Model comparison
Gemini 1.0 Pro vs Qwen2-72B
Qwen2-72B is the stronger model overall, scoring 30.0 to 27.3 on the Noometry Index.
Last verified . 20 shared benchmarks.
Google
Alibaba (Qwen)Summary
- They share 20 benchmarks with published results for both. Gemini 1.0 Pro scores higher in 1 category and Qwen2-72B in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen2-72B leads 30.2 to 9.3.
- The biggest single-benchmark swing is MATH Level 5: 11.2% for Gemini 1.0 Pro and 39.1% for Qwen2-72B.
- Qwen2-72B has downloadable open weights; the other is API-only.
Side by side
| Gemini 1.0 Pro | Qwen2-72B | |
|---|---|---|
| Provider | Alibaba (Qwen) | |
| Noometry Index | 27.3 | 30.0 |
| Released | 2023-12-13 | 2024-06-07 |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 24 | 26 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 1.0 Pro leads
Gemini 1.0 Pro: 32.2 (#275), Qwen2-72B: 29.1 (#310)
| Benchmark | Gemini 1.0 Pro | Qwen2-72B |
|---|---|---|
| LMArena Coding | 1108 | 1196 |
| WeirdML | — | 11.3% |
| BigCodeBench Instruct | — | 38.5% |
| BigCodeBench Complete | — | 54% |
| HumanEval+ | 55.5% | — |
| MBPP+ | 61.4% | — |
Agentic & Tool Use Not comparable
Gemini 1.0 Pro: —, Qwen2-72B: 17.0 (#146)
| Benchmark | Gemini 1.0 Pro | Qwen2-72B |
|---|---|---|
| TheAgentCompany | — | 1.1% |
| METR Time Horizons | — | 29.9% |
Reasoning Qwen2-72B leads
Gemini 1.0 Pro: 17.1 (#296), Qwen2-72B: 23.2 (#181)
| Benchmark | Gemini 1.0 Pro | Qwen2-72B |
|---|---|---|
| LMArena Hard Prompts | 1109 | 1191 |
| Epoch Capabilities Index | 117.04 | 125.28 |
| DTBench | 45.9% | — |
Math Qwen2-72B leads
Gemini 1.0 Pro: 9.3 (#321), Qwen2-72B: 30.2 (#236)
| Benchmark | Gemini 1.0 Pro | Qwen2-72B |
|---|---|---|
| LMArena Math | 1132 | 1235 |
| MATH Level 5 | 11.2% | 39.1% |
| OTIS Mock AIME 2024-2025 | 1.1% | — |
Knowledge Qwen2-72B leads
Gemini 1.0 Pro: 15.6 (#291), Qwen2-72B: 21.2 (#275)
| Benchmark | Gemini 1.0 Pro | Qwen2-72B |
|---|---|---|
| GPQA Diamond | 34% | 40.8% |
| LMArena Expert | 1059 | 1171 |
| MMLU | 70% | 82.4% |
Multilingual Qwen2-72B leads
Gemini 1.0 Pro: 33.4 (#252), Qwen2-72B: 35.9 (#244)
| Benchmark | Gemini 1.0 Pro | Qwen2-72B |
|---|---|---|
| LMArena Non-English | 1138 | 1176 |
| LMArena Chinese | 1124 | 1240 |
| LMArena French | 1145 | 1170 |
| LMArena German | 1125 | 1151 |
| LMArena Japanese | 1023 | 1111 |
| LMArena Russian | 1186 | 1169 |
| LMArena Spanish | 1119 | 1169 |
| LMArena Korean | — | 1083 |
Instruction Following Qwen2-72B leads
Gemini 1.0 Pro: 57.6 (#267), Qwen2-72B: 61.7 (#241)
| Benchmark | Gemini 1.0 Pro | Qwen2-72B |
|---|---|---|
| LMArena Instruction Following | 1114 | 1181 |
Long Context Qwen2-72B leads
Gemini 1.0 Pro: 34.3 (#249), Qwen2-72B: 36.1 (#235)
| Benchmark | Gemini 1.0 Pro | Qwen2-72B |
|---|---|---|
| LMArena Longer Query | 1132 | 1192 |
Writing & Preference Qwen2-72B leads
Gemini 1.0 Pro: 36.0 (#264), Qwen2-72B: 40.8 (#241)
| Benchmark | Gemini 1.0 Pro | Qwen2-72B |
|---|---|---|
| LMArena Text | 1149 | 1203 |
| LMArena Creative Writing | 1131 | 1181 |
| LMArena Multi-Turn | 1139 | 1196 |
Frequently asked questions
Is Gemini 1.0 Pro better than Qwen2-72B?
Qwen2-72B is the stronger model overall, scoring 30.0 to 27.3 on the Noometry Index.
Is Gemini 1.0 Pro or Qwen2-72B better for coding?
Gemini 1.0 Pro scores higher on coding benchmarks: 32.2 versus 29.1 in the Noometry coding category.
How many benchmarks do Gemini 1.0 Pro and Qwen2-72B share?
20 benchmarks have published results for both models. Gemini 1.0 Pro has 24 scored results on Noometry and Qwen2-72B has 26.