Qwen1.5 72B vs Qwen2 72B: Benchmark Comparison
Detailed comparison of Qwen1.5 72B and Qwen2 72B covering benchmarks, pricing, context window, and compliance.
Key Specifications
| Specification | Qwen1.5 72B | Qwen2 72B |
|---|---|---|
| Vendor | alibaba | alibaba |
| Version | 1.5-72b | 2-72b |
| Release Date | 2024-02-25 | 2024-06-07 |
| Context Window | 32768 tokens | 131072 tokens |
| Input Modalities | text | text |
| Output Modalities | text | text |
| License | Qwen License | Qwen License |
| SOC2 | ✗ | ✗ |
| HIPAA | ✗ | ✗ |
| GDPR | ✗ | ✗ |
| ISO 27001 | ✗ | ✗ |
Benchmark Results
| Benchmark | Qwen1.5 72B | Qwen2 72B | Winner |
|---|---|---|---|
| ARC | 92.6 | 94.4 | Qwen2 72B |
| BBH | 76.5 | 83.4 | Qwen2 72B |
| GPQA | 39.8 | 53.6 | Qwen2 72B |
| GSM8K | 80.9 | 87 | Qwen2 72B |
| HUMANEVAL | 65.2 | 76.5 | Qwen2 72B |
| IFEVAL | 76.4 | 76.9 | Qwen2 72B |
| MATH | 37.6 | 71.9 | Qwen2 72B |
| MMLU | 81.3 | 80.2 | Qwen1.5 72B |
| MUSR | 50.8 | 68.9 | Qwen2 72B |
| WINOGRANDE | 83.1 | 82.5 | Qwen1.5 72B |
Pricing Comparison
| Tier (per Mtok) | Qwen1.5 72B | Qwen2 72B |
|---|---|---|
| Input | $0.5 | $0.5 |
| Output | $0.8 | $0.8 |
| Cache Read | $0 | $0 |
| Cache Write | $0 | $0 |
Qwen1.5 72B vs Qwen2 72B
Model Overview
Qwen1.5 72B and Qwen2 72B are both notable options in the AI model market. This page compares their benchmarks, pricing, and compliance.
Key Specifications
| Vendor | Release Date | Context Window | License |
|---|---|---|---|
| Alibaba / Alibaba | 2024-02-25 / 2024-06-07 | 32K / 131K | Qwen License / Qwen License |
Benchmark Performance
| Benchmark | Qwen1.5 72B | Qwen2 72B | Winner |
|---|---|---|---|
| ARC | 92.6 | 94.4 | B |
| BBH (BIG-Bench Hard) | 76.5 | 83.4 | B |
| GPQA | 39.8 | 53.6 | B |
| GSM8K (Grade School Math 8K) | 80.9 | 87.0 | B |
| HumanEval | 65.2 | 76.5 | B |
| IFEval | 76.4 | 76.9 | B |
| MATH | 37.6 | 71.9 | B |
| MMLU (Massive Multitask Language Understanding) | 81.3 | 80.2 | A |
| MUSR | 50.8 | 68.9 | B |
| WinoGrande | 83.1 | 82.5 | A |
Pricing Comparison
| Input | Output | Cache Read | Cache Write |
|---|---|---|---|
| — / — | — / — | — / — | — / — |
per million tokens — A / B
Strengths & Weaknesses
Qwen1.5 72B
- ✅ MMLU score 81.3, strong knowledge reasoning.
- ⚠️ Proprietary, not self-hostable.
Qwen2 72B
- ✅ MMLU score 80.2, strong knowledge reasoning.
- ✅ GSM8K 87.0, robust math reasoning.
- ⚠️ Proprietary, not self-hostable.
Editor’s Take
Qwen1.5 72B and Qwen2 72B each have their strengths. Choose based on workload (code, long context, vision), referencing the tables above.
FAQ
Which model is better for coding tasks?
Refer to the HumanEval benchmark table; the model with a higher score is better suited for coding tasks.
Which model is cheaper?
Refer to the pricing comparison table above; the model with lower input/output prices is more cost-effective.
Which has a longer context window?
Refer to the key specifications table; the model with a larger context window is better for long documents.
References
Editor's Take
See Editor's Take section.