Model comparison
Llama 3.1-70B vs Qwen3.7 Plus
Qwen3.7 Plus is the stronger model overall, scoring 45.3 to 29.6 on the Noometry Index. Llama 3.1-70B costs 1.8× less per token, which makes it the better buy when Qwen3.7 Plus's lead doesn't matter for your workload.
Last verified . 22 shared benchmarks.
Meta
Alibaba (Qwen)Summary
- They share 22 benchmarks with published results for both. Llama 3.1-70B scores higher in 1 category and Qwen3.7 Plus in 8 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3.7 Plus leads 50.5 to 13.5.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 3.6% for Llama 3.1-70B and 93.3% for Qwen3.7 Plus.
- Llama 3.1-70B is cheaper at $0.40 / $0.40 per million input/output tokens, against $0.40 / $1.60 for Qwen3.7 Plus.
- Qwen3.7 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 | Qwen3.7 Plus | |
|---|---|---|
| Provider | Meta | Alibaba (Qwen) |
| Noometry Index | 29.6 | 45.3 |
| Released | 2024-07-23 | 2026-06-02 |
| Weights | Open | Proprietary |
| Context window | 128K | 1M |
| Max output | 4K | 131K |
| Input $ / M tokens | $0.40 | $0.40 |
| Output $ / M tokens | $0.40 | $1.60 |
| Results tracked | 35 | 32 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.7 Plus leads
Llama 3.1-70B: 30.3 (#296), Qwen3.7 Plus: 36.6 (#206)
| Benchmark | Llama 3.1-70B | Qwen3.7 Plus |
|---|---|---|
| LMArena Coding | 1260 | 1473 |
| FrontierCode | — | 10.2% |
| SciCode | — | 45.5% |
| WeirdML | 9% | — |
| BigCodeBench Instruct | 46.1% | — |
| BigCodeBench Complete | 54.8% | — |
Agentic & Tool Use Llama 3.1-70B leads
Llama 3.1-70B: 25.1 (#112), Qwen3.7 Plus: 21.4 (#138)
| Benchmark | Llama 3.1-70B | Qwen3.7 Plus |
|---|---|---|
| OSWorld 2.0 | — | 2.8% |
| TheAgentCompany | 6.9% | — |
| BALROG | 27.9% | — |
Reasoning Qwen3.7 Plus leads
Llama 3.1-70B: 21.6 (#220), Qwen3.7 Plus: 39.3 (#59)
| Benchmark | Llama 3.1-70B | Qwen3.7 Plus |
|---|---|---|
| LMArena Hard Prompts | 1241 | 1460 |
| DTBench | 60% | 84% |
| LMCA | 14.8% | 37.6% |
| Epoch Capabilities Index | 125.92 | 147.37 |
| NYT Connections (extended) | — | 74.8% |
| CritPt | — | 9.1% |
| Chess Puzzles | — | 24% |
| Mystery Game Puzzles | — | 17% |
Math Qwen3.7 Plus leads
Llama 3.1-70B: 13.5 (#304), Qwen3.7 Plus: 50.5 (#56)
| Benchmark | Llama 3.1-70B | Qwen3.7 Plus |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 3.6% | 93.3% |
| LMArena Math | 1252 | 1466 |
| FrontierMath (Tiers 1-3) | — | 34.4% |
| Omni-MATH | 21% | — |
| MATH Level 5 | 36.7% | — |
Knowledge Qwen3.7 Plus leads
Llama 3.1-70B: 24.2 (#269), Qwen3.7 Plus: 54.9 (#51)
| Benchmark | Llama 3.1-70B | Qwen3.7 Plus |
|---|---|---|
| GPQA Diamond | 44.2% | 87.9% |
| LMArena Expert | 1209 | 1467 |
| MMLU-Pro | 65.3% | — |
| GPQA (HELM) | 42.6% | — |
| MMLU | 80.1% | — |
Multimodal Not comparable
Llama 3.1-70B: —, Qwen3.7 Plus: 41.8 (#33)
| Benchmark | Llama 3.1-70B | Qwen3.7 Plus |
|---|---|---|
| LMArena Vision | — | 1279 |
| LMArena Document | — | 1444 |
Multilingual Qwen3.7 Plus leads
Llama 3.1-70B: 38.8 (#225), Qwen3.7 Plus: 54.8 (#38)
| Benchmark | Llama 3.1-70B | Qwen3.7 Plus |
|---|---|---|
| LMArena Non-English | 1219 | 1445 |
| LMArena Chinese | 1215 | 1510 |
| LMArena French | 1261 | 1473 |
| LMArena German | 1222 | 1471 |
| LMArena Japanese | 1132 | 1413 |
| LMArena Korean | 1140 | 1415 |
| LMArena Russian | 1234 | 1457 |
| LMArena Spanish | 1253 | 1457 |
Instruction Following Qwen3.7 Plus leads
Llama 3.1-70B: 65.3 (#223), Qwen3.7 Plus: 75.8 (#52)
| Benchmark | Llama 3.1-70B | Qwen3.7 Plus |
|---|---|---|
| LMArena Instruction Following | 1231 | 1440 |
| IFEval | 82.1% | — |
Long Context Qwen3.7 Plus leads
Llama 3.1-70B: 37.6 (#214), Qwen3.7 Plus: 44.5 (#65)
| Benchmark | Llama 3.1-70B | Qwen3.7 Plus |
|---|---|---|
| LMArena Longer Query | 1241 | 1455 |
Writing & Preference Qwen3.7 Plus leads
Llama 3.1-70B: 35.4 (#267), Qwen3.7 Plus: 64.3 (#56)
| Benchmark | Llama 3.1-70B | Qwen3.7 Plus |
|---|---|---|
| LMArena Text | 1261 | 1455 |
| LMArena Creative Writing | 1232 | 1439 |
| LMArena Multi-Turn | 1256 | 1460 |
| EQ-Bench Creative Writing | 784 | — |
| WildBench | 75.8% | — |
Frequently asked questions
Is Llama 3.1-70B better than Qwen3.7 Plus?
Qwen3.7 Plus is the stronger model overall, scoring 45.3 to 29.6 on the Noometry Index. Llama 3.1-70B costs 1.8× less per token, which makes it the better buy when Qwen3.7 Plus's lead doesn't matter for your workload.
Which is cheaper, Llama 3.1-70B or Qwen3.7 Plus?
Llama 3.1-70B is cheaper. It lists at $0.40 per million input tokens and $0.40 per million output tokens; Qwen3.7 Plus lists at $0.40 and $1.60.
Is Llama 3.1-70B or Qwen3.7 Plus better for coding?
Qwen3.7 Plus scores higher on coding benchmarks: 36.6 versus 30.3 in the Noometry coding category.
Which has the bigger context window?
Qwen3.7 Plus does, with 1M tokens against 128K.
How many benchmarks do Llama 3.1-70B and Qwen3.7 Plus share?
22 benchmarks have published results for both models. Llama 3.1-70B has 35 scored results on Noometry and Qwen3.7 Plus has 32.