Model comparison
Claude 2.1 vs Qwen1.5-14B
Qwen1.5-14B is the stronger model overall, scoring 32.7 to 25.2 on the Noometry Index.
Last verified . 1 shared benchmarks.
Alibaba (Qwen)Summary
- They share 1 benchmark with published results for both. Claude 2.1 scores higher in 1 category and Qwen1.5-14B in 3 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen1.5-14B leads 32.4 to 10.2.
- Qwen1.5-14B has downloadable open weights; the other is API-only.
Side by side
| Claude 2.1 | Qwen1.5-14B | |
|---|---|---|
| Provider | Anthropic | Alibaba (Qwen) |
| Noometry Index | 25.2 | 32.7 |
| Released | 2023-11-21 | 2024-02-04 |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 7 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen1.5-14B leads
Claude 2.1: 26.2 (#327), Qwen1.5-14B: 33.1 (#263)
| Benchmark | Claude 2.1 | Qwen1.5-14B |
|---|---|---|
| WeirdML | 7.1% | — |
| LMArena Coding | — | 1138 |
Reasoning Too close to call
Claude 2.1: 21.4 (#221), Qwen1.5-14B: 21.4 (#223)
| Benchmark | Claude 2.1 | Qwen1.5-14B |
|---|---|---|
| LMArena Hard Prompts | — | 1113 |
| DTBench | 51% | — |
| Epoch Capabilities Index | 119.27 | — |
| ForecastBench | 54.2 | — |
Math Qwen1.5-14B leads
Claude 2.1: 10.2 (#315), Qwen1.5-14B: 32.4 (#215)
| Benchmark | Claude 2.1 | Qwen1.5-14B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 1.9% | — |
| LMArena Math | — | 1125 |
Knowledge Qwen1.5-14B leads
Claude 2.1: 15.4 (#292), Qwen1.5-14B: 29.8 (#232)
| Benchmark | Claude 2.1 | Qwen1.5-14B |
|---|---|---|
| MMLU | 73.5% | 68.6% |
| GPQA Diamond | 33% | — |
| LMArena Expert | — | 1094 |
Multilingual Not comparable
Claude 2.1: —, Qwen1.5-14B: 30.7 (#262)
| Benchmark | Claude 2.1 | Qwen1.5-14B |
|---|---|---|
| LMArena Non-English | — | 1095 |
| LMArena Chinese | — | 1147 |
| LMArena French | — | 1116 |
| LMArena German | — | 1043 |
| LMArena Japanese | — | 1019 |
| LMArena Russian | — | 1046 |
| LMArena Spanish | — | 1085 |
Instruction Following Not comparable
Claude 2.1: —, Qwen1.5-14B: 56.8 (#271)
| Benchmark | Claude 2.1 | Qwen1.5-14B |
|---|---|---|
| LMArena Instruction Following | — | 1102 |
Long Context Not comparable
Claude 2.1: —, Qwen1.5-14B: 33.7 (#257)
| Benchmark | Claude 2.1 | Qwen1.5-14B |
|---|---|---|
| LMArena Longer Query | — | 1113 |
Writing & Preference Not comparable
Claude 2.1: —, Qwen1.5-14B: 33.6 (#276)
| Benchmark | Claude 2.1 | Qwen1.5-14B |
|---|---|---|
| LMArena Text | — | 1128 |
| LMArena Creative Writing | — | 1091 |
| LMArena Multi-Turn | — | 1110 |
Frequently asked questions
Is Claude 2.1 better than Qwen1.5-14B?
Qwen1.5-14B is the stronger model overall, scoring 32.7 to 25.2 on the Noometry Index.
Is Claude 2.1 or Qwen1.5-14B better for coding?
Qwen1.5-14B scores higher on coding benchmarks: 33.1 versus 26.2 in the Noometry coding category.
How many benchmarks do Claude 2.1 and Qwen1.5-14B share?
1 benchmark has published results for both models. Claude 2.1 has 7 scored results on Noometry and Qwen1.5-14B has 17.