Model comparison
Palm 2 vs Qwen2.5 72B Instruct
Qwen2.5 72B Instruct is the stronger model overall, scoring 31.9 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 1 category and Qwen2.5 72B Instruct in 6 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Qwen2.5 72B Instruct leads 46.7 to 25.6.
- Qwen2.5 72B Instruct has downloadable open weights; the other is API-only.
Side by side
| Palm 2 | Qwen2.5 72B Instruct | |
|---|---|---|
| Provider | Alibaba (Qwen) | |
| Noometry Index | 30.0 | 31.9 |
| Released | — | 2024-09 |
| Weights | Proprietary | Open |
| Context window | — | 131K |
| Max output | — | 8K |
| Input $ / M tokens | — | $1.40 |
| Output $ / M tokens | — | $5.60 |
| Results tracked | 10 | 43 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen2.5 72B Instruct leads
Palm 2: 29.0 (#311), Qwen2.5 72B Instruct: 33.2 (#260)
| Benchmark | Palm 2 | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Coding | 994 | 1292 |
| WeirdML | — | 16% |
| BigCodeBench Instruct | — | 45.8% |
| BigCodeBench Complete | — | 55.9% |
Agentic & Tool Use Not comparable
Palm 2: —, Qwen2.5 72B Instruct: 22.1 (#133)
| Benchmark | Palm 2 | Qwen2.5 72B Instruct |
|---|---|---|
| TheAgentCompany | — | 5.7% |
| BALROG | — | 16.2% |
| METR Time Horizons | — | 35.8% |
Reasoning Qwen2.5 72B Instruct leads
Palm 2: 19.1 (#271), Qwen2.5 72B Instruct: 22.3 (#199)
| Benchmark | Palm 2 | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Hard Prompts | 1005 | 1271 |
| DTBench | — | 62.9% |
| LMCA | — | 13.4% |
| BIG-Bench Hard | — | 79.8% |
| Epoch Capabilities Index | — | 129 |
| ForecastBench | — | 57.5 |
| HellaSwag | — | 84.8% |
| PIQA | — | 82.6% |
| WinoGrande | — | 82.3% |
Math Palm 2 leads
Palm 2: 30.8 (#231), Qwen2.5 72B Instruct: 19.3 (#287)
| Benchmark | Palm 2 | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Math | 1049 | 1283 |
| OTIS Mock AIME 2024-2025 | — | 8.1% |
| Omni-MATH | — | 33% |
| MATH Level 5 | — | 63.2% |
Knowledge Not comparable
Palm 2: —, Qwen2.5 72B Instruct: 27.0 (#253)
| Benchmark | Palm 2 | Qwen2.5 72B Instruct |
|---|---|---|
| GPQA Diamond | — | 49.1% |
| MMLU-Pro | — | 63.1% |
| Confabulations | — | 19.1% |
| GPQA (HELM) | — | 42.6% |
| LMArena Expert | — | 1245 |
| ARC (AI2) Challenge | — | 94.5% |
| MMLU | — | 85.3% |
| TriviaQA | — | 71.9% |
Multilingual Qwen2.5 72B Instruct leads
Palm 2: 20.9 (#295), Qwen2.5 72B Instruct: 41.0 (#213)
| Benchmark | Palm 2 | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Non-English | 916 | 1252 |
| LMArena Chinese | 887 | 1272 |
| LMArena French | — | 1280 |
| LMArena German | — | 1234 |
| LMArena Japanese | — | 1180 |
| LMArena Korean | — | 1188 |
| LMArena Russian | — | 1264 |
| LMArena Spanish | — | 1256 |
Instruction Following Qwen2.5 72B Instruct leads
Palm 2: 51.0 (#296), Qwen2.5 72B Instruct: 65.5 (#221)
| Benchmark | Palm 2 | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Instruction Following | 1010 | 1254 |
| IFEval | — | 80.6% |
Long Context Qwen2.5 72B Instruct leads
Palm 2: 30.8 (#285), Qwen2.5 72B Instruct: 38.9 (#188)
| Benchmark | Palm 2 | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Longer Query | 1010 | 1282 |
Writing & Preference Qwen2.5 72B Instruct leads
Palm 2: 25.6 (#304), Qwen2.5 72B Instruct: 46.7 (#215)
| Benchmark | Palm 2 | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Text | 1027 | 1269 |
| LMArena Creative Writing | 991 | 1221 |
| LMArena Multi-Turn | 994 | 1272 |
| WildBench | — | 80.2% |
Frequently asked questions
Is Palm 2 better than Qwen2.5 72B Instruct?
Qwen2.5 72B Instruct is the stronger model overall, scoring 31.9 to 30.0 on the Noometry Index.
Is Palm 2 or Qwen2.5 72B Instruct better for coding?
Qwen2.5 72B Instruct scores higher on coding benchmarks: 33.2 versus 29.0 in the Noometry coding category.
How many benchmarks do Palm 2 and Qwen2.5 72B Instruct share?
10 benchmarks have published results for both models. Palm 2 has 10 scored results on Noometry and Qwen2.5 72B Instruct has 43.