Model comparison
Palm 2 vs Qwen-14B
Qwen-14B is the stronger model overall, scoring 30.8 to 29.4 on the Noometry Index.
Last verified . 10 shared benchmarks.
Google
Alibaba (Qwen)Summary
- They share 10 benchmarks with published results for both. Palm 2 scores higher in 0 categories and Qwen-14B in 7 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in multilingual, where Qwen-14B leads 27.7 to 21.1.
- Qwen-14B has downloadable open weights; the other is API-only.
Side by side
| Palm 2 | Qwen-14B | |
|---|---|---|
| Provider | Alibaba (Qwen) | |
| Noometry Index | 29.4 | 30.8 |
| Released | — | 2023-09-24 |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 10 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen-14B leads
Palm 2: 28.5 (#306), Qwen-14B: 30.6 (#283)
| Benchmark | Palm 2 | Qwen-14B |
|---|---|---|
| LMArena Coding | 995 | 1072 |
Reasoning Too close to call
Palm 2: 18.2 (#270), Qwen-14B: 18.7 (#255)
| Benchmark | Palm 2 | Qwen-14B |
|---|---|---|
| LMArena Hard Prompts | 1005 | 1027 |
| BIG-Bench Hard | — | 55% |
| Epoch Capabilities Index | — | 112.8 |
| LAMBADA | — | 71.1% |
| PIQA | — | 79.9% |
Math Too close to call
Palm 2: 28.4 (#229), Qwen-14B: 28.7 (#224)
| Benchmark | Palm 2 | Qwen-14B |
|---|---|---|
| LMArena Math | 1049 | 1068 |
| GSM8K | — | 61.3% |
Knowledge Not comparable
Palm 2: —, Qwen-14B: —
| Benchmark | Palm 2 | Qwen-14B |
|---|---|---|
| ARC (AI2) Challenge | — | 84.4% |
| BoolQ | — | 86.2% |
| MMLU | — | 66.3% |
Multilingual Qwen-14B leads
Palm 2: 21.1 (#290), Qwen-14B: 27.7 (#270)
| Benchmark | Palm 2 | Qwen-14B |
|---|---|---|
| LMArena Non-English | 916 | 1042 |
| LMArena Chinese | 887 | 1077 |
Instruction Following Qwen-14B leads
Palm 2: 51.3 (#291), Qwen-14B: 52.6 (#284)
| Benchmark | Palm 2 | Qwen-14B |
|---|---|---|
| LMArena Instruction Following | 1010 | 1031 |
Long Context Too close to call
Palm 2: 30.7 (#280), Qwen-14B: 31.3 (#276)
| Benchmark | Palm 2 | Qwen-14B |
|---|---|---|
| LMArena Longer Query | 1010 | 1029 |
Writing & Preference Qwen-14B leads
Palm 2: 25.7 (#299), Qwen-14B: 27.8 (#294)
| Benchmark | Palm 2 | Qwen-14B |
|---|---|---|
| LMArena Text | 1027 | 1051 |
| LMArena Creative Writing | 991 | 1028 |
| LMArena Multi-Turn | 994 | 1022 |
Frequently asked questions
Is Palm 2 better than Qwen-14B?
Qwen-14B is the stronger model overall, scoring 30.8 to 29.4 on the Noometry Index.
Is Palm 2 or Qwen-14B better for coding?
Qwen-14B scores higher on coding benchmarks: 30.6 versus 28.5 in the Noometry coding category.
How many benchmarks do Palm 2 and Qwen-14B share?
10 benchmarks have published results for both models. Palm 2 has 10 scored results on Noometry and Qwen-14B has 18.