Model comparison
Gemini 2.0 Flash (Feb 2025) vs Qwen2.5-Coder-32B
Gemini 2.0 Flash (Feb 2025) is the stronger model overall, scoring 34.8 to 32.9 on the Noometry Index.
Last verified . 25 shared benchmarks.
Google
Alibaba (Qwen)Summary
- They share 25 benchmarks with published results for both. Gemini 2.0 Flash (Feb 2025) scores higher in 6 categories and Qwen2.5-Coder-32B in 2 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in instruction following, where Gemini 2.0 Flash (Feb 2025) leads 74.6 to 61.6.
- The biggest single-benchmark swing is LiveBench Reasoning: 78.2% for Gemini 2.0 Flash (Feb 2025) and 42.1% for Qwen2.5-Coder-32B.
- Qwen2.5-Coder-32B has downloadable open weights; the other is API-only.
Side by side
| Gemini 2.0 Flash (Feb 2025) | Qwen2.5-Coder-32B | |
|---|---|---|
| Provider | Alibaba (Qwen) | |
| Noometry Index | 34.8 | 32.9 |
| Released | 2024-12-06 | 2024-09-18 |
| Weights | Proprietary | Open |
| Context window | — | 33K |
| Max output | — | 29K |
| Input $ / M tokens | — | $0.66 |
| Output $ / M tokens | — | $1 |
| Results tracked | 54 | 31 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 2.0 Flash (Feb 2025) leads
Gemini 2.0 Flash (Feb 2025): 28.2 (#308), Qwen2.5-Coder-32B: 22.4 (#328)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Qwen2.5-Coder-32B |
|---|---|---|
| SWE-bench Verified (bash only) | 13.5% | 9% |
| Aider Polyglot | 38.2% | 16.4% |
| BigCodeBench Instruct | 45.9% | 49% |
| LiveBench Coding | 63.4% | 56.9% |
| LMArena Coding | 1351 | 1276 |
| BigCodeBench Complete | 59.9% | 58% |
| WeirdML | 25.8% | — |
| CadEval | 30% | — |
| HumanEval+ | — | 87.2% |
| MBPP+ | — | 77% |
Agentic & Tool Use Not comparable
Gemini 2.0 Flash (Feb 2025): 28.0 (#85), Qwen2.5-Coder-32B: —
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Qwen2.5-Coder-32B |
|---|---|---|
| TheAgentCompany | 11.4% | — |
Reasoning Qwen2.5-Coder-32B leads
Gemini 2.0 Flash (Feb 2025): 15.2 (#308), Qwen2.5-Coder-32B: 20.4 (#220)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Qwen2.5-Coder-32B |
|---|---|---|
| LiveBench Reasoning | 78.2% | 42.1% |
| LMArena Hard Prompts | 1346 | 1251 |
| LiveBench Data Analysis | 69.4% | 49.9% |
| Epoch Capabilities Index | 135.36 | 119.41 |
| LiveBench | 66.9% | 46.2% |
| ARC-AGI-2 | 1.3% | — |
| SimpleBench | 31.1% | — |
| Kagi LLM Benchmark | 37.8% | — |
| EnigmaEval | 1.1% | — |
| DTBench | 63.2% | — |
| HellaSwag | — | 83% |
| WinoGrande | — | 80.8% |
Math Gemini 2.0 Flash (Feb 2025) leads
Gemini 2.0 Flash (Feb 2025): 36.1 (#127), Qwen2.5-Coder-32B: 30.8 (#203)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Qwen2.5-Coder-32B |
|---|---|---|
| LiveBench Math | 75.8% | 46.6% |
| LMArena Math | 1351 | 1251 |
| OTIS Mock AIME 2024-2025 | 57.8% | — |
| Omni-MATH | 45.9% | — |
| MATH Level 5 | 82.2% | — |
| FrontierMath (Feb 2025 set) | 1.7% | — |
| GSM8K | — | 93% |
Knowledge Too close to call
Gemini 2.0 Flash (Feb 2025): 32.0 (#207), Qwen2.5-Coder-32B: 32.9 (#200)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Expert | 1340 | 1221 |
| MMLU | 79.7% | 79.1% |
| GPQA Diamond | 64.1% | — |
| Humanity's Last Exam | 6.6% | — |
| MMLU-Pro | 73.7% | — |
| Confabulations | 12.4% | — |
| GPQA (HELM) | 55.6% | — |
| ARC (AI2) Challenge | — | 70.5% |
Multimodal Not comparable
Gemini 2.0 Flash (Feb 2025): 35.9 (#74), Qwen2.5-Coder-32B: —
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Vision | 1158 | — |
| GeoBench | 77% | — |
Multilingual Gemini 2.0 Flash (Feb 2025) leads
Gemini 2.0 Flash (Feb 2025): 47.6 (#144), Qwen2.5-Coder-32B: 38.0 (#230)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Non-English | 1342 | 1205 |
| LMArena Chinese | 1373 | 1222 |
| LMArena Russian | 1351 | 1228 |
| LMArena French | 1390 | — |
| LMArena German | 1354 | — |
| LMArena Japanese | 1293 | — |
| LMArena Korean | 1314 | — |
| LMArena Spanish | 1363 | — |
Instruction Following Gemini 2.0 Flash (Feb 2025) leads
Gemini 2.0 Flash (Feb 2025): 74.6 (#91), Qwen2.5-Coder-32B: 61.6 (#240)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Qwen2.5-Coder-32B |
|---|---|---|
| LiveBench Instruction Following | 85.8% | 58.7% |
| LMArena Instruction Following | 1336 | 1223 |
| IFEval | 84.1% | — |
Long Context Too close to call
Gemini 2.0 Flash (Feb 2025): 38.1 (#198), Qwen2.5-Coder-32B: 37.9 (#204)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Longer Query | 1345 | 1251 |
| Fiction.LiveBench | 61.1% | — |
Writing & Preference Gemini 2.0 Flash (Feb 2025) leads
Gemini 2.0 Flash (Feb 2025): 49.8 (#184), Qwen2.5-Coder-32B: 41.8 (#235)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Text | 1354 | 1230 |
| LMArena Creative Writing | 1340 | 1174 |
| LMArena Multi-Turn | 1350 | 1222 |
| LiveBench Language | 51.3% | 23.3% |
| Short-Story Creative Writing | 73.8% | — |
| EQ-Bench Creative Writing | 1128 | — |
| WildBench | 80% | — |
Frequently asked questions
Is Gemini 2.0 Flash (Feb 2025) better than Qwen2.5-Coder-32B?
Gemini 2.0 Flash (Feb 2025) is the stronger model overall, scoring 34.8 to 32.9 on the Noometry Index.
Is Gemini 2.0 Flash (Feb 2025) or Qwen2.5-Coder-32B better for coding?
Gemini 2.0 Flash (Feb 2025) scores higher on coding benchmarks: 28.2 versus 22.4 in the Noometry coding category.
How many benchmarks do Gemini 2.0 Flash (Feb 2025) and Qwen2.5-Coder-32B share?
25 benchmarks have published results for both models. Gemini 2.0 Flash (Feb 2025) has 54 scored results on Noometry and Qwen2.5-Coder-32B has 31.