Model comparison
Llama 3-8B vs Qwen2.5-Max
Qwen2.5-Max is the stronger model overall, scoring 40.7 to 25.5 on the Noometry Index.
Last verified . 18 shared benchmarks.
Meta
Alibaba (Qwen)Summary
- They share 18 benchmarks with published results for both. Llama 3-8B scores higher in 0 categories and Qwen2.5-Max in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen2.5-Max leads 36.9 to 8.8.
- Llama 3-8B has downloadable open weights; the other is API-only.
Side by side
| Llama 3-8B | Qwen2.5-Max | |
|---|---|---|
| Provider | Meta | Alibaba (Qwen) |
| Noometry Index | 25.5 | 40.7 |
| Released | 2024-04-18 | 2025-01-25 |
| Weights | Open | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 34 | 27 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen2.5-Max leads
Llama 3-8B: 31.0 (#289), Qwen2.5-Max: 41.8 (#117)
| Benchmark | Llama 3-8B | Qwen2.5-Max |
|---|---|---|
| LMArena Coding | 1152 | 1359 |
| BigCodeBench Instruct | 31.9% | — |
| LiveBench Coding | — | 64.4% |
| BigCodeBench Complete | 36.9% | — |
| HumanEval+ | 56.7% | — |
| MBPP+ | 54.8% | — |
Reasoning Qwen2.5-Max leads
Llama 3-8B: 14.3 (#326), Qwen2.5-Max: 25.6 (#147)
| Benchmark | Llama 3-8B | Qwen2.5-Max |
|---|---|---|
| LMArena Hard Prompts | 1133 | 1360 |
| Epoch Capabilities Index | 116.45 | 132.53 |
| Chess Puzzles | 0% | — |
| LiveBench Reasoning | — | 51.4% |
| DTBench | 43.9% | — |
| LiveBench Data Analysis | — | 67.9% |
| Adversarial NLI | 57.3% | — |
| ForecastBench | 58.6 | — |
| LiveBench | — | 62.3% |
| WinoGrande | 75.7% | — |
Math Qwen2.5-Max leads
Llama 3-8B: 8.8 (#323), Qwen2.5-Max: 36.9 (#162)
| Benchmark | Llama 3-8B | Qwen2.5-Max |
|---|---|---|
| LMArena Math | 1151 | 1369 |
| OTIS Mock AIME 2024-2025 | 1.9% | — |
| LiveBench Math | — | 58.4% |
| MATH Level 5 | 6.1% | — |
Knowledge Qwen2.5-Max leads
Llama 3-8B: 7.8 (#308), Qwen2.5-Max: 35.3 (#186)
| Benchmark | Llama 3-8B | Qwen2.5-Max |
|---|---|---|
| LMArena Expert | 1113 | 1337 |
| GPQA Diamond | 26.1% | — |
| Confabulations | — | 21.8% |
| ARC (AI2) Challenge | 82.8% | — |
| MMLU | 68.8% | — |
| OpenBookQA | 82.6% | — |
| TriviaQA | 67.7% | — |
Multilingual Qwen2.5-Max leads
Llama 3-8B: 30.8 (#261), Qwen2.5-Max: 48.1 (#146)
| Benchmark | Llama 3-8B | Qwen2.5-Max |
|---|---|---|
| LMArena Non-English | 1098 | 1352 |
| LMArena Chinese | 1076 | 1382 |
| LMArena French | 1159 | 1396 |
| LMArena German | 1104 | 1350 |
| LMArena Japanese | 967 | 1300 |
| LMArena Korean | 1004 | 1304 |
| LMArena Russian | 1109 | 1353 |
| LMArena Spanish | 1173 | 1377 |
Instruction Following Qwen2.5-Max leads
Llama 3-8B: 58.4 (#260), Qwen2.5-Max: 71.3 (#152)
| Benchmark | Llama 3-8B | Qwen2.5-Max |
|---|---|---|
| LMArena Instruction Following | 1127 | 1335 |
| LiveBench Instruction Following | — | 75.3% |
Long Context Qwen2.5-Max leads
Llama 3-8B: 34.2 (#251), Qwen2.5-Max: 41.4 (#142)
| Benchmark | Llama 3-8B | Qwen2.5-Max |
|---|---|---|
| LMArena Longer Query | 1128 | 1358 |
Writing & Preference Qwen2.5-Max leads
Llama 3-8B: 37.5 (#256), Qwen2.5-Max: 55.4 (#146)
| Benchmark | Llama 3-8B | Qwen2.5-Max |
|---|---|---|
| LMArena Text | 1166 | 1367 |
| LMArena Creative Writing | 1150 | 1339 |
| LMArena Multi-Turn | 1152 | 1364 |
| Short-Story Creative Writing | — | 72.9% |
| LiveBench Language | — | 56.3% |
Frequently asked questions
Is Llama 3-8B better than Qwen2.5-Max?
Qwen2.5-Max is the stronger model overall, scoring 40.7 to 25.5 on the Noometry Index.
Is Llama 3-8B or Qwen2.5-Max better for coding?
Qwen2.5-Max scores higher on coding benchmarks: 41.8 versus 31.0 in the Noometry coding category.
How many benchmarks do Llama 3-8B and Qwen2.5-Max share?
18 benchmarks have published results for both models. Llama 3-8B has 34 scored results on Noometry and Qwen2.5-Max has 27.