Model comparison
Claude 2 vs Qwen2.5 7B Instruct
Qwen2.5 7B Instruct is the stronger model overall, scoring 28.6 to 24.7 on the Noometry Index.
Last verified . 5 shared benchmarks.
Alibaba (Qwen)Summary
- They share 5 benchmarks with published results for both. Claude 2 scores higher in 1 category and Qwen2.5 7B Instruct in 2 categories; 2 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Claude 2 leads 20.8 to 14.3.
- Qwen2.5 7B Instruct has downloadable open weights; the other is API-only.
Side by side
| Claude 2 | Qwen2.5 7B Instruct | |
|---|---|---|
| Provider | Anthropic | Alibaba (Qwen) |
| Noometry Index | 24.7 | 28.6 |
| Released | 2023-07-11 | 2024-09 |
| Weights | Proprietary | Open |
| Context window | — | 131K |
| Max output | — | 8K |
| Input $ / M tokens | — | $0.17 |
| Output $ / M tokens | — | $0.70 |
| Results tracked | 8 | 15 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Claude 2: —, Qwen2.5 7B Instruct: 35.9 (#204)
| Benchmark | Claude 2 | Qwen2.5 7B Instruct |
|---|---|---|
| BigCodeBench Instruct | — | 37.6% |
| BigCodeBench Complete | — | 46.1% |
| HumanEval+ | 61.6% | — |
Agentic & Tool Use Not comparable
Claude 2: —, Qwen2.5 7B Instruct: 23.5 (#117)
| Benchmark | Claude 2 | Qwen2.5 7B Instruct |
|---|---|---|
| BALROG | — | 7.8% |
Reasoning Claude 2 leads
Claude 2: 20.8 (#213), Qwen2.5 7B Instruct: 14.3 (#317)
| Benchmark | Claude 2 | Qwen2.5 7B Instruct |
|---|---|---|
| DTBench | 51.9% | 47.7% |
| Epoch Capabilities Index | 120.08 | 118.44 |
| Chess Puzzles | — | 0% |
| LMCA | — | 6.4% |
Math Qwen2.5 7B Instruct leads
Claude 2: 8.7 (#314), Qwen2.5 7B Instruct: 11.8 (#300)
| Benchmark | Claude 2 | Qwen2.5 7B Instruct |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 2.5% | 2.5% |
| Omni-MATH | — | 29.4% |
| MATH Level 5 | 11.7% | — |
Knowledge Too close to call
Claude 2: 17.0 (#282), Qwen2.5 7B Instruct: 17.0 (#281)
| Benchmark | Claude 2 | Qwen2.5 7B Instruct |
|---|---|---|
| GPQA Diamond | 34.7% | 35.5% |
| MMLU | 78.5% | 72.9% |
| MMLU-Pro | — | 53.9% |
| GPQA (HELM) | — | 34.1% |
| TriviaQA | 87.5% | — |
Instruction Following Not comparable
Claude 2: —, Qwen2.5 7B Instruct: 63.4 (#226)
| Benchmark | Claude 2 | Qwen2.5 7B Instruct |
|---|---|---|
| IFEval | — | 74.1% |
Writing & Preference Not comparable
Claude 2: —, Qwen2.5 7B Instruct: 48.8 (#194)
| Benchmark | Claude 2 | Qwen2.5 7B Instruct |
|---|---|---|
| WildBench | — | 73.1% |
Frequently asked questions
Is Claude 2 better than Qwen2.5 7B Instruct?
Qwen2.5 7B Instruct is the stronger model overall, scoring 28.6 to 24.7 on the Noometry Index.
How many benchmarks do Claude 2 and Qwen2.5 7B Instruct share?
5 benchmarks have published results for both models. Claude 2 has 8 scored results on Noometry and Qwen2.5 7B Instruct has 15.