Model comparison
Gemini 1.5 Pro (May 2024) vs Qwen2-72B
Gemini 1.5 Pro (May 2024) is the stronger model overall, scoring 32.1 to 30.0 on the Noometry Index.
Last verified . 25 shared benchmarks.
Google
Alibaba (Qwen)Summary
- They share 25 benchmarks with published results for both. Gemini 1.5 Pro (May 2024) scores higher in 7 categories and Qwen2-72B in 2 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Gemini 1.5 Pro (May 2024) leads 52.4 to 40.8.
- The biggest single-benchmark swing is MATH Level 5: 70.4% for Gemini 1.5 Pro (May 2024) and 39.1% for Qwen2-72B.
- Qwen2-72B has downloadable open weights; the other is API-only.
Side by side
| Gemini 1.5 Pro (May 2024) | Qwen2-72B | |
|---|---|---|
| Provider | Alibaba (Qwen) | |
| Noometry Index | 32.1 | 30.0 |
| Released | 2024-02-15 | 2024-06-07 |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 45 | 26 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 1.5 Pro (May 2024) leads
Gemini 1.5 Pro (May 2024): 34.2 (#241), Qwen2-72B: 29.1 (#310)
| Benchmark | Gemini 1.5 Pro (May 2024) | Qwen2-72B |
|---|---|---|
| WeirdML | 22.2% | 11.3% |
| BigCodeBench Instruct | 43.8% | 38.5% |
| LMArena Coding | 1294 | 1196 |
| BigCodeBench Complete | 57.5% | 54% |
| CadEval | 34% | — |
| HumanEval+ | 79.3% | — |
| MBPP+ | 74.6% | — |
Agentic & Tool Use Too close to call
Gemini 1.5 Pro (May 2024): 17.9 (#145), Qwen2-72B: 17.0 (#146)
| Benchmark | Gemini 1.5 Pro (May 2024) | Qwen2-72B |
|---|---|---|
| TheAgentCompany | 3.4% | 1.1% |
| Cybench | 7.5% | — |
| BALROG | 21% | — |
| METR Time Horizons | — | 29.9% |
Reasoning Qwen2-72B leads
Gemini 1.5 Pro (May 2024): 12.3 (#338), Qwen2-72B: 23.2 (#181)
| Benchmark | Gemini 1.5 Pro (May 2024) | Qwen2-72B |
|---|---|---|
| LMArena Hard Prompts | 1296 | 1191 |
| Epoch Capabilities Index | 131.73 | 125.28 |
| ARC-AGI-2 | 0.8% | — |
| SimpleBench | 27.1% | — |
| DTBench | 59% | — |
| BIG-Bench Hard | 89.2% | — |
| ForecastBench | 58.4 | — |
Math Qwen2-72B leads
Gemini 1.5 Pro (May 2024): 25.8 (#266), Qwen2-72B: 30.2 (#236)
| Benchmark | Gemini 1.5 Pro (May 2024) | Qwen2-72B |
|---|---|---|
| LMArena Math | 1315 | 1235 |
| MATH Level 5 | 70.4% | 39.1% |
| OTIS Mock AIME 2024-2025 | 23.1% | — |
| Omni-MATH | 36.4% | — |
Knowledge Gemini 1.5 Pro (May 2024) leads
Gemini 1.5 Pro (May 2024): 29.4 (#239), Qwen2-72B: 21.2 (#275)
| Benchmark | Gemini 1.5 Pro (May 2024) | Qwen2-72B |
|---|---|---|
| GPQA Diamond | 57.2% | 40.8% |
| LMArena Expert | 1279 | 1171 |
| MMLU | 86.9% | 82.4% |
| Humanity's Last Exam | 4.6% | — |
| MMLU-Pro | 73.7% | — |
| Confabulations | 13.5% | — |
| GPQA (HELM) | 53.4% | — |
Multimodal Not comparable
Gemini 1.5 Pro (May 2024): 36.8 (#77), Qwen2-72B: —
| Benchmark | Gemini 1.5 Pro (May 2024) | Qwen2-72B |
|---|---|---|
| LMArena Vision | 1161 | — |
| Video-MME | 75% | — |
Multilingual Gemini 1.5 Pro (May 2024) leads
Gemini 1.5 Pro (May 2024): 45.3 (#174), Qwen2-72B: 35.9 (#244)
| Benchmark | Gemini 1.5 Pro (May 2024) | Qwen2-72B |
|---|---|---|
| LMArena Non-English | 1312 | 1176 |
| LMArena Chinese | 1331 | 1240 |
| LMArena French | 1302 | 1170 |
| LMArena German | 1286 | 1151 |
| LMArena Japanese | 1292 | 1111 |
| LMArena Korean | 1298 | 1083 |
| LMArena Russian | 1320 | 1169 |
| LMArena Spanish | 1311 | 1169 |
Instruction Following Gemini 1.5 Pro (May 2024) leads
Gemini 1.5 Pro (May 2024): 68.6 (#185), Qwen2-72B: 61.7 (#241)
| Benchmark | Gemini 1.5 Pro (May 2024) | Qwen2-72B |
|---|---|---|
| LMArena Instruction Following | 1297 | 1181 |
| IFEval | 83.7% | — |
Long Context Gemini 1.5 Pro (May 2024) leads
Gemini 1.5 Pro (May 2024): 39.8 (#169), Qwen2-72B: 36.1 (#235)
| Benchmark | Gemini 1.5 Pro (May 2024) | Qwen2-72B |
|---|---|---|
| LMArena Longer Query | 1308 | 1192 |
Writing & Preference Gemini 1.5 Pro (May 2024) leads
Gemini 1.5 Pro (May 2024): 52.4 (#172), Qwen2-72B: 40.8 (#241)
| Benchmark | Gemini 1.5 Pro (May 2024) | Qwen2-72B |
|---|---|---|
| LMArena Text | 1319 | 1203 |
| LMArena Creative Writing | 1333 | 1181 |
| LMArena Multi-Turn | 1296 | 1196 |
| WildBench | 81.3% | — |
Frequently asked questions
Is Gemini 1.5 Pro (May 2024) better than Qwen2-72B?
Gemini 1.5 Pro (May 2024) is the stronger model overall, scoring 32.1 to 30.0 on the Noometry Index.
Is Gemini 1.5 Pro (May 2024) or Qwen2-72B better for coding?
Gemini 1.5 Pro (May 2024) scores higher on coding benchmarks: 34.2 versus 29.1 in the Noometry coding category.
How many benchmarks do Gemini 1.5 Pro (May 2024) and Qwen2-72B share?
25 benchmarks have published results for both models. Gemini 1.5 Pro (May 2024) has 45 scored results on Noometry and Qwen2-72B has 26.