Model comparison
Gemini 2.0 Flash (Feb 2025) vs Qwen3 32B
Qwen3 32B is the stronger model overall, scoring 39.2 to 35.1 on the Noometry Index.
Last verified . 20 shared benchmarks.
Google
Alibaba (Qwen)Summary
- They share 20 benchmarks with published results for both. Gemini 2.0 Flash (Feb 2025) scores higher in 2 categories and Qwen3 32B in 7 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in coding, where Qwen3 32B leads 37.7 to 28.4.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 37.8% for Gemini 2.0 Flash (Feb 2025) and 54.9% for Qwen3 32B.
- Qwen3 32B has downloadable open weights; the other is API-only.
Side by side
| Gemini 2.0 Flash (Feb 2025) | Qwen3 32B | |
|---|---|---|
| Provider | Alibaba (Qwen) | |
| Noometry Index | 35.1 | 39.2 |
| Released | 2024-12-06 | 2025-04 |
| Weights | Proprietary | Open |
| Context window | — | 131K |
| Max output | — | 16K |
| Input $ / M tokens | — | $0.70 |
| Output $ / M tokens | — | $2.80 |
| Results tracked | 54 | 26 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3 32B leads
Gemini 2.0 Flash (Feb 2025): 28.4 (#315), Qwen3 32B: 37.7 (#190)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Qwen3 32B |
|---|---|---|
| Aider Polyglot | 38.2% | 40% |
| LMArena Coding | 1350 | 1358 |
| SWE-bench Verified (bash only) | 13.5% | — |
| SciCode | — | 35.4% |
| WeirdML | 25.8% | — |
| BigCodeBench Instruct | 45.9% | — |
| LiveBench Coding | 63.4% | — |
| BigCodeBench Complete | 59.9% | — |
| CadEval | 30% | — |
Agentic & Tool Use Qwen3 32B leads
Gemini 2.0 Flash (Feb 2025): 28.1 (#92), Qwen3 32B: 32.6 (#62)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Qwen3 32B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 48.7% |
| TheAgentCompany | 11.4% | — |
Reasoning Qwen3 32B leads
Gemini 2.0 Flash (Feb 2025): 15.2 (#318), Qwen3 32B: 20.2 (#241)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Qwen3 32B |
|---|---|---|
| Kagi LLM Benchmark | 37.8% | 54.9% |
| LMArena Hard Prompts | 1346 | 1334 |
| DTBench | 63.2% | 67.5% |
| Epoch Capabilities Index | 135.36 | 138.51 |
| ARC-AGI-2 | 1.3% | — |
| SimpleBench | 31.1% | — |
| CritPt | — | 0.3% |
| Chess Puzzles | — | 5% |
| EnigmaEval | 1.1% | — |
| LiveBench Reasoning | 78.2% | — |
| LiveBench Data Analysis | 69.4% | — |
| LMCA | — | 17.3% |
| LiveBench | 66.9% | — |
Math Qwen3 32B leads
Gemini 2.0 Flash (Feb 2025): 37.9 (#146), Qwen3 32B: 39.7 (#99)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Qwen3 32B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 57.8% | 66.9% |
| LMArena Math | 1352 | 1399 |
| Omni-MATH | 45.9% | — |
| LiveBench Math | 75.8% | — |
| MATH Level 5 | 82.2% | — |
| FrontierMath (Feb 2025 set) | 1.7% | — |
Knowledge Qwen3 32B leads
Gemini 2.0 Flash (Feb 2025): 32.0 (#213), Qwen3 32B: 40.0 (#125)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Qwen3 32B |
|---|---|---|
| GPQA Diamond | 64.1% | 65.7% |
| LMArena Expert | 1339 | 1362 |
| Humanity's Last Exam | 6.6% | — |
| MMLU-Pro | 73.7% | — |
| Confabulations | 12.4% | — |
| Vectara Hallucination Rate | — | 5.9% |
| GPQA (HELM) | 55.6% | — |
| MMLU | 79.7% | — |
Multimodal Not comparable
Gemini 2.0 Flash (Feb 2025): 36.5 (#79), Qwen3 32B: —
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Qwen3 32B |
|---|---|---|
| LMArena Vision | 1158 | — |
| GeoBench | 77% | — |
Multilingual Gemini 2.0 Flash (Feb 2025) leads
Gemini 2.0 Flash (Feb 2025): 47.4 (#149), Qwen3 32B: 45.6 (#167)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Qwen3 32B |
|---|---|---|
| LMArena Non-English | 1342 | 1317 |
| LMArena Chinese | 1373 | 1357 |
| LMArena German | 1353 | 1341 |
| LMArena Russian | 1351 | 1311 |
| LMArena French | 1391 | — |
| LMArena Japanese | 1294 | — |
| LMArena Korean | 1313 | — |
| LMArena Spanish | 1363 | — |
Instruction Following Gemini 2.0 Flash (Feb 2025) leads
Gemini 2.0 Flash (Feb 2025): 74.4 (#97), Qwen3 32B: 68.9 (#179)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Qwen3 32B |
|---|---|---|
| LMArena Instruction Following | 1336 | 1305 |
| LiveBench Instruction Following | 85.8% | — |
| IFEval | 84.1% | — |
Long Context Qwen3 32B leads
Gemini 2.0 Flash (Feb 2025): 38.1 (#203), Qwen3 32B: 43.8 (#87)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Qwen3 32B |
|---|---|---|
| Fiction.LiveBench | 61.1% | 74.2% |
| LMArena Longer Query | 1344 | 1327 |
Writing & Preference Qwen3 32B leads
Gemini 2.0 Flash (Feb 2025): 49.5 (#190), Qwen3 32B: 52.9 (#163)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Qwen3 32B |
|---|---|---|
| LMArena Text | 1354 | 1340 |
| LMArena Creative Writing | 1340 | 1297 |
| LMArena Multi-Turn | 1350 | 1331 |
| Short-Story Creative Writing | 73.8% | — |
| EQ-Bench Creative Writing | 1128 | — |
| WildBench | 80% | — |
| LiveBench Language | 51.3% | — |
Frequently asked questions
Is Gemini 2.0 Flash (Feb 2025) better than Qwen3 32B?
Qwen3 32B is the stronger model overall, scoring 39.2 to 35.1 on the Noometry Index.
Is Gemini 2.0 Flash (Feb 2025) or Qwen3 32B better for coding?
Qwen3 32B scores higher on coding benchmarks: 37.7 versus 28.4 in the Noometry coding category.
How many benchmarks do Gemini 2.0 Flash (Feb 2025) and Qwen3 32B share?
20 benchmarks have published results for both models. Gemini 2.0 Flash (Feb 2025) has 54 scored results on Noometry and Qwen3 32B has 26.