Model comparison
Gemini 2.0 Flash (Feb 2025) vs Qwen1.5-32B
Gemini 2.0 Flash (Feb 2025) is the stronger model overall, scoring 35.1 to 30.5 on the Noometry Index.
Last verified . 21 shared benchmarks.
Google
Alibaba (Qwen)Summary
- They share 21 benchmarks with published results for both. Gemini 2.0 Flash (Feb 2025) scores higher in 6 categories and Qwen1.5-32B in 2 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Gemini 2.0 Flash (Feb 2025) leads 32.0 to 13.5.
- The biggest single-benchmark swing is GPQA Diamond: 64.1% for Gemini 2.0 Flash (Feb 2025) and 30.7% for Qwen1.5-32B.
- Qwen1.5-32B has downloadable open weights; the other is API-only.
Side by side
| Gemini 2.0 Flash (Feb 2025) | Qwen1.5-32B | |
|---|---|---|
| Provider | Alibaba (Qwen) | |
| Noometry Index | 35.1 | 30.5 |
| Released | 2024-12-06 | 2024-02-04 |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 54 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen1.5-32B leads
Gemini 2.0 Flash (Feb 2025): 28.4 (#315), Qwen1.5-32B: 31.7 (#282)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Qwen1.5-32B |
|---|---|---|
| BigCodeBench Instruct | 45.9% | 32.3% |
| LMArena Coding | 1350 | 1155 |
| BigCodeBench Complete | 59.9% | 42% |
| SWE-bench Verified (bash only) | 13.5% | — |
| Aider Polyglot | 38.2% | — |
| WeirdML | 25.8% | — |
| LiveBench Coding | 63.4% | — |
| CadEval | 30% | — |
Agentic & Tool Use Not comparable
Gemini 2.0 Flash (Feb 2025): 28.1 (#92), Qwen1.5-32B: —
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Qwen1.5-32B |
|---|---|---|
| TheAgentCompany | 11.4% | — |
Reasoning Qwen1.5-32B leads
Gemini 2.0 Flash (Feb 2025): 15.2 (#318), Qwen1.5-32B: 21.8 (#212)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Qwen1.5-32B |
|---|---|---|
| LMArena Hard Prompts | 1346 | 1130 |
| ARC-AGI-2 | 1.3% | — |
| SimpleBench | 31.1% | — |
| Kagi LLM Benchmark | 37.8% | — |
| EnigmaEval | 1.1% | — |
| LiveBench Reasoning | 78.2% | — |
| DTBench | 63.2% | — |
| LiveBench Data Analysis | 69.4% | — |
| Epoch Capabilities Index | 135.36 | — |
| LiveBench | 66.9% | — |
Math Gemini 2.0 Flash (Feb 2025) leads
Gemini 2.0 Flash (Feb 2025): 37.9 (#146), Qwen1.5-32B: 33.0 (#207)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Qwen1.5-32B |
|---|---|---|
| LMArena Math | 1352 | 1155 |
| OTIS Mock AIME 2024-2025 | 57.8% | — |
| Omni-MATH | 45.9% | — |
| LiveBench Math | 75.8% | — |
| MATH Level 5 | 82.2% | — |
| FrontierMath (Feb 2025 set) | 1.7% | — |
Knowledge Gemini 2.0 Flash (Feb 2025) leads
Gemini 2.0 Flash (Feb 2025): 32.0 (#213), Qwen1.5-32B: 13.5 (#296)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Qwen1.5-32B |
|---|---|---|
| GPQA Diamond | 64.1% | 30.7% |
| LMArena Expert | 1339 | 1126 |
| MMLU | 79.7% | 74.4% |
| Humanity's Last Exam | 6.6% | — |
| MMLU-Pro | 73.7% | — |
| Confabulations | 12.4% | — |
| GPQA (HELM) | 55.6% | — |
Multimodal Not comparable
Gemini 2.0 Flash (Feb 2025): 36.5 (#79), Qwen1.5-32B: —
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Qwen1.5-32B |
|---|---|---|
| LMArena Vision | 1158 | — |
| GeoBench | 77% | — |
Multilingual Gemini 2.0 Flash (Feb 2025) leads
Gemini 2.0 Flash (Feb 2025): 47.4 (#149), Qwen1.5-32B: 31.4 (#259)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Qwen1.5-32B |
|---|---|---|
| LMArena Non-English | 1342 | 1106 |
| LMArena Chinese | 1373 | 1177 |
| LMArena French | 1391 | 1101 |
| LMArena German | 1353 | 1058 |
| LMArena Japanese | 1294 | 1027 |
| LMArena Korean | 1313 | 1008 |
| LMArena Russian | 1351 | 1073 |
| LMArena Spanish | 1363 | 1089 |
Instruction Following Gemini 2.0 Flash (Feb 2025) leads
Gemini 2.0 Flash (Feb 2025): 74.4 (#97), Qwen1.5-32B: 57.7 (#265)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Qwen1.5-32B |
|---|---|---|
| LMArena Instruction Following | 1336 | 1116 |
| LiveBench Instruction Following | 85.8% | — |
| IFEval | 84.1% | — |
Long Context Gemini 2.0 Flash (Feb 2025) leads
Gemini 2.0 Flash (Feb 2025): 38.1 (#203), Qwen1.5-32B: 34.7 (#246)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Qwen1.5-32B |
|---|---|---|
| LMArena Longer Query | 1344 | 1146 |
| Fiction.LiveBench | 61.1% | — |
Writing & Preference Gemini 2.0 Flash (Feb 2025) leads
Gemini 2.0 Flash (Feb 2025): 49.5 (#190), Qwen1.5-32B: 34.2 (#271)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Qwen1.5-32B |
|---|---|---|
| LMArena Text | 1354 | 1137 |
| LMArena Creative Writing | 1340 | 1083 |
| LMArena Multi-Turn | 1350 | 1140 |
| 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 Qwen1.5-32B?
Gemini 2.0 Flash (Feb 2025) is the stronger model overall, scoring 35.1 to 30.5 on the Noometry Index.
Is Gemini 2.0 Flash (Feb 2025) or Qwen1.5-32B better for coding?
Qwen1.5-32B scores higher on coding benchmarks: 31.7 versus 28.4 in the Noometry coding category.
How many benchmarks do Gemini 2.0 Flash (Feb 2025) and Qwen1.5-32B share?
21 benchmarks have published results for both models. Gemini 2.0 Flash (Feb 2025) has 54 scored results on Noometry and Qwen1.5-32B has 21.