Model comparison
Llama 3-8B vs Qwen2.5 7B Instruct
Qwen2.5 7B Instruct is the stronger model overall, scoring 29.0 to 25.5 on the Noometry Index.
Last verified . 8 shared benchmarks.
Meta
Alibaba (Qwen)Summary
- They share 8 benchmarks with published results for both. Llama 3-8B scores higher in 0 categories and Qwen2.5 7B Instruct in 6 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Qwen2.5 7B Instruct leads 48.8 to 37.5.
- The biggest single-benchmark swing is GPQA Diamond: 26.1% for Llama 3-8B and 35.5% for Qwen2.5 7B Instruct.
Side by side
| Llama 3-8B | Qwen2.5 7B Instruct | |
|---|---|---|
| Provider | Meta | Alibaba (Qwen) |
| Noometry Index | 25.5 | 29.0 |
| Released | 2024-04-18 | 2024-09 |
| Weights | Open | Open |
| Context window | — | 131K |
| Max output | — | 8K |
| Input $ / M tokens | — | $0.17 |
| Output $ / M tokens | — | $0.70 |
| Results tracked | 34 | 15 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen2.5 7B Instruct leads
Llama 3-8B: 31.0 (#289), Qwen2.5 7B Instruct: 36.5 (#208)
| Benchmark | Llama 3-8B | Qwen2.5 7B Instruct |
|---|---|---|
| BigCodeBench Instruct | 31.9% | 37.6% |
| BigCodeBench Complete | 36.9% | 46.1% |
| LMArena Coding | 1152 | — |
| HumanEval+ | 56.7% | — |
| MBPP+ | 54.8% | — |
Agentic & Tool Use Not comparable
Llama 3-8B: —, Qwen2.5 7B Instruct: 23.8 (#124)
| Benchmark | Llama 3-8B | Qwen2.5 7B Instruct |
|---|---|---|
| BALROG | — | 7.8% |
Reasoning Too close to call
Llama 3-8B: 14.3 (#326), Qwen2.5 7B Instruct: 14.8 (#322)
| Benchmark | Llama 3-8B | Qwen2.5 7B Instruct |
|---|---|---|
| Chess Puzzles | 0% | 0% |
| DTBench | 43.9% | 47.7% |
| Epoch Capabilities Index | 116.45 | 118.51 |
| LMArena Hard Prompts | 1133 | — |
| LMCA | — | 6.4% |
| Adversarial NLI | 57.3% | — |
| ForecastBench | 58.6 | — |
| WinoGrande | 75.7% | — |
Math Qwen2.5 7B Instruct leads
Llama 3-8B: 8.8 (#323), Qwen2.5 7B Instruct: 12.6 (#306)
| Benchmark | Llama 3-8B | Qwen2.5 7B Instruct |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 1.9% | 2.5% |
| Omni-MATH | — | 29.4% |
| LMArena Math | 1151 | — |
| MATH Level 5 | 6.1% | — |
Knowledge Qwen2.5 7B Instruct leads
Llama 3-8B: 7.8 (#308), Qwen2.5 7B Instruct: 17.0 (#286)
| Benchmark | Llama 3-8B | Qwen2.5 7B Instruct |
|---|---|---|
| GPQA Diamond | 26.1% | 35.5% |
| MMLU | 68.8% | 72.9% |
| MMLU-Pro | — | 53.9% |
| GPQA (HELM) | — | 34.1% |
| LMArena Expert | 1113 | — |
| ARC (AI2) Challenge | 82.8% | — |
| OpenBookQA | 82.6% | — |
| TriviaQA | 67.7% | — |
Multilingual Not comparable
Llama 3-8B: 30.8 (#261), Qwen2.5 7B Instruct: —
| Benchmark | Llama 3-8B | Qwen2.5 7B Instruct |
|---|---|---|
| LMArena Non-English | 1098 | — |
| LMArena Chinese | 1076 | — |
| LMArena French | 1159 | — |
| LMArena German | 1104 | — |
| LMArena Japanese | 967 | — |
| LMArena Korean | 1004 | — |
| LMArena Russian | 1109 | — |
| LMArena Spanish | 1173 | — |
Instruction Following Qwen2.5 7B Instruct leads
Llama 3-8B: 58.4 (#260), Qwen2.5 7B Instruct: 63.2 (#231)
| Benchmark | Llama 3-8B | Qwen2.5 7B Instruct |
|---|---|---|
| IFEval | — | 74.1% |
| LMArena Instruction Following | 1127 | — |
Long Context Not comparable
Llama 3-8B: 34.2 (#251), Qwen2.5 7B Instruct: —
| Benchmark | Llama 3-8B | Qwen2.5 7B Instruct |
|---|---|---|
| LMArena Longer Query | 1128 | — |
Writing & Preference Qwen2.5 7B Instruct leads
Llama 3-8B: 37.5 (#256), Qwen2.5 7B Instruct: 48.8 (#195)
| Benchmark | Llama 3-8B | Qwen2.5 7B Instruct |
|---|---|---|
| LMArena Text | 1166 | — |
| LMArena Creative Writing | 1150 | — |
| WildBench | — | 73.1% |
| LMArena Multi-Turn | 1152 | — |
Frequently asked questions
Is Llama 3-8B better than Qwen2.5 7B Instruct?
Qwen2.5 7B Instruct is the stronger model overall, scoring 29.0 to 25.5 on the Noometry Index.
Is Llama 3-8B or Qwen2.5 7B Instruct better for coding?
Qwen2.5 7B Instruct scores higher on coding benchmarks: 36.5 versus 31.0 in the Noometry coding category.
How many benchmarks do Llama 3-8B and Qwen2.5 7B Instruct share?
8 benchmarks have published results for both models. Llama 3-8B has 34 scored results on Noometry and Qwen2.5 7B Instruct has 15.