Xentir Llama 3.1-70B vs Qwen2-72B
Llama 3.1-70B OPEN WEIGHTS · Meta AI, released 2024-07-23
Qwen2-72B OPEN WEIGHTS · Alibaba, released 2024-06-07
“Epoch AI, 'AI Benchmarking Hub'. Published online at epoch.ai. Retrieved from 'https://epoch.ai/benchmarks' [online resource].” · epoch.ai/benchmarks · Licensed CC BY 4.0 · data last verified 2026-09-09 · Methodology · Data Sources
Llama 3.1-70B leads on more of the 3 benchmarks where both are measured — Llama 3.1-70B on 2, Qwen2-72B on 1. The remaining 6 of 9 tracked benchmarks cannot be compared: 1 has a result for only one of the two models, 5 for neither. Nothing on this page is estimated to fill those in.
Head-to-head
Measured on 3 of 9 tracked benchmarks for both models — Llama 3.1-70B leads on 2, Qwen2-72B leads on 1.
| Benchmark | Llama 3.1-70B | Qwen2-72B | Leads |
|---|---|---|---|
| Epoch Capabilities Index (ECI) | 125.9 | 125.3 | Llama 3.1-70B |
| SWE-bench Verified | Not measured | Not measured | Not measured on both |
| GPQA Diamond | 0.442 | 0.408 | Llama 3.1-70B |
| MATH Level 5 | 0.367 | 0.391 | Qwen2-72B |
| OTIS Mock AIME 2024-2025 | 0.036 | Not measured | Comparison unavailable — Qwen2-72B has no published result |
| FrontierMath | Not measured | Not measured | Not measured on both |
| FrontierMath Tier 4 | Not measured | Not measured | Not measured on both |
| SimpleQA Verified | Not measured | Not measured | Not measured on both |
| Chess Puzzles | Not measured | Not measured | Not measured on both |
What remains uncertain
- Qwen2-72B has no published result on OTIS Mock AIME 2024-2025.
- 5 tracked benchmarks have no published result for either model.
A missing result means Xentir has not found one published by the source it cites, not that the model performs badly. See Data Sources.
Full profiles
Llama 3.1-70B → · Qwen2-72B → · the full AI Model Rankings table