Model comparison
Gemini 1.5 Flash (May 2024) vs Qwen2.5 72B Instruct
Gemini 1.5 Flash (May 2024) is the stronger model overall, scoring 33.2 to 31.9 on the Noometry Index.
Last verified . 34 shared benchmarks.
Google
Alibaba (Qwen)Summary
- They share 34 benchmarks with published results for both. Gemini 1.5 Flash (May 2024) scores higher in 7 categories and Qwen2.5 72B Instruct in 2 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in agentic & tool use, where Gemini 1.5 Flash (May 2024) leads 26.6 to 22.1.
- The biggest single-benchmark swing is DTBench: 53.8% for Gemini 1.5 Flash (May 2024) and 62.9% for Qwen2.5 72B Instruct.
- Qwen2.5 72B Instruct has downloadable open weights; the other is API-only.
Side by side
| Gemini 1.5 Flash (May 2024) | Qwen2.5 72B Instruct | |
|---|---|---|
| Provider | Alibaba (Qwen) | |
| Noometry Index | 33.2 | 31.9 |
| Released | 2024-05-14 | 2024-09 |
| Weights | Proprietary | Open |
| Context window | — | 131K |
| Max output | — | 8K |
| Input $ / M tokens | — | $1.40 |
| Output $ / M tokens | — | $5.60 |
| Results tracked | 42 | 43 |
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): 34.4 (#236), Qwen2.5 72B Instruct: 33.2 (#260)
| Benchmark | Gemini 1.5 Flash (May 2024) | Qwen2.5 72B Instruct |
|---|---|---|
| WeirdML | 24.9% | 16% |
| BigCodeBench Instruct | 43.5% | 45.8% |
| LMArena Coding | 1261 | 1292 |
| BigCodeBench Complete | 55.1% | 55.9% |
| HumanEval+ | 75.6% | — |
| MBPP+ | 67.5% | — |
Agentic & Tool Use Gemini 1.5 Flash (May 2024) leads
Gemini 1.5 Flash (May 2024): 26.6 (#102), Qwen2.5 72B Instruct: 22.1 (#133)
| Benchmark | Gemini 1.5 Flash (May 2024) | Qwen2.5 72B Instruct |
|---|---|---|
| BALROG | 14.6% | 16.2% |
| TheAgentCompany | — | 5.7% |
| METR Time Horizons | — | 35.8% |
Reasoning Too close to call
Gemini 1.5 Flash (May 2024): 21.7 (#215), Qwen2.5 72B Instruct: 22.3 (#199)
| Benchmark | Gemini 1.5 Flash (May 2024) | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Hard Prompts | 1257 | 1271 |
| DTBench | 53.8% | 62.9% |
| Epoch Capabilities Index | 129.36 | 129 |
| ForecastBench | 53.9 | 57.5 |
| PIQA | 87.5% | 82.6% |
| LMCA | — | 13.4% |
| BIG-Bench Hard | — | 79.8% |
| HellaSwag | — | 84.8% |
| WinoGrande | — | 82.3% |
Math Gemini 1.5 Flash (May 2024) leads
Gemini 1.5 Flash (May 2024): 22.1 (#281), Qwen2.5 72B Instruct: 19.3 (#287)
| Benchmark | Gemini 1.5 Flash (May 2024) | Qwen2.5 72B Instruct |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 16.3% | 8.1% |
| Omni-MATH | 30.4% | 33% |
| LMArena Math | 1269 | 1283 |
| MATH Level 5 | 61.9% | 63.2% |
| FrontierMath (Feb 2025 set) | 0% | — |
| GSM8K | 82.4% | — |
Knowledge Too close to call
Gemini 1.5 Flash (May 2024): 26.2 (#260), Qwen2.5 72B Instruct: 27.0 (#253)
| Benchmark | Gemini 1.5 Flash (May 2024) | Qwen2.5 72B Instruct |
|---|---|---|
| GPQA Diamond | 47.3% | 49.1% |
| MMLU-Pro | 67.8% | 63.1% |
| GPQA (HELM) | 43.7% | 42.6% |
| LMArena Expert | 1233 | 1245 |
| MMLU | 77.9% | 85.3% |
| Confabulations | — | 19.1% |
| ARC (AI2) Challenge | — | 94.5% |
| BoolQ | 85.8% | — |
| TriviaQA | — | 71.9% |
Multimodal Not comparable
Gemini 1.5 Flash (May 2024): 36.0 (#81), Qwen2.5 72B Instruct: —
| Benchmark | Gemini 1.5 Flash (May 2024) | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Vision | 1141 | — |
| Video-MME | 70.3% | — |
| GeoBench | 76% | — |
Multilingual Gemini 1.5 Flash (May 2024) leads
Gemini 1.5 Flash (May 2024): 42.9 (#189), Qwen2.5 72B Instruct: 41.0 (#213)
| Benchmark | Gemini 1.5 Flash (May 2024) | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Non-English | 1278 | 1252 |
| LMArena Chinese | 1295 | 1272 |
| LMArena French | 1258 | 1280 |
| LMArena German | 1262 | 1234 |
| LMArena Japanese | 1252 | 1180 |
| LMArena Korean | 1221 | 1188 |
| LMArena Russian | 1288 | 1264 |
| LMArena Spanish | 1243 | 1256 |
Instruction Following Gemini 1.5 Flash (May 2024) leads
Gemini 1.5 Flash (May 2024): 66.8 (#205), Qwen2.5 72B Instruct: 65.5 (#221)
| Benchmark | Gemini 1.5 Flash (May 2024) | Qwen2.5 72B Instruct |
|---|---|---|
| IFEval | 83.1% | 80.6% |
| LMArena Instruction Following | 1258 | 1254 |
Long Context Too close to call
Gemini 1.5 Flash (May 2024): 39.0 (#187), Qwen2.5 72B Instruct: 38.9 (#188)
| Benchmark | Gemini 1.5 Flash (May 2024) | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Longer Query | 1284 | 1282 |
Writing & Preference Gemini 1.5 Flash (May 2024) leads
Gemini 1.5 Flash (May 2024): 48.7 (#196), Qwen2.5 72B Instruct: 46.7 (#215)
| Benchmark | Gemini 1.5 Flash (May 2024) | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Text | 1287 | 1269 |
| LMArena Creative Writing | 1285 | 1221 |
| WildBench | 79.2% | 80.2% |
| LMArena Multi-Turn | 1253 | 1272 |
Frequently asked questions
Is Gemini 1.5 Flash (May 2024) better than Qwen2.5 72B Instruct?
Gemini 1.5 Flash (May 2024) is the stronger model overall, scoring 33.2 to 31.9 on the Noometry Index.
Is Gemini 1.5 Flash (May 2024) or Qwen2.5 72B Instruct better for coding?
Gemini 1.5 Flash (May 2024) scores higher on coding benchmarks: 34.4 versus 33.2 in the Noometry coding category.
How many benchmarks do Gemini 1.5 Flash (May 2024) and Qwen2.5 72B Instruct share?
34 benchmarks have published results for both models. Gemini 1.5 Flash (May 2024) has 42 scored results on Noometry and Qwen2.5 72B Instruct has 43.