Model comparison
Claude 2 vs Qwen1.5-72B
Qwen1.5-72B is the stronger model overall, scoring 30.8 to 25.0 on the Noometry Index.
Last verified . 2 shared benchmarks.
Alibaba (Qwen)Summary
- They share 2 benchmarks with published results for both. Claude 2 scores higher in 1 category and Qwen1.5-72B in 2 categories; 2 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen1.5-72B leads 33.2 to 9.3.
- The biggest single-benchmark swing is GPQA Diamond: 34.7% for Claude 2 and 28.8% for Qwen1.5-72B.
- Qwen1.5-72B has downloadable open weights; the other is API-only.
Side by side
| Claude 2 | Qwen1.5-72B | |
|---|---|---|
| Provider | Anthropic | Alibaba (Qwen) |
| Noometry Index | 25.0 | 30.8 |
| Released | 2023-07-11 | 2024-02-04 |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 8 | 22 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Claude 2: —, Qwen1.5-72B: 31.9 (#277)
| Benchmark | Claude 2 | Qwen1.5-72B |
|---|---|---|
| HumanEval+ | 61.6% | 59.1% |
| BigCodeBench Instruct | — | 33.2% |
| LMArena Coding | — | 1165 |
| BigCodeBench Complete | — | 40.3% |
| MBPP+ | — | 61.6% |
Reasoning Too close to call
Claude 2: 21.7 (#216), Qwen1.5-72B: 22.2 (#203)
| Benchmark | Claude 2 | Qwen1.5-72B |
|---|---|---|
| LMArena Hard Prompts | — | 1148 |
| DTBench | 51.9% | — |
| Epoch Capabilities Index | 120.13 | — |
Math Qwen1.5-72B leads
Claude 2: 9.3 (#320), Qwen1.5-72B: 33.2 (#205)
| Benchmark | Claude 2 | Qwen1.5-72B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 2.5% | — |
| LMArena Math | — | 1164 |
| MATH Level 5 | 11.7% | — |
Knowledge Claude 2 leads
Claude 2: 16.9 (#287), Qwen1.5-72B: 11.5 (#300)
| Benchmark | Claude 2 | Qwen1.5-72B |
|---|---|---|
| GPQA Diamond | 34.7% | 28.8% |
| LMArena Expert | — | 1136 |
| MMLU | 78.5% | — |
| TriviaQA | 87.5% | — |
Multilingual Not comparable
Claude 2: —, Qwen1.5-72B: 33.2 (#253)
| Benchmark | Claude 2 | Qwen1.5-72B |
|---|---|---|
| LMArena Non-English | — | 1135 |
| LMArena Chinese | — | 1186 |
| LMArena French | — | 1159 |
| LMArena German | — | 1084 |
| LMArena Japanese | — | 1061 |
| LMArena Korean | — | 1050 |
| LMArena Russian | — | 1104 |
| LMArena Spanish | — | 1110 |
Instruction Following Not comparable
Claude 2: —, Qwen1.5-72B: 59.3 (#256)
| Benchmark | Claude 2 | Qwen1.5-72B |
|---|---|---|
| LMArena Instruction Following | — | 1141 |
Long Context Not comparable
Claude 2: —, Qwen1.5-72B: 35.1 (#243)
| Benchmark | Claude 2 | Qwen1.5-72B |
|---|---|---|
| LMArena Longer Query | — | 1157 |
Writing & Preference Not comparable
Claude 2: —, Qwen1.5-72B: 37.3 (#258)
| Benchmark | Claude 2 | Qwen1.5-72B |
|---|---|---|
| LMArena Text | — | 1166 |
| LMArena Creative Writing | — | 1137 |
| LMArena Multi-Turn | — | 1160 |
Frequently asked questions
Is Claude 2 better than Qwen1.5-72B?
Qwen1.5-72B is the stronger model overall, scoring 30.8 to 25.0 on the Noometry Index.
How many benchmarks do Claude 2 and Qwen1.5-72B share?
2 benchmarks have published results for both models. Claude 2 has 8 scored results on Noometry and Qwen1.5-72B has 22.