Model comparison
Llama 3-8B vs Qwen Max
Qwen Max is the stronger model overall, scoring 34.7 to 25.5 on the Noometry Index.
Last verified . 20 shared benchmarks.
Meta
Alibaba (Qwen)Summary
- They share 20 benchmarks with published results for both. Llama 3-8B scores higher in 1 category and Qwen Max in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen Max leads 30.3 to 7.8.
- The biggest single-benchmark swing is MATH Level 5: 6.1% for Llama 3-8B and 67.2% for Qwen Max.
- Llama 3-8B has downloadable open weights; the other is API-only.
Side by side
| Llama 3-8B | Qwen Max | |
|---|---|---|
| Provider | Meta | Alibaba (Qwen) |
| Noometry Index | 25.5 | 34.7 |
| Released | 2024-04-18 | 2024-04-03 |
| Weights | Open | Proprietary |
| Context window | — | 33K |
| Max output | — | 8K |
| Input $ / M tokens | — | $1.60 |
| Output $ / M tokens | — | $6.40 |
| Results tracked | 34 | 23 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Llama 3-8B: 31.0 (#289), Qwen Max: 30.7 (#292)
| Benchmark | Llama 3-8B | Qwen Max |
|---|---|---|
| LMArena Coding | 1152 | 1288 |
| Aider Polyglot | — | 21.8% |
| BigCodeBench Instruct | 31.9% | — |
| BigCodeBench Complete | 36.9% | — |
| HumanEval+ | 56.7% | — |
| MBPP+ | 54.8% | — |
Reasoning Qwen Max leads
Llama 3-8B: 14.3 (#326), Qwen Max: 25.1 (#151)
| Benchmark | Llama 3-8B | Qwen Max |
|---|---|---|
| LMArena Hard Prompts | 1133 | 1269 |
| Chess Puzzles | 0% | — |
| DTBench | 43.9% | — |
| Adversarial NLI | 57.3% | — |
| Epoch Capabilities Index | 116.45 | — |
| ForecastBench | 58.6 | — |
| WinoGrande | 75.7% | — |
Math Qwen Max leads
Llama 3-8B: 8.8 (#323), Qwen Max: 22.3 (#276)
| Benchmark | Llama 3-8B | Qwen Max |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 1.9% | 16.1% |
| LMArena Math | 1151 | 1275 |
| MATH Level 5 | 6.1% | 67.2% |
| FrontierMath (Feb 2025 set) | — | 1% |
Knowledge Qwen Max leads
Llama 3-8B: 7.8 (#308), Qwen Max: 30.3 (#228)
| Benchmark | Llama 3-8B | Qwen Max |
|---|---|---|
| GPQA Diamond | 26.1% | 56.1% |
| LMArena Expert | 1113 | 1248 |
| ARC (AI2) Challenge | 82.8% | — |
| MMLU | 68.8% | — |
| OpenBookQA | 82.6% | — |
| TriviaQA | 67.7% | — |
Multilingual Qwen Max leads
Llama 3-8B: 30.8 (#261), Qwen Max: 41.8 (#202)
| Benchmark | Llama 3-8B | Qwen Max |
|---|---|---|
| LMArena Non-English | 1098 | 1263 |
| LMArena Chinese | 1076 | 1254 |
| LMArena French | 1159 | 1330 |
| LMArena German | 1104 | 1254 |
| LMArena Japanese | 967 | 1205 |
| LMArena Korean | 1004 | 1142 |
| LMArena Russian | 1109 | 1274 |
| LMArena Spanish | 1173 | 1290 |
Instruction Following Qwen Max leads
Llama 3-8B: 58.4 (#260), Qwen Max: 66.5 (#208)
| Benchmark | Llama 3-8B | Qwen Max |
|---|---|---|
| LMArena Instruction Following | 1127 | 1262 |
Long Context Qwen Max leads
Llama 3-8B: 34.2 (#251), Qwen Max: 39.4 (#180)
| Benchmark | Llama 3-8B | Qwen Max |
|---|---|---|
| LMArena Longer Query | 1128 | 1288 |
| Fiction.LiveBench | — | 66.7% |
Writing & Preference Qwen Max leads
Llama 3-8B: 37.5 (#256), Qwen Max: 47.8 (#205)
| Benchmark | Llama 3-8B | Qwen Max |
|---|---|---|
| LMArena Text | 1166 | 1282 |
| LMArena Creative Writing | 1150 | 1248 |
| LMArena Multi-Turn | 1152 | 1277 |
Frequently asked questions
Is Llama 3-8B better than Qwen Max?
Qwen Max is the stronger model overall, scoring 34.7 to 25.5 on the Noometry Index.
Is Llama 3-8B or Qwen Max better for coding?
They score almost the same on coding (31.0 vs 30.7); test both on your own repository before choosing.
How many benchmarks do Llama 3-8B and Qwen Max share?
20 benchmarks have published results for both models. Llama 3-8B has 34 scored results on Noometry and Qwen Max has 23.