Model comparison
Llama 3.1-70B vs Qwen Plus
Qwen Plus is the stronger model overall, scoring 37.1 to 29.6 on the Noometry Index. Llama 3.1-70B costs 1.5× less per token, which makes it the better buy when Qwen Plus's lead doesn't matter for your workload.
Last verified . 18 shared benchmarks.
Meta
Alibaba (Qwen)Summary
- They share 18 benchmarks with published results for both. Llama 3.1-70B scores higher in 0 categories and Qwen Plus in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Qwen Plus leads 52.2 to 35.4.
- The biggest single-benchmark swing is MATH Level 5: 36.7% for Llama 3.1-70B and 65.3% for Qwen Plus.
- Llama 3.1-70B is cheaper at $0.40 / $0.40 per million input/output tokens, against $0.40 / $1.20 for Qwen Plus.
- Qwen Plus accepts more context: 1M tokens versus 128K.
- Llama 3.1-70B has downloadable open weights; the other is API-only.
Side by side
| Llama 3.1-70B | Qwen Plus | |
|---|---|---|
| Provider | Meta | Alibaba (Qwen) |
| Noometry Index | 29.6 | 37.1 |
| Released | 2024-07-23 | 2024-01-25 |
| Weights | Open | Proprietary |
| Context window | 128K | 1M |
| Max output | 4K | 33K |
| Input $ / M tokens | $0.40 | $0.40 |
| Output $ / M tokens | $0.40 | $1.20 |
| Results tracked | 35 | 20 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen Plus leads
Llama 3.1-70B: 30.3 (#296), Qwen Plus: 38.9 (#167)
| Benchmark | Llama 3.1-70B | Qwen Plus |
|---|---|---|
| LMArena Coding | 1260 | 1328 |
| WeirdML | 9% | — |
| BigCodeBench Instruct | 46.1% | — |
| BigCodeBench Complete | 54.8% | — |
Agentic & Tool Use Not comparable
Llama 3.1-70B: 25.1 (#112), Qwen Plus: —
| Benchmark | Llama 3.1-70B | Qwen Plus |
|---|---|---|
| TheAgentCompany | 6.9% | — |
| BALROG | 27.9% | — |
Reasoning Qwen Plus leads
Llama 3.1-70B: 21.6 (#220), Qwen Plus: 28.4 (#107)
| Benchmark | Llama 3.1-70B | Qwen Plus |
|---|---|---|
| LMArena Hard Prompts | 1241 | 1317 |
| DTBench | 60% | 81.1% |
| LMCA | 14.8% | 24% |
| Kagi LLM Benchmark | — | 63.3% |
| Epoch Capabilities Index | 125.92 | — |
Math Qwen Plus leads
Llama 3.1-70B: 13.5 (#304), Qwen Plus: 23.3 (#271)
| Benchmark | Llama 3.1-70B | Qwen Plus |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 3.6% | 17.8% |
| LMArena Math | 1252 | 1326 |
| MATH Level 5 | 36.7% | 65.3% |
| Omni-MATH | 21% | — |
| FrontierMath (Feb 2025 set) | — | 1.7% |
Knowledge Qwen Plus leads
Llama 3.1-70B: 24.2 (#269), Qwen Plus: 27.4 (#251)
| Benchmark | Llama 3.1-70B | Qwen Plus |
|---|---|---|
| GPQA Diamond | 44.2% | 48.1% |
| LMArena Expert | 1209 | 1328 |
| MMLU-Pro | 65.3% | — |
| GPQA (HELM) | 42.6% | — |
| MMLU | 80.1% | — |
Multilingual Qwen Plus leads
Llama 3.1-70B: 38.8 (#225), Qwen Plus: 45.1 (#175)
| Benchmark | Llama 3.1-70B | Qwen Plus |
|---|---|---|
| LMArena Non-English | 1219 | 1310 |
| LMArena Chinese | 1215 | 1347 |
| LMArena Japanese | 1132 | 1251 |
| LMArena Russian | 1234 | 1323 |
| LMArena French | 1261 | — |
| LMArena German | 1222 | — |
| LMArena Korean | 1140 | — |
| LMArena Spanish | 1253 | — |
Instruction Following Qwen Plus leads
Llama 3.1-70B: 65.3 (#223), Qwen Plus: 68.8 (#181)
| Benchmark | Llama 3.1-70B | Qwen Plus |
|---|---|---|
| LMArena Instruction Following | 1231 | 1303 |
| IFEval | 82.1% | — |
Long Context Qwen Plus leads
Llama 3.1-70B: 37.6 (#214), Qwen Plus: 40.3 (#158)
| Benchmark | Llama 3.1-70B | Qwen Plus |
|---|---|---|
| LMArena Longer Query | 1241 | 1324 |
Writing & Preference Qwen Plus leads
Llama 3.1-70B: 35.4 (#267), Qwen Plus: 52.2 (#176)
| Benchmark | Llama 3.1-70B | Qwen Plus |
|---|---|---|
| LMArena Text | 1261 | 1326 |
| LMArena Creative Writing | 1232 | 1293 |
| LMArena Multi-Turn | 1256 | 1336 |
| EQ-Bench Creative Writing | 784 | — |
| WildBench | 75.8% | — |
Frequently asked questions
Is Llama 3.1-70B better than Qwen Plus?
Qwen Plus is the stronger model overall, scoring 37.1 to 29.6 on the Noometry Index. Llama 3.1-70B costs 1.5× less per token, which makes it the better buy when Qwen Plus's lead doesn't matter for your workload.
Which is cheaper, Llama 3.1-70B or Qwen Plus?
Llama 3.1-70B is cheaper. It lists at $0.40 per million input tokens and $0.40 per million output tokens; Qwen Plus lists at $0.40 and $1.20.
Is Llama 3.1-70B or Qwen Plus better for coding?
Qwen Plus scores higher on coding benchmarks: 38.9 versus 30.3 in the Noometry coding category.
Which has the bigger context window?
Qwen Plus does, with 1M tokens against 128K.
How many benchmarks do Llama 3.1-70B and Qwen Plus share?
18 benchmarks have published results for both models. Llama 3.1-70B has 35 scored results on Noometry and Qwen Plus has 20.