Model comparison
Gemini 1.5 Pro (May 2024) vs Qwen2.5-Coder-32B
Qwen2.5-Coder-32B is the stronger model overall, scoring 33.4 to 32.1 on the Noometry Index.
Last verified . 18 shared benchmarks.
Google
Alibaba (Qwen)Summary
- They share 18 benchmarks with published results for both. Gemini 1.5 Pro (May 2024) scores higher in 5 categories and Qwen2.5-Coder-32B in 3 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in coding, where Gemini 1.5 Pro (May 2024) leads 34.2 to 22.6.
- The biggest single-benchmark swing is BigCodeBench Instruct: 43.8% for Gemini 1.5 Pro (May 2024) and 49% for Qwen2.5-Coder-32B.
- Qwen2.5-Coder-32B has downloadable open weights; the other is API-only.
Side by side
| Gemini 1.5 Pro (May 2024) | Qwen2.5-Coder-32B | |
|---|---|---|
| Provider | Alibaba (Qwen) | |
| Noometry Index | 32.1 | 33.4 |
| Released | 2024-02-15 | 2024-09-18 |
| Weights | Proprietary | Open |
| Context window | — | 33K |
| Max output | — | 29K |
| Input $ / M tokens | — | $0.66 |
| Output $ / M tokens | — | $1 |
| Results tracked | 45 | 31 |
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), Qwen2.5-Coder-32B: 22.6 (#333)
| Benchmark | Gemini 1.5 Pro (May 2024) | Qwen2.5-Coder-32B |
|---|---|---|
| BigCodeBench Instruct | 43.8% | 49% |
| LMArena Coding | 1294 | 1276 |
| BigCodeBench Complete | 57.5% | 58% |
| HumanEval+ | 79.3% | 87.2% |
| MBPP+ | 74.6% | 77% |
| SWE-bench Verified (bash only) | — | 9% |
| Aider Polyglot | — | 16.4% |
| WeirdML | 22.2% | — |
| LiveBench Coding | — | 56.9% |
| CadEval | 34% | — |
Agentic & Tool Use Not comparable
Gemini 1.5 Pro (May 2024): 17.9 (#145), Qwen2.5-Coder-32B: —
| Benchmark | Gemini 1.5 Pro (May 2024) | Qwen2.5-Coder-32B |
|---|---|---|
| TheAgentCompany | 3.4% | — |
| Cybench | 7.5% | — |
| BALROG | 21% | — |
Reasoning Qwen2.5-Coder-32B leads
Gemini 1.5 Pro (May 2024): 12.3 (#338), Qwen2.5-Coder-32B: 21.2 (#225)
| Benchmark | Gemini 1.5 Pro (May 2024) | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Hard Prompts | 1296 | 1251 |
| Epoch Capabilities Index | 131.73 | 119.49 |
| ARC-AGI-2 | 0.8% | — |
| SimpleBench | 27.1% | — |
| LiveBench Reasoning | — | 42.1% |
| DTBench | 59% | — |
| LiveBench Data Analysis | — | 49.9% |
| BIG-Bench Hard | 89.2% | — |
| ForecastBench | 58.4 | — |
| HellaSwag | — | 83% |
| LiveBench | — | 46.2% |
| WinoGrande | — | 80.8% |
Math Qwen2.5-Coder-32B leads
Gemini 1.5 Pro (May 2024): 25.8 (#266), Qwen2.5-Coder-32B: 33.3 (#204)
| Benchmark | Gemini 1.5 Pro (May 2024) | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Math | 1315 | 1251 |
| OTIS Mock AIME 2024-2025 | 23.1% | — |
| Omni-MATH | 36.4% | — |
| LiveBench Math | — | 46.6% |
| MATH Level 5 | 70.4% | — |
| GSM8K | — | 93% |
Knowledge Qwen2.5-Coder-32B leads
Gemini 1.5 Pro (May 2024): 29.4 (#239), Qwen2.5-Coder-32B: 33.4 (#203)
| Benchmark | Gemini 1.5 Pro (May 2024) | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Expert | 1279 | 1221 |
| MMLU | 86.9% | 79.1% |
| GPQA Diamond | 57.2% | — |
| Humanity's Last Exam | 4.6% | — |
| MMLU-Pro | 73.7% | — |
| Confabulations | 13.5% | — |
| GPQA (HELM) | 53.4% | — |
| ARC (AI2) Challenge | — | 70.5% |
Multimodal Not comparable
Gemini 1.5 Pro (May 2024): 36.8 (#77), Qwen2.5-Coder-32B: —
| Benchmark | Gemini 1.5 Pro (May 2024) | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Vision | 1161 | — |
| Video-MME | 75% | — |
Multilingual Gemini 1.5 Pro (May 2024) leads
Gemini 1.5 Pro (May 2024): 45.3 (#174), Qwen2.5-Coder-32B: 37.8 (#235)
| Benchmark | Gemini 1.5 Pro (May 2024) | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Non-English | 1312 | 1205 |
| LMArena Chinese | 1331 | 1222 |
| LMArena Russian | 1320 | 1228 |
| LMArena French | 1302 | — |
| LMArena German | 1286 | — |
| LMArena Japanese | 1292 | — |
| LMArena Korean | 1298 | — |
| LMArena Spanish | 1311 | — |
Instruction Following Gemini 1.5 Pro (May 2024) leads
Gemini 1.5 Pro (May 2024): 68.6 (#185), Qwen2.5-Coder-32B: 61.4 (#245)
| Benchmark | Gemini 1.5 Pro (May 2024) | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Instruction Following | 1297 | 1223 |
| LiveBench Instruction Following | — | 58.7% |
| IFEval | 83.7% | — |
Long Context Gemini 1.5 Pro (May 2024) leads
Gemini 1.5 Pro (May 2024): 39.8 (#169), Qwen2.5-Coder-32B: 38.0 (#208)
| Benchmark | Gemini 1.5 Pro (May 2024) | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Longer Query | 1308 | 1251 |
Writing & Preference Gemini 1.5 Pro (May 2024) leads
Gemini 1.5 Pro (May 2024): 52.4 (#172), Qwen2.5-Coder-32B: 41.6 (#240)
| Benchmark | Gemini 1.5 Pro (May 2024) | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Text | 1319 | 1230 |
| LMArena Creative Writing | 1333 | 1174 |
| LMArena Multi-Turn | 1296 | 1222 |
| WildBench | 81.3% | — |
| LiveBench Language | — | 23.3% |
Frequently asked questions
Is Gemini 1.5 Pro (May 2024) better than Qwen2.5-Coder-32B?
Qwen2.5-Coder-32B is the stronger model overall, scoring 33.4 to 32.1 on the Noometry Index.
Is Gemini 1.5 Pro (May 2024) or Qwen2.5-Coder-32B better for coding?
Gemini 1.5 Pro (May 2024) scores higher on coding benchmarks: 34.2 versus 22.6 in the Noometry coding category.
How many benchmarks do Gemini 1.5 Pro (May 2024) and Qwen2.5-Coder-32B share?
18 benchmarks have published results for both models. Gemini 1.5 Pro (May 2024) has 45 scored results on Noometry and Qwen2.5-Coder-32B has 31.