Model comparison
Gemini 2.0 Pro vs Qwen2.5 72B Instruct
Gemini 2.0 Pro is the stronger model overall, scoring 38.6 to 31.5 on the Noometry Index.
Last verified . 4 shared benchmarks.
Google
Alibaba (Qwen)Summary
- They share 4 benchmarks with published results for both. Gemini 2.0 Pro scores higher in 6 categories and Qwen2.5 72B Instruct in 1 category; 6 gaps are clear of the uncertainty.
- The widest gap is in math, where Gemini 2.0 Pro leads 37.1 to 18.1.
- The biggest single-benchmark swing is MATH Level 5: 83.5% for Gemini 2.0 Pro and 63.2% for Qwen2.5 72B Instruct.
- Qwen2.5 72B Instruct has downloadable open weights; the other is API-only.
Side by side
| Gemini 2.0 Pro | Qwen2.5 72B Instruct | |
|---|---|---|
| Provider | Alibaba (Qwen) | |
| Noometry Index | 38.6 | 31.5 |
| Released | 2025-02-05 | 2024-09 |
| Weights | Proprietary | Open |
| Context window | — | 131K |
| Max output | — | 8K |
| Input $ / M tokens | — | $1.40 |
| Output $ / M tokens | — | $5.60 |
| Results tracked | 14 | 43 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 2.0 Pro leads
Gemini 2.0 Pro: 37.4 (#182), Qwen2.5 72B Instruct: 32.8 (#256)
| Benchmark | Gemini 2.0 Pro | Qwen2.5 72B Instruct |
|---|---|---|
| Aider Polyglot | 35.6% | — |
| WeirdML | — | 16% |
| BigCodeBench Instruct | — | 45.8% |
| LiveBench Coding | 63.5% | — |
| LMArena Coding | — | 1293 |
| BigCodeBench Complete | — | 55.9% |
Agentic & Tool Use Not comparable
Gemini 2.0 Pro: —, Qwen2.5 72B Instruct: 22.0 (#124)
| Benchmark | Gemini 2.0 Pro | Qwen2.5 72B Instruct |
|---|---|---|
| TheAgentCompany | — | 5.7% |
| BALROG | — | 16.2% |
| METR Time Horizons | — | 35.8% |
Reasoning Too close to call
Gemini 2.0 Pro: 21.6 (#194), Qwen2.5 72B Instruct: 21.4 (#197)
| Benchmark | Gemini 2.0 Pro | Qwen2.5 72B Instruct |
|---|---|---|
| Epoch Capabilities Index | 135.06 | 129.01 |
| EnigmaEval | 0.7% | — |
| LiveBench Reasoning | 60.1% | — |
| LMArena Hard Prompts | — | 1271 |
| DTBench | — | 62.9% |
| LiveBench Data Analysis | 68% | — |
| LMCA | — | 13.4% |
| BIG-Bench Hard | — | 79.8% |
| ForecastBench | — | 57.5 |
| HellaSwag | — | 84.8% |
| LiveBench | 65.1% | — |
| PIQA | — | 82.6% |
| WinoGrande | — | 82.3% |
Math Gemini 2.0 Pro leads
Gemini 2.0 Pro: 37.1 (#101), Qwen2.5 72B Instruct: 18.1 (#281)
| Benchmark | Gemini 2.0 Pro | Qwen2.5 72B Instruct |
|---|---|---|
| MATH Level 5 | 83.5% | 63.2% |
| OTIS Mock AIME 2024-2025 | — | 8.1% |
| Omni-MATH | — | 33% |
| LiveBench Math | 71% | — |
| LMArena Math | — | 1283 |
Knowledge Gemini 2.0 Pro leads
Gemini 2.0 Pro: 36.5 (#156), Qwen2.5 72B Instruct: 26.9 (#247)
| Benchmark | Gemini 2.0 Pro | Qwen2.5 72B Instruct |
|---|---|---|
| GPQA Diamond | 65.7% | 49.1% |
| Confabulations | 18.4% | 19.1% |
| MMLU-Pro | — | 63.1% |
| GPQA (HELM) | — | 42.6% |
| LMArena Expert | — | 1245 |
| ARC (AI2) Challenge | — | 94.5% |
| MMLU | — | 85.3% |
| TriviaQA | — | 71.9% |
Multilingual Not comparable
Gemini 2.0 Pro: —, Qwen2.5 72B Instruct: 41.2 (#208)
| Benchmark | Gemini 2.0 Pro | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Non-English | — | 1252 |
| LMArena Chinese | — | 1272 |
| LMArena French | — | 1279 |
| LMArena German | — | 1234 |
| LMArena Japanese | — | 1180 |
| LMArena Korean | — | 1188 |
| LMArena Russian | — | 1264 |
| LMArena Spanish | — | 1255 |
Instruction Following Gemini 2.0 Pro leads
Gemini 2.0 Pro: 75.6 (#57), Qwen2.5 72B Instruct: 65.7 (#216)
| Benchmark | Gemini 2.0 Pro | Qwen2.5 72B Instruct |
|---|---|---|
| LiveBench Instruction Following | 83.4% | — |
| IFEval | — | 80.6% |
| LMArena Instruction Following | — | 1254 |
Long Context Qwen2.5 72B Instruct leads
Gemini 2.0 Pro: 29.1 (#287), Qwen2.5 72B Instruct: 38.9 (#183)
| Benchmark | Gemini 2.0 Pro | Qwen2.5 72B Instruct |
|---|---|---|
| Fiction.LiveBench | 41.7% | — |
| LMArena Longer Query | — | 1282 |
Writing & Preference Gemini 2.0 Pro leads
Gemini 2.0 Pro: 52.7 (#164), Qwen2.5 72B Instruct: 46.9 (#210)
| Benchmark | Gemini 2.0 Pro | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Text | — | 1269 |
| LMArena Creative Writing | — | 1221 |
| WildBench | — | 80.2% |
| LMArena Multi-Turn | — | 1272 |
| LiveBench Language | 44.9% | — |
Frequently asked questions
Is Gemini 2.0 Pro better than Qwen2.5 72B Instruct?
Gemini 2.0 Pro is the stronger model overall, scoring 38.6 to 31.5 on the Noometry Index.
Is Gemini 2.0 Pro or Qwen2.5 72B Instruct better for coding?
Gemini 2.0 Pro scores higher on coding benchmarks: 37.4 versus 32.8 in the Noometry coding category.
How many benchmarks do Gemini 2.0 Pro and Qwen2.5 72B Instruct share?
4 benchmarks have published results for both models. Gemini 2.0 Pro has 14 scored results on Noometry and Qwen2.5 72B Instruct has 43.