Model comparison
Gemini 1.5 Pro (May 2024) vs Qwen3 32B
Qwen3 32B is the stronger model overall, scoring 39.2 to 32.1 on the Noometry Index.
Last verified . 17 shared benchmarks.
Google
Alibaba (Qwen)Summary
- They share 17 benchmarks with published results for both. Gemini 1.5 Pro (May 2024) scores higher in 0 categories and Qwen3 32B in 9 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in agentic & tool use, where Qwen3 32B leads 32.6 to 17.9.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 23.1% for Gemini 1.5 Pro (May 2024) and 66.9% for Qwen3 32B.
- Qwen3 32B has downloadable open weights; the other is API-only.
Side by side
| Gemini 1.5 Pro (May 2024) | Qwen3 32B | |
|---|---|---|
| Provider | Alibaba (Qwen) | |
| Noometry Index | 32.1 | 39.2 |
| Released | 2024-02-15 | 2025-04 |
| Weights | Proprietary | Open |
| Context window | — | 131K |
| Max output | — | 16K |
| Input $ / M tokens | — | $0.70 |
| Output $ / M tokens | — | $2.80 |
| Results tracked | 45 | 26 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3 32B leads
Gemini 1.5 Pro (May 2024): 34.2 (#241), Qwen3 32B: 37.7 (#190)
| Benchmark | Gemini 1.5 Pro (May 2024) | Qwen3 32B |
|---|---|---|
| LMArena Coding | 1294 | 1358 |
| Aider Polyglot | — | 40% |
| SciCode | — | 35.4% |
| WeirdML | 22.2% | — |
| BigCodeBench Instruct | 43.8% | — |
| BigCodeBench Complete | 57.5% | — |
| CadEval | 34% | — |
| HumanEval+ | 79.3% | — |
| MBPP+ | 74.6% | — |
Agentic & Tool Use Qwen3 32B leads
Gemini 1.5 Pro (May 2024): 17.9 (#145), Qwen3 32B: 32.6 (#62)
| Benchmark | Gemini 1.5 Pro (May 2024) | Qwen3 32B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 48.7% |
| TheAgentCompany | 3.4% | — |
| Cybench | 7.5% | — |
| BALROG | 21% | — |
Reasoning Qwen3 32B leads
Gemini 1.5 Pro (May 2024): 12.3 (#338), Qwen3 32B: 20.2 (#241)
| Benchmark | Gemini 1.5 Pro (May 2024) | Qwen3 32B |
|---|---|---|
| LMArena Hard Prompts | 1296 | 1334 |
| DTBench | 59% | 67.5% |
| Epoch Capabilities Index | 131.73 | 138.51 |
| ARC-AGI-2 | 0.8% | — |
| SimpleBench | 27.1% | — |
| Kagi LLM Benchmark | — | 54.9% |
| CritPt | — | 0.3% |
| Chess Puzzles | — | 5% |
| LMCA | — | 17.3% |
| BIG-Bench Hard | 89.2% | — |
| ForecastBench | 58.4 | — |
Math Qwen3 32B leads
Gemini 1.5 Pro (May 2024): 25.8 (#266), Qwen3 32B: 39.7 (#99)
| Benchmark | Gemini 1.5 Pro (May 2024) | Qwen3 32B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 23.1% | 66.9% |
| LMArena Math | 1315 | 1399 |
| Omni-MATH | 36.4% | — |
| MATH Level 5 | 70.4% | — |
Knowledge Qwen3 32B leads
Gemini 1.5 Pro (May 2024): 29.4 (#239), Qwen3 32B: 40.0 (#125)
| Benchmark | Gemini 1.5 Pro (May 2024) | Qwen3 32B |
|---|---|---|
| GPQA Diamond | 57.2% | 65.7% |
| LMArena Expert | 1279 | 1362 |
| Humanity's Last Exam | 4.6% | — |
| MMLU-Pro | 73.7% | — |
| Confabulations | 13.5% | — |
| Vectara Hallucination Rate | — | 5.9% |
| GPQA (HELM) | 53.4% | — |
| MMLU | 86.9% | — |
Multimodal Not comparable
Gemini 1.5 Pro (May 2024): 36.8 (#77), Qwen3 32B: —
| Benchmark | Gemini 1.5 Pro (May 2024) | Qwen3 32B |
|---|---|---|
| LMArena Vision | 1161 | — |
| Video-MME | 75% | — |
Multilingual Too close to call
Gemini 1.5 Pro (May 2024): 45.3 (#174), Qwen3 32B: 45.6 (#167)
| Benchmark | Gemini 1.5 Pro (May 2024) | Qwen3 32B |
|---|---|---|
| LMArena Non-English | 1312 | 1317 |
| LMArena Chinese | 1331 | 1357 |
| LMArena German | 1286 | 1341 |
| LMArena Russian | 1320 | 1311 |
| LMArena French | 1302 | — |
| LMArena Japanese | 1292 | — |
| LMArena Korean | 1298 | — |
| LMArena Spanish | 1311 | — |
Instruction Following Too close to call
Gemini 1.5 Pro (May 2024): 68.6 (#185), Qwen3 32B: 68.9 (#179)
| Benchmark | Gemini 1.5 Pro (May 2024) | Qwen3 32B |
|---|---|---|
| LMArena Instruction Following | 1297 | 1305 |
| IFEval | 83.7% | — |
Long Context Qwen3 32B leads
Gemini 1.5 Pro (May 2024): 39.8 (#169), Qwen3 32B: 43.8 (#87)
| Benchmark | Gemini 1.5 Pro (May 2024) | Qwen3 32B |
|---|---|---|
| LMArena Longer Query | 1308 | 1327 |
| Fiction.LiveBench | — | 74.2% |
Writing & Preference Too close to call
Gemini 1.5 Pro (May 2024): 52.4 (#172), Qwen3 32B: 52.9 (#163)
| Benchmark | Gemini 1.5 Pro (May 2024) | Qwen3 32B |
|---|---|---|
| LMArena Text | 1319 | 1340 |
| LMArena Creative Writing | 1333 | 1297 |
| LMArena Multi-Turn | 1296 | 1331 |
| WildBench | 81.3% | — |
Frequently asked questions
Is Gemini 1.5 Pro (May 2024) better than Qwen3 32B?
Qwen3 32B is the stronger model overall, scoring 39.2 to 32.1 on the Noometry Index.
Is Gemini 1.5 Pro (May 2024) or Qwen3 32B better for coding?
Qwen3 32B scores higher on coding benchmarks: 37.7 versus 34.2 in the Noometry coding category.
How many benchmarks do Gemini 1.5 Pro (May 2024) and Qwen3 32B share?
17 benchmarks have published results for both models. Gemini 1.5 Pro (May 2024) has 45 scored results on Noometry and Qwen3 32B has 26.