Model comparison
Gemini 1.5 Flash (May 2024) vs Qwen1.5-32B
Gemini 1.5 Flash (May 2024) is the stronger model overall, scoring 32.9 to 30.0 on the Noometry Index.
Last verified . 21 shared benchmarks.
Google
Alibaba (Qwen)Summary
- They share 21 benchmarks with published results for both. Gemini 1.5 Flash (May 2024) scores higher in 6 categories and Qwen1.5-32B in 2 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Gemini 1.5 Flash (May 2024) leads 48.9 to 34.4.
- The biggest single-benchmark swing is GPQA Diamond: 47.3% for Gemini 1.5 Flash (May 2024) and 30.7% for Qwen1.5-32B.
- Qwen1.5-32B has downloadable open weights; the other is API-only.
Side by side
| Gemini 1.5 Flash (May 2024) | Qwen1.5-32B | |
|---|---|---|
| Provider | Alibaba (Qwen) | |
| Noometry Index | 32.9 | 30.0 |
| Released | 2024-05-14 | 2024-02-04 |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 42 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 1.5 Flash (May 2024) leads
Gemini 1.5 Flash (May 2024): 33.9 (#233), Qwen1.5-32B: 31.1 (#278)
| Benchmark | Gemini 1.5 Flash (May 2024) | Qwen1.5-32B |
|---|---|---|
| BigCodeBench Instruct | 43.5% | 32.3% |
| LMArena Coding | 1262 | 1155 |
| BigCodeBench Complete | 55.1% | 42% |
| WeirdML | 24.9% | — |
| HumanEval+ | 75.6% | — |
| MBPP+ | 67.5% | — |
Agentic & Tool Use Not comparable
Gemini 1.5 Flash (May 2024): 26.3 (#97), Qwen1.5-32B: —
| Benchmark | Gemini 1.5 Flash (May 2024) | Qwen1.5-32B |
|---|---|---|
| BALROG | 14.6% | — |
Reasoning Too close to call
Gemini 1.5 Flash (May 2024): 20.8 (#212), Qwen1.5-32B: 20.9 (#210)
| Benchmark | Gemini 1.5 Flash (May 2024) | Qwen1.5-32B |
|---|---|---|
| LMArena Hard Prompts | 1257 | 1131 |
| DTBench | 53.8% | — |
| Epoch Capabilities Index | 129.37 | — |
| ForecastBench | 53.9 | — |
| PIQA | 87.5% | — |
Math Qwen1.5-32B leads
Gemini 1.5 Flash (May 2024): 20.8 (#274), Qwen1.5-32B: 30.5 (#207)
| Benchmark | Gemini 1.5 Flash (May 2024) | Qwen1.5-32B |
|---|---|---|
| LMArena Math | 1269 | 1155 |
| OTIS Mock AIME 2024-2025 | 16.3% | — |
| Omni-MATH | 30.4% | — |
| MATH Level 5 | 61.9% | — |
| FrontierMath (Feb 2025 set) | 0% | — |
| GSM8K | 82.4% | — |
Knowledge Gemini 1.5 Flash (May 2024) leads
Gemini 1.5 Flash (May 2024): 26.2 (#253), Qwen1.5-32B: 13.5 (#291)
| Benchmark | Gemini 1.5 Flash (May 2024) | Qwen1.5-32B |
|---|---|---|
| GPQA Diamond | 47.3% | 30.7% |
| LMArena Expert | 1233 | 1126 |
| MMLU | 77.9% | 74.4% |
| MMLU-Pro | 67.8% | — |
| GPQA (HELM) | 43.7% | — |
| BoolQ | 85.8% | — |
Multimodal Not comparable
Gemini 1.5 Flash (May 2024): 35.3 (#76), Qwen1.5-32B: —
| Benchmark | Gemini 1.5 Flash (May 2024) | Qwen1.5-32B |
|---|---|---|
| LMArena Vision | 1141 | — |
| Video-MME | 70.3% | — |
| GeoBench | 76% | — |
Multilingual Gemini 1.5 Flash (May 2024) leads
Gemini 1.5 Flash (May 2024): 43.1 (#184), Qwen1.5-32B: 31.6 (#254)
| Benchmark | Gemini 1.5 Flash (May 2024) | Qwen1.5-32B |
|---|---|---|
| LMArena Non-English | 1278 | 1106 |
| LMArena Chinese | 1295 | 1176 |
| LMArena French | 1257 | 1100 |
| LMArena German | 1262 | 1058 |
| LMArena Japanese | 1252 | 1027 |
| LMArena Korean | 1220 | 1007 |
| LMArena Russian | 1288 | 1073 |
| LMArena Spanish | 1242 | 1089 |
Instruction Following Gemini 1.5 Flash (May 2024) leads
Gemini 1.5 Flash (May 2024): 67.0 (#199), Qwen1.5-32B: 58.0 (#260)
| Benchmark | Gemini 1.5 Flash (May 2024) | Qwen1.5-32B |
|---|---|---|
| LMArena Instruction Following | 1258 | 1116 |
| IFEval | 83.1% | — |
Long Context Gemini 1.5 Flash (May 2024) leads
Gemini 1.5 Flash (May 2024): 39.0 (#182), Qwen1.5-32B: 34.7 (#241)
| Benchmark | Gemini 1.5 Flash (May 2024) | Qwen1.5-32B |
|---|---|---|
| LMArena Longer Query | 1284 | 1146 |
Writing & Preference Gemini 1.5 Flash (May 2024) leads
Gemini 1.5 Flash (May 2024): 48.9 (#190), Qwen1.5-32B: 34.4 (#266)
| Benchmark | Gemini 1.5 Flash (May 2024) | Qwen1.5-32B |
|---|---|---|
| LMArena Text | 1287 | 1137 |
| LMArena Creative Writing | 1285 | 1083 |
| LMArena Multi-Turn | 1253 | 1140 |
| WildBench | 79.2% | — |
Frequently asked questions
Is Gemini 1.5 Flash (May 2024) better than Qwen1.5-32B?
Gemini 1.5 Flash (May 2024) is the stronger model overall, scoring 32.9 to 30.0 on the Noometry Index.
Is Gemini 1.5 Flash (May 2024) or Qwen1.5-32B better for coding?
Gemini 1.5 Flash (May 2024) scores higher on coding benchmarks: 33.9 versus 31.1 in the Noometry coding category.
How many benchmarks do Gemini 1.5 Flash (May 2024) and Qwen1.5-32B share?
21 benchmarks have published results for both models. Gemini 1.5 Flash (May 2024) has 42 scored results on Noometry and Qwen1.5-32B has 21.