Model comparison
Gemini 3 Pro vs Qwen2.5-Coder-32B
Gemini 3 Pro is the stronger model overall, scoring 54.8 to 33.4 on the Noometry Index.
Last verified . 14 shared benchmarks.
Google
Alibaba (Qwen)Summary
- They share 14 benchmarks with published results for both. Gemini 3 Pro scores higher in 8 categories and Qwen2.5-Coder-32B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Gemini 3 Pro leads 52.5 to 21.2.
- The biggest single-benchmark swing is SWE-bench Verified (bash only): 74.2% for Gemini 3 Pro and 9% for Qwen2.5-Coder-32B.
- Qwen2.5-Coder-32B has downloadable open weights; the other is API-only.
Side by side
| Gemini 3 Pro | Qwen2.5-Coder-32B | |
|---|---|---|
| Provider | Alibaba (Qwen) | |
| Noometry Index | 54.8 | 33.4 |
| Released | 2025-11-18 | 2024-09-18 |
| Weights | Proprietary | Open |
| Context window | — | 33K |
| Max output | — | 29K |
| Input $ / M tokens | — | $0.66 |
| Output $ / M tokens | — | $1 |
| Results tracked | 67 | 31 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 3 Pro leads
Gemini 3 Pro: 51.6 (#39), Qwen2.5-Coder-32B: 22.6 (#333)
| Benchmark | Gemini 3 Pro | Qwen2.5-Coder-32B |
|---|---|---|
| SWE-bench Verified (bash only) | 74.2% | 9% |
| LMArena Coding | 1481 | 1276 |
| SWE-bench Verified | 72.9% | — |
| Aider Polyglot | — | 16.4% |
| LMArena WebDev | 1440 | — |
| SWE-bench Multilingual | 68.7% | — |
| GSO | 18.6% | — |
| WeirdML | 69.9% | — |
| BigCodeBench Instruct | — | 49% |
| LiveBench Coding | — | 56.9% |
| BigCodeBench Complete | — | 58% |
| ALE-Bench | 1,177 | — |
| AlgoTune | 1.83 | — |
| HumanEval+ | — | 87.2% |
| MBPP+ | — | 77% |
Agentic & Tool Use Not comparable
Gemini 3 Pro: 40.6 (#23), Qwen2.5-Coder-32B: —
| Benchmark | Gemini 3 Pro | Qwen2.5-Coder-32B |
|---|---|---|
| Terminal-Bench | 69.4% | — |
| Berkeley Function Calling Leaderboard | 72.5% | — |
| GDPval | 40.3% | — |
| Remote Labor Index | 1.3% | — |
| τ²-bench Airline | 80.5% | — |
| τ²-bench Banking | 18% | — |
| τ²-bench Retail | 75.9% | — |
| τ²-bench Telecom | 91% | — |
| DeepResearch Bench | 46.3% | — |
| BALROG | 58.1% | — |
| LMArena Search | 1207 | — |
| METR Time Horizons | 71% | — |
| Vending-Bench 2 | 5,478 | — |
Reasoning Gemini 3 Pro leads
Gemini 3 Pro: 52.5 (#31), Qwen2.5-Coder-32B: 21.2 (#225)
| Benchmark | Gemini 3 Pro | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Hard Prompts | 1480 | 1251 |
| Epoch Capabilities Index | 152.92 | 119.49 |
| ARC-AGI-2 | 31.1% | — |
| SimpleBench | 76.4% | — |
| Kagi LLM Benchmark | 80.1% | — |
| NYT Connections (extended) | 94.4% | — |
| ARC-AGI-1 | 75% | — |
| CritPt | 6.9% | — |
| Chess Puzzles | 31% | — |
| EnigmaEval | 18.2% | — |
| LiveBench Reasoning | — | 42.1% |
| LiveBench Data Analysis | — | 49.9% |
| ForecastBench | 61.2 | — |
| HellaSwag | — | 83% |
| LiveBench | — | 46.2% |
| WinoGrande | — | 80.8% |
Math Gemini 3 Pro leads
Gemini 3 Pro: 49.9 (#59), Qwen2.5-Coder-32B: 33.3 (#204)
| Benchmark | Gemini 3 Pro | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Math | 1476 | 1251 |
| MathArena Final-Answer Competitions | 67% | — |
| OTIS Mock AIME 2024-2025 | 91.4% | — |
| ProofBench | 20% | — |
| Omni-MATH | 55.5% | — |
| LiveBench Math | — | 46.6% |
| FrontierMath (Feb 2025 set) | 37.6% | — |
| FrontierMath Tier 4 (v1) | 18.8% | — |
| GSM8K | — | 93% |
Knowledge Gemini 3 Pro leads
Gemini 3 Pro: 64.4 (#16), Qwen2.5-Coder-32B: 33.4 (#203)
| Benchmark | Gemini 3 Pro | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Expert | 1475 | 1221 |
| GPQA Diamond | 92.6% | — |
| Humanity's Last Exam | 37.5% | — |
| MMLU-Pro | 90.3% | — |
| Vectara Hallucination Rate | 13.6% | — |
| GPQA (HELM) | 80.3% | — |
| ARC (AI2) Challenge | — | 70.5% |
| MMLU | — | 79.1% |
Multimodal Not comparable
Gemini 3 Pro: 57.6 (#2), Qwen2.5-Coder-32B: —
| Benchmark | Gemini 3 Pro | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Vision | 1305 | — |
| GeoBench | 84% | — |
| VPCT | 91% | — |
| LMArena Document | 1434 | — |
Multilingual Gemini 3 Pro leads
Gemini 3 Pro: 56.9 (#16), Qwen2.5-Coder-32B: 37.8 (#235)
| Benchmark | Gemini 3 Pro | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Non-English | 1474 | 1205 |
| LMArena Chinese | 1523 | 1222 |
| LMArena Russian | 1493 | 1228 |
| LMArena French | 1492 | — |
| LMArena German | 1515 | — |
| LMArena Japanese | 1510 | — |
| LMArena Korean | 1448 | — |
| LMArena Spanish | 1470 | — |
Instruction Following Gemini 3 Pro leads
Gemini 3 Pro: 76.3 (#45), Qwen2.5-Coder-32B: 61.4 (#245)
| Benchmark | Gemini 3 Pro | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Instruction Following | 1458 | 1223 |
| LiveBench Instruction Following | — | 58.7% |
| IFEval | 87.7% | — |
Long Context Gemini 3 Pro leads
Gemini 3 Pro: 44.0 (#79), Qwen2.5-Coder-32B: 38.0 (#208)
| Benchmark | Gemini 3 Pro | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Longer Query | 1471 | 1251 |
| CL-bench | 15.8% | — |
Writing & Preference Gemini 3 Pro leads
Gemini 3 Pro: 66.4 (#35), Qwen2.5-Coder-32B: 41.6 (#240)
| Benchmark | Gemini 3 Pro | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Text | 1479 | 1230 |
| LMArena Creative Writing | 1482 | 1174 |
| LMArena Multi-Turn | 1484 | 1222 |
| EQ-Bench Creative Writing | 1525 | — |
| WildBench | 85.9% | — |
| LiveBench Language | — | 23.3% |
Frequently asked questions
Is Gemini 3 Pro better than Qwen2.5-Coder-32B?
Gemini 3 Pro is the stronger model overall, scoring 54.8 to 33.4 on the Noometry Index.
Is Gemini 3 Pro or Qwen2.5-Coder-32B better for coding?
Gemini 3 Pro scores higher on coding benchmarks: 51.6 versus 22.6 in the Noometry coding category.
How many benchmarks do Gemini 3 Pro and Qwen2.5-Coder-32B share?
14 benchmarks have published results for both models. Gemini 3 Pro has 67 scored results on Noometry and Qwen2.5-Coder-32B has 31.