Model comparison
Palm 2 vs Qwen1.5-72B
Palm 2 and Qwen1.5-72B score almost the same on the Noometry Index (30.0 vs 30.8), so choose on price, context window or the category you care about most.
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 Qwen1.5-72B in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in multilingual, where Qwen1.5-72B leads 33.2 to 20.9.
- Qwen1.5-72B has downloadable open weights; the other is API-only.
Side by side
| Palm 2 | Qwen1.5-72B | |
|---|---|---|
| Provider | Alibaba (Qwen) | |
| Noometry Index | 30.0 | 30.8 |
| Released | — | 2024-02-04 |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 10 | 22 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen1.5-72B leads
Palm 2: 29.0 (#311), Qwen1.5-72B: 31.9 (#277)
| Benchmark | Palm 2 | Qwen1.5-72B |
|---|---|---|
| LMArena Coding | 994 | 1165 |
| BigCodeBench Instruct | — | 33.2% |
| BigCodeBench Complete | — | 40.3% |
| HumanEval+ | — | 59.1% |
| MBPP+ | — | 61.6% |
Reasoning Qwen1.5-72B leads
Palm 2: 19.1 (#271), Qwen1.5-72B: 22.2 (#203)
| Benchmark | Palm 2 | Qwen1.5-72B |
|---|---|---|
| LMArena Hard Prompts | 1005 | 1148 |
Math Qwen1.5-72B leads
Palm 2: 30.8 (#231), Qwen1.5-72B: 33.2 (#205)
| Benchmark | Palm 2 | Qwen1.5-72B |
|---|---|---|
| LMArena Math | 1049 | 1164 |
Knowledge Not comparable
Palm 2: —, Qwen1.5-72B: 11.5 (#300)
| Benchmark | Palm 2 | Qwen1.5-72B |
|---|---|---|
| GPQA Diamond | — | 28.8% |
| LMArena Expert | — | 1136 |
Multilingual Qwen1.5-72B leads
Palm 2: 20.9 (#295), Qwen1.5-72B: 33.2 (#253)
| Benchmark | Palm 2 | Qwen1.5-72B |
|---|---|---|
| LMArena Non-English | 916 | 1135 |
| LMArena Chinese | 887 | 1186 |
| LMArena French | — | 1159 |
| LMArena German | — | 1084 |
| LMArena Japanese | — | 1061 |
| LMArena Korean | — | 1050 |
| LMArena Russian | — | 1104 |
| LMArena Spanish | — | 1110 |
Instruction Following Qwen1.5-72B leads
Palm 2: 51.0 (#296), Qwen1.5-72B: 59.3 (#256)
| Benchmark | Palm 2 | Qwen1.5-72B |
|---|---|---|
| LMArena Instruction Following | 1010 | 1141 |
Long Context Qwen1.5-72B leads
Palm 2: 30.8 (#285), Qwen1.5-72B: 35.1 (#243)
| Benchmark | Palm 2 | Qwen1.5-72B |
|---|---|---|
| LMArena Longer Query | 1010 | 1157 |
Writing & Preference Qwen1.5-72B leads
Palm 2: 25.6 (#304), Qwen1.5-72B: 37.3 (#258)
| Benchmark | Palm 2 | Qwen1.5-72B |
|---|---|---|
| LMArena Text | 1027 | 1166 |
| LMArena Creative Writing | 991 | 1137 |
| LMArena Multi-Turn | 994 | 1160 |
Frequently asked questions
Is Palm 2 better than Qwen1.5-72B?
Palm 2 and Qwen1.5-72B score almost the same on the Noometry Index (30.0 vs 30.8), so choose on price, context window or the category you care about most.
Is Palm 2 or Qwen1.5-72B better for coding?
Qwen1.5-72B scores higher on coding benchmarks: 31.9 versus 29.0 in the Noometry coding category.
How many benchmarks do Palm 2 and Qwen1.5-72B share?
10 benchmarks have published results for both models. Palm 2 has 10 scored results on Noometry and Qwen1.5-72B has 22.