Model comparison
Llama 3-8B vs Qwen Plus
Qwen Plus is the stronger model overall, scoring 37.1 to 25.5 on the Noometry Index.
Last verified . 17 shared benchmarks.
Meta
Alibaba (Qwen)Summary
- They share 17 benchmarks with published results for both. Llama 3-8B scores higher in 0 categories and Qwen Plus in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen Plus leads 27.4 to 7.8.
- The biggest single-benchmark swing is MATH Level 5: 6.1% for Llama 3-8B and 65.3% for Qwen Plus.
- Llama 3-8B has downloadable open weights; the other is API-only.
Side by side
| Llama 3-8B | Qwen Plus | |
|---|---|---|
| Provider | Meta | Alibaba (Qwen) |
| Noometry Index | 25.5 | 37.1 |
| Released | 2024-04-18 | 2024-01-25 |
| Weights | Open | Proprietary |
| Context window | — | 1M |
| Max output | — | 33K |
| Input $ / M tokens | — | $0.40 |
| Output $ / M tokens | — | $1.20 |
| Results tracked | 34 | 20 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen Plus leads
Llama 3-8B: 31.0 (#289), Qwen Plus: 38.9 (#167)
| Benchmark | Llama 3-8B | Qwen Plus |
|---|---|---|
| LMArena Coding | 1152 | 1328 |
| BigCodeBench Instruct | 31.9% | — |
| BigCodeBench Complete | 36.9% | — |
| HumanEval+ | 56.7% | — |
| MBPP+ | 54.8% | — |
Reasoning Qwen Plus leads
Llama 3-8B: 14.3 (#326), Qwen Plus: 28.4 (#107)
| Benchmark | Llama 3-8B | Qwen Plus |
|---|---|---|
| LMArena Hard Prompts | 1133 | 1317 |
| DTBench | 43.9% | 81.1% |
| Kagi LLM Benchmark | — | 63.3% |
| Chess Puzzles | 0% | — |
| LMCA | — | 24% |
| Adversarial NLI | 57.3% | — |
| Epoch Capabilities Index | 116.45 | — |
| ForecastBench | 58.6 | — |
| WinoGrande | 75.7% | — |
Math Qwen Plus leads
Llama 3-8B: 8.8 (#323), Qwen Plus: 23.3 (#271)
| Benchmark | Llama 3-8B | Qwen Plus |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 1.9% | 17.8% |
| LMArena Math | 1151 | 1326 |
| MATH Level 5 | 6.1% | 65.3% |
| FrontierMath (Feb 2025 set) | — | 1.7% |
Knowledge Qwen Plus leads
Llama 3-8B: 7.8 (#308), Qwen Plus: 27.4 (#251)
| Benchmark | Llama 3-8B | Qwen Plus |
|---|---|---|
| GPQA Diamond | 26.1% | 48.1% |
| LMArena Expert | 1113 | 1328 |
| ARC (AI2) Challenge | 82.8% | — |
| MMLU | 68.8% | — |
| OpenBookQA | 82.6% | — |
| TriviaQA | 67.7% | — |
Multilingual Qwen Plus leads
Llama 3-8B: 30.8 (#261), Qwen Plus: 45.1 (#175)
| Benchmark | Llama 3-8B | Qwen Plus |
|---|---|---|
| LMArena Non-English | 1098 | 1310 |
| LMArena Chinese | 1076 | 1347 |
| LMArena Japanese | 967 | 1251 |
| LMArena Russian | 1109 | 1323 |
| LMArena French | 1159 | — |
| LMArena German | 1104 | — |
| LMArena Korean | 1004 | — |
| LMArena Spanish | 1173 | — |
Instruction Following Qwen Plus leads
Llama 3-8B: 58.4 (#260), Qwen Plus: 68.8 (#181)
| Benchmark | Llama 3-8B | Qwen Plus |
|---|---|---|
| LMArena Instruction Following | 1127 | 1303 |
Long Context Qwen Plus leads
Llama 3-8B: 34.2 (#251), Qwen Plus: 40.3 (#158)
| Benchmark | Llama 3-8B | Qwen Plus |
|---|---|---|
| LMArena Longer Query | 1128 | 1324 |
Writing & Preference Qwen Plus leads
Llama 3-8B: 37.5 (#256), Qwen Plus: 52.2 (#176)
| Benchmark | Llama 3-8B | Qwen Plus |
|---|---|---|
| LMArena Text | 1166 | 1326 |
| LMArena Creative Writing | 1150 | 1293 |
| LMArena Multi-Turn | 1152 | 1336 |
Frequently asked questions
Is Llama 3-8B better than Qwen Plus?
Qwen Plus is the stronger model overall, scoring 37.1 to 25.5 on the Noometry Index.
Is Llama 3-8B or Qwen Plus better for coding?
Qwen Plus scores higher on coding benchmarks: 38.9 versus 31.0 in the Noometry coding category.
How many benchmarks do Llama 3-8B and Qwen Plus share?
17 benchmarks have published results for both models. Llama 3-8B has 34 scored results on Noometry and Qwen Plus has 20.