Model comparison
Palm 2 vs Qwen1.5-14B
Qwen1.5-14B is the stronger model overall, scoring 32.7 to 30.0 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 Qwen1.5-14B in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in multilingual, where Qwen1.5-14B leads 30.7 to 20.9.
- Qwen1.5-14B has downloadable open weights; the other is API-only.
Side by side
| Palm 2 | Qwen1.5-14B | |
|---|---|---|
| Provider | Alibaba (Qwen) | |
| Noometry Index | 30.0 | 32.7 |
| Released | — | 2024-02-04 |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 10 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen1.5-14B leads
Palm 2: 29.0 (#311), Qwen1.5-14B: 33.1 (#263)
| Benchmark | Palm 2 | Qwen1.5-14B |
|---|---|---|
| LMArena Coding | 994 | 1138 |
Reasoning Qwen1.5-14B leads
Palm 2: 19.1 (#271), Qwen1.5-14B: 21.4 (#223)
| Benchmark | Palm 2 | Qwen1.5-14B |
|---|---|---|
| LMArena Hard Prompts | 1005 | 1113 |
Math Qwen1.5-14B leads
Palm 2: 30.8 (#231), Qwen1.5-14B: 32.4 (#215)
| Benchmark | Palm 2 | Qwen1.5-14B |
|---|---|---|
| LMArena Math | 1049 | 1125 |
Knowledge Not comparable
Palm 2: —, Qwen1.5-14B: 29.8 (#232)
| Benchmark | Palm 2 | Qwen1.5-14B |
|---|---|---|
| LMArena Expert | — | 1094 |
| MMLU | — | 68.6% |
Multilingual Qwen1.5-14B leads
Palm 2: 20.9 (#295), Qwen1.5-14B: 30.7 (#262)
| Benchmark | Palm 2 | Qwen1.5-14B |
|---|---|---|
| LMArena Non-English | 916 | 1095 |
| LMArena Chinese | 887 | 1147 |
| LMArena French | — | 1116 |
| LMArena German | — | 1043 |
| LMArena Japanese | — | 1019 |
| LMArena Russian | — | 1046 |
| LMArena Spanish | — | 1085 |
Instruction Following Qwen1.5-14B leads
Palm 2: 51.0 (#296), Qwen1.5-14B: 56.8 (#271)
| Benchmark | Palm 2 | Qwen1.5-14B |
|---|---|---|
| LMArena Instruction Following | 1010 | 1102 |
Long Context Qwen1.5-14B leads
Palm 2: 30.8 (#285), Qwen1.5-14B: 33.7 (#257)
| Benchmark | Palm 2 | Qwen1.5-14B |
|---|---|---|
| LMArena Longer Query | 1010 | 1113 |
Writing & Preference Qwen1.5-14B leads
Palm 2: 25.6 (#304), Qwen1.5-14B: 33.6 (#276)
| Benchmark | Palm 2 | Qwen1.5-14B |
|---|---|---|
| LMArena Text | 1027 | 1128 |
| LMArena Creative Writing | 991 | 1091 |
| LMArena Multi-Turn | 994 | 1110 |
Frequently asked questions
Is Palm 2 better than Qwen1.5-14B?
Qwen1.5-14B is the stronger model overall, scoring 32.7 to 30.0 on the Noometry Index.
Is Palm 2 or Qwen1.5-14B better for coding?
Qwen1.5-14B scores higher on coding benchmarks: 33.1 versus 29.0 in the Noometry coding category.
How many benchmarks do Palm 2 and Qwen1.5-14B share?
10 benchmarks have published results for both models. Palm 2 has 10 scored results on Noometry and Qwen1.5-14B has 17.