Model comparison
Llama 3.1-70B vs Qwen2.5 32B Instruct
Llama 3.1-70B and Qwen2.5 32B Instruct score almost the same on the Noometry Index (29.6 vs 30.1), so choose on price, context window or the category you care about most.
Last verified . 6 shared benchmarks.
Meta
Alibaba (Qwen)Summary
- They share 6 benchmarks with published results for both. Llama 3.1-70B scores higher in 1 category and Qwen2.5 32B Instruct in 3 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in coding, where Qwen2.5 32B Instruct leads 38.7 to 30.3.
- The biggest single-benchmark swing is MATH Level 5: 36.7% for Llama 3.1-70B and 56.1% for Qwen2.5 32B Instruct.
- Llama 3.1-70B is cheaper at $0.40 / $0.40 per million input/output tokens, against $0.70 / $2.80 for Qwen2.5 32B Instruct.
- Qwen2.5 32B Instruct accepts more context: 131K tokens versus 128K.
Side by side
| Llama 3.1-70B | Qwen2.5 32B Instruct | |
|---|---|---|
| Provider | Meta | Alibaba (Qwen) |
| Noometry Index | 29.6 | 30.1 |
| Released | 2024-07-23 | 2024-09 |
| Weights | Open | Open |
| Context window | 128K | 131K |
| Max output | 4K | 8K |
| Input $ / M tokens | $0.40 | $0.70 |
| Output $ / M tokens | $0.40 | $2.80 |
| Results tracked | 35 | 7 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen2.5 32B Instruct leads
Llama 3.1-70B: 30.3 (#296), Qwen2.5 32B Instruct: 38.7 (#169)
| Benchmark | Llama 3.1-70B | Qwen2.5 32B Instruct |
|---|---|---|
| BigCodeBench Instruct | 46.1% | 45% |
| BigCodeBench Complete | 54.8% | 52.3% |
| WeirdML | 9% | — |
| LMArena Coding | 1260 | — |
Agentic & Tool Use Not comparable
Llama 3.1-70B: 25.1 (#112), Qwen2.5 32B Instruct: —
| Benchmark | Llama 3.1-70B | Qwen2.5 32B Instruct |
|---|---|---|
| TheAgentCompany | 6.9% | — |
| BALROG | 27.9% | — |
Reasoning Llama 3.1-70B leads
Llama 3.1-70B: 21.6 (#220), Qwen2.5 32B Instruct: 19.2 (#266)
| Benchmark | Llama 3.1-70B | Qwen2.5 32B Instruct |
|---|---|---|
| Epoch Capabilities Index | 125.92 | 128.52 |
| Chess Puzzles | — | 0% |
| LMArena Hard Prompts | 1241 | — |
| DTBench | 60% | — |
| LMCA | 14.8% | — |
Math Qwen2.5 32B Instruct leads
Llama 3.1-70B: 13.5 (#304), Qwen2.5 32B Instruct: 16.2 (#296)
| Benchmark | Llama 3.1-70B | Qwen2.5 32B Instruct |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 3.6% | 7.4% |
| MATH Level 5 | 36.7% | 56.1% |
| Omni-MATH | 21% | — |
| LMArena Math | 1252 | — |
Knowledge Too close to call
Llama 3.1-70B: 24.2 (#269), Qwen2.5 32B Instruct: 24.9 (#266)
| Benchmark | Llama 3.1-70B | Qwen2.5 32B Instruct |
|---|---|---|
| GPQA Diamond | 44.2% | 46.1% |
| MMLU-Pro | 65.3% | — |
| GPQA (HELM) | 42.6% | — |
| LMArena Expert | 1209 | — |
| MMLU | 80.1% | — |
Multilingual Not comparable
Llama 3.1-70B: 38.8 (#225), Qwen2.5 32B Instruct: —
| Benchmark | Llama 3.1-70B | Qwen2.5 32B Instruct |
|---|---|---|
| LMArena Non-English | 1219 | — |
| LMArena Chinese | 1215 | — |
| LMArena French | 1261 | — |
| LMArena German | 1222 | — |
| LMArena Japanese | 1132 | — |
| LMArena Korean | 1140 | — |
| LMArena Russian | 1234 | — |
| LMArena Spanish | 1253 | — |
Instruction Following Not comparable
Llama 3.1-70B: 65.3 (#223), Qwen2.5 32B Instruct: —
| Benchmark | Llama 3.1-70B | Qwen2.5 32B Instruct |
|---|---|---|
| IFEval | 82.1% | — |
| LMArena Instruction Following | 1231 | — |
Long Context Not comparable
Llama 3.1-70B: 37.6 (#214), Qwen2.5 32B Instruct: —
| Benchmark | Llama 3.1-70B | Qwen2.5 32B Instruct |
|---|---|---|
| LMArena Longer Query | 1241 | — |
Writing & Preference Not comparable
Llama 3.1-70B: 35.4 (#267), Qwen2.5 32B Instruct: —
| Benchmark | Llama 3.1-70B | Qwen2.5 32B Instruct |
|---|---|---|
| LMArena Text | 1261 | — |
| LMArena Creative Writing | 1232 | — |
| EQ-Bench Creative Writing | 784 | — |
| WildBench | 75.8% | — |
| LMArena Multi-Turn | 1256 | — |
Frequently asked questions
Is Llama 3.1-70B better than Qwen2.5 32B Instruct?
Llama 3.1-70B and Qwen2.5 32B Instruct score almost the same on the Noometry Index (29.6 vs 30.1), so choose on price, context window or the category you care about most.
Which is cheaper, Llama 3.1-70B or Qwen2.5 32B Instruct?
Llama 3.1-70B is cheaper. It lists at $0.40 per million input tokens and $0.40 per million output tokens; Qwen2.5 32B Instruct lists at $0.70 and $2.80.
Is Llama 3.1-70B or Qwen2.5 32B Instruct better for coding?
Qwen2.5 32B Instruct scores higher on coding benchmarks: 38.7 versus 30.3 in the Noometry coding category.
Which has the bigger context window?
Qwen2.5 32B Instruct does, with 131K tokens against 128K.
How many benchmarks do Llama 3.1-70B and Qwen2.5 32B Instruct share?
6 benchmarks have published results for both models. Llama 3.1-70B has 35 scored results on Noometry and Qwen2.5 32B Instruct has 7.