | 1151 | 1347 |
| LMArena Japanese | 1061 | 1251 |
| LMArena Russian | 1158 | 1323 |
| LMArena French | 1177 | — |
| LMArena German | 1144 | — |
| LMArena Korean | 1053 | — |
| LMArena Spanish | 1169 | — |
Instruction Following Qwen Plus leads
Llama 3.1-8B: 58.9 (#258), Qwen Plus: 68.8 (#181)
| Benchmark | Llama 3.1-8B | Qwen Plus |
|---|---|---|
| LMArena Instruction Following | 1159 | 1303 |
| IFEval | 74.3% | — |
Long Context Qwen Plus leads
Llama 3.1-8B: 35.8 (#238), Qwen Plus: 40.3 (#158)
| Benchmark | Llama 3.1-8B | Qwen Plus |
|---|---|---|
| LMArena Longer Query | 1182 | 1324 |
Writing & Preference Qwen Plus leads
Llama 3.1-8B: 29.7 (#290), Qwen Plus: 52.2 (#176)
| Benchmark | Llama 3.1-8B | Qwen Plus |
|---|---|---|
| LMArena Text | 1187 | 1326 |
| LMArena Creative Writing | 1154 | 1293 |
| LMArena Multi-Turn | 1172 | 1336 |
| EQ-Bench Creative Writing | 713 | — |
| WildBench | 68.7% | — |
Frequently asked questions
Is Llama 3.1-8B better than Qwen Plus?
Qwen Plus is the stronger model overall, scoring 37.1 to 23.0 on the Noometry Index. Llama 3.1-8B costs 10× less per token, which makes it the better buy when Qwen Plus's lead doesn't matter for your workload.
Which is cheaper, Llama 3.1-8B or Qwen Plus?
Llama 3.1-8B is cheaper. It lists at $0.05 per million input tokens and $0.08 per million output tokens; Qwen Plus lists at $0.40 and $1.20.
Is Llama 3.1-8B or Qwen Plus better for coding?
Qwen Plus scores higher on coding benchmarks: 38.9 versus 20.2 in the Noometry coding category.
Which has the bigger context window?
Qwen Plus does, with 1M tokens against 128K.
How many benchmarks do Llama 3.1-8B and Qwen Plus share?
18 benchmarks have published results for both models. Llama 3.1-8B has 43 scored results on Noometry and Qwen Plus has 20.