Model comparison
Llama 3-70B vs Qwen2.5 7B Instruct
Llama 3-70B and Qwen2.5 7B Instruct score almost the same on the Noometry Index (28.8 vs 29.0), so choose on price, context window or the category you care about most.
Last verified . 7 shared benchmarks.
Meta
Alibaba (Qwen)Summary
- They share 7 benchmarks with published results for both. Llama 3-70B scores higher in 3 categories and Qwen2.5 7B Instruct in 4 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Qwen2.5 7B Instruct leads 48.8 to 42.8.
- The biggest single-benchmark swing is BigCodeBench Complete: 54.5% for Llama 3-70B and 46.1% for Qwen2.5 7B Instruct.
Side by side
| Llama 3-70B | Qwen2.5 7B Instruct | |
|---|---|---|
| Provider | Meta | Alibaba (Qwen) |
| Noometry Index | 28.8 | 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 | 31 | 15 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Llama 3-70B: 35.8 (#218), Qwen2.5 7B Instruct: 36.5 (#208)
| Benchmark | Llama 3-70B | Qwen2.5 7B Instruct |
|---|---|---|
| BigCodeBench Instruct | 43.6% | 37.6% |
| BigCodeBench Complete | 54.5% | 46.1% |
| LMArena Coding | 1206 | — |
| HumanEval+ | 72% | — |
| MBPP+ | 69% | — |
Agentic & Tool Use Qwen2.5 7B Instruct leads
Llama 3-70B: 21.1 (#139), Qwen2.5 7B Instruct: 23.8 (#124)
Reasoning Llama 3-70B leads
Llama 3-70B: 18.0 (#288), Qwen2.5 7B Instruct: 14.8 (#322)
| Benchmark | Llama 3-70B | Qwen2.5 7B Instruct |
|---|---|---|
| DTBench | 54.2% | 47.7% |
| Epoch Capabilities Index | 122.93 | 118.51 |
| Kagi LLM Benchmark | 35.1% | — |
| Chess Puzzles | — | 0% |
| LMArena Hard Prompts | 1195 | — |
| LMCA | — | 6.4% |
| ForecastBench | 57.1 | — |
| WinoGrande | 83.5% | — |
Math Too close to call
Llama 3-70B: 12.8 (#305), Qwen2.5 7B Instruct: 12.6 (#306)
| Benchmark | Llama 3-70B | Qwen2.5 7B Instruct |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 4.3% | 2.5% |
| Omni-MATH | — | 29.4% |
| LMArena Math | 1218 | — |
| MATH Level 5 | 22.6% | — |
Knowledge Llama 3-70B leads
Llama 3-70B: 20.8 (#277), Qwen2.5 7B Instruct: 17.0 (#286)
| Benchmark | Llama 3-70B | Qwen2.5 7B Instruct |
|---|---|---|
| GPQA Diamond | 40.6% | 35.5% |
| MMLU | 79.3% | 72.9% |
| MMLU-Pro | — | 53.9% |
| GPQA (HELM) | — | 34.1% |
| LMArena Expert | 1149 | — |
Multilingual Not comparable
Llama 3-70B: 33.6 (#251), Qwen2.5 7B Instruct: —
| Benchmark | Llama 3-70B | Qwen2.5 7B Instruct |
|---|---|---|
| LMArena Non-English | 1142 | — |
| LMArena Chinese | 1114 | — |
| LMArena French | 1232 | — |
| LMArena German | 1169 | — |
| LMArena Japanese | 1017 | — |
| LMArena Korean | 1017 | — |
| LMArena Russian | 1159 | — |
| LMArena Spanish | 1241 | — |
Instruction Following Too close to call
Llama 3-70B: 62.5 (#238), Qwen2.5 7B Instruct: 63.2 (#231)
| Benchmark | Llama 3-70B | Qwen2.5 7B Instruct |
|---|---|---|
| IFEval | — | 74.1% |
| LMArena Instruction Following | 1194 | — |
Long Context Not comparable
Llama 3-70B: 35.6 (#240), Qwen2.5 7B Instruct: —
| Benchmark | Llama 3-70B | Qwen2.5 7B Instruct |
|---|---|---|
| LMArena Longer Query | 1174 | — |
Writing & Preference Qwen2.5 7B Instruct leads
Llama 3-70B: 42.8 (#231), Qwen2.5 7B Instruct: 48.8 (#195)
| Benchmark | Llama 3-70B | Qwen2.5 7B Instruct |
|---|---|---|
| LMArena Text | 1221 | — |
| LMArena Creative Writing | 1210 | — |
| WildBench | — | 73.1% |
| LMArena Multi-Turn | 1223 | — |
Frequently asked questions
Is Llama 3-70B better than Qwen2.5 7B Instruct?
Llama 3-70B and Qwen2.5 7B Instruct score almost the same on the Noometry Index (28.8 vs 29.0), so choose on price, context window or the category you care about most.
Is Llama 3-70B or Qwen2.5 7B Instruct better for coding?
They score almost the same on coding (35.8 vs 36.5); test both on your own repository before choosing.
How many benchmarks do Llama 3-70B and Qwen2.5 7B Instruct share?
7 benchmarks have published results for both models. Llama 3-70B has 31 scored results on Noometry and Qwen2.5 7B Instruct has 15.