Model comparison
Claude 2.1 vs Qwen-14B
Qwen-14B is the stronger model overall, scoring 30.8 to 24.9 on the Noometry Index.
Last verified . 2 shared benchmarks.
Alibaba (Qwen)Summary
- They share 2 benchmarks with published results for both. Claude 2.1 scores higher in 1 category and Qwen-14B in 2 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen-14B leads 28.7 to 9.6.
- Qwen-14B has downloadable open weights; the other is API-only.
Side by side
| Claude 2.1 | Qwen-14B | |
|---|---|---|
| Provider | Anthropic | Alibaba (Qwen) |
| Noometry Index | 24.9 | 30.8 |
| Released | 2023-11-21 | 2023-09-24 |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 7 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen-14B leads
Claude 2.1: 25.8 (#322), Qwen-14B: 30.6 (#283)
| Benchmark | Claude 2.1 | Qwen-14B |
|---|---|---|
| WeirdML | 7.1% | — |
| LMArena Coding | — | 1072 |
Reasoning Claude 2.1 leads
Claude 2.1: 20.6 (#216), Qwen-14B: 18.7 (#255)
| Benchmark | Claude 2.1 | Qwen-14B |
|---|---|---|
| Epoch Capabilities Index | 119.22 | 112.8 |
| LMArena Hard Prompts | — | 1027 |
| DTBench | 51% | — |
| BIG-Bench Hard | — | 55% |
| ForecastBench | 54.2 | — |
| LAMBADA | — | 71.1% |
| PIQA | — | 79.9% |
Math Qwen-14B leads
Claude 2.1: 9.6 (#309), Qwen-14B: 28.7 (#224)
| Benchmark | Claude 2.1 | Qwen-14B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 1.9% | — |
| LMArena Math | — | 1068 |
| GSM8K | — | 61.3% |
Knowledge Not comparable
Claude 2.1: 15.5 (#287), Qwen-14B: —
| Benchmark | Claude 2.1 | Qwen-14B |
|---|---|---|
| MMLU | 73.5% | 66.3% |
| GPQA Diamond | 33% | — |
| ARC (AI2) Challenge | — | 84.4% |
| BoolQ | — | 86.2% |
Multilingual Not comparable
Claude 2.1: —, Qwen-14B: 27.7 (#270)
| Benchmark | Claude 2.1 | Qwen-14B |
|---|---|---|
| LMArena Non-English | — | 1042 |
| LMArena Chinese | — | 1077 |
Instruction Following Not comparable
Claude 2.1: —, Qwen-14B: 52.6 (#284)
| Benchmark | Claude 2.1 | Qwen-14B |
|---|---|---|
| LMArena Instruction Following | — | 1031 |
Long Context Not comparable
Claude 2.1: —, Qwen-14B: 31.3 (#276)
| Benchmark | Claude 2.1 | Qwen-14B |
|---|---|---|
| LMArena Longer Query | — | 1029 |
Writing & Preference Not comparable
Claude 2.1: —, Qwen-14B: 27.8 (#294)
| Benchmark | Claude 2.1 | Qwen-14B |
|---|---|---|
| LMArena Text | — | 1051 |
| LMArena Creative Writing | — | 1028 |
| LMArena Multi-Turn | — | 1022 |
Frequently asked questions
Is Claude 2.1 better than Qwen-14B?
Qwen-14B is the stronger model overall, scoring 30.8 to 24.9 on the Noometry Index.
Is Claude 2.1 or Qwen-14B better for coding?
Qwen-14B scores higher on coding benchmarks: 30.6 versus 25.8 in the Noometry coding category.
How many benchmarks do Claude 2.1 and Qwen-14B share?
2 benchmarks have published results for both models. Claude 2.1 has 7 scored results on Noometry and Qwen-14B has 18.