Model comparison
Gemini 1.5 Pro (May 2024) vs QwQ-32B
QwQ-32B is the stronger model overall, scoring 39.8 to 32.1 on the Noometry Index.
Last verified . 24 shared benchmarks.
Google
Alibaba (Qwen)Summary
- They share 24 benchmarks with published results for both. Gemini 1.5 Pro (May 2024) scores higher in 2 categories and QwQ-32B in 6 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where QwQ-32B leads 38.0 to 25.8.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 23.1% for Gemini 1.5 Pro (May 2024) and 59.2% for QwQ-32B.
- QwQ-32B has downloadable open weights; the other is API-only.
Side by side
| Gemini 1.5 Pro (May 2024) | QwQ-32B | |
|---|---|---|
| Provider | Alibaba (Qwen) | |
| Noometry Index | 32.1 | 39.8 |
| Released | 2024-02-15 | 2024-11-28 |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 45 | 36 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding QwQ-32B leads
Gemini 1.5 Pro (May 2024): 34.2 (#241), QwQ-32B: 35.4 (#226)
| Benchmark | Gemini 1.5 Pro (May 2024) | QwQ-32B |
|---|---|---|
| BigCodeBench Instruct | 43.8% | 44.6% |
| LMArena Coding | 1294 | 1333 |
| BigCodeBench Complete | 57.5% | 54.4% |
| Aider Polyglot | — | 20.9% |
| WeirdML | 22.2% | — |
| LiveBench Coding | — | 72.2% |
| CadEval | 34% | — |
| HumanEval+ | 79.3% | — |
| MBPP+ | 74.6% | — |
Agentic & Tool Use Not comparable
Gemini 1.5 Pro (May 2024): 17.9 (#145), QwQ-32B: —
| Benchmark | Gemini 1.5 Pro (May 2024) | QwQ-32B |
|---|---|---|
| TheAgentCompany | 3.4% | — |
| Cybench | 7.5% | — |
| BALROG | 21% | — |
Reasoning QwQ-32B leads
Gemini 1.5 Pro (May 2024): 12.3 (#338), QwQ-32B: 23.7 (#174)
| Benchmark | Gemini 1.5 Pro (May 2024) | QwQ-32B |
|---|---|---|
| LMArena Hard Prompts | 1296 | 1325 |
| Epoch Capabilities Index | 131.73 | 137.6 |
| ForecastBench | 58.4 | 58.3 |
| ARC-AGI-2 | 0.8% | — |
| SimpleBench | 27.1% | — |
| Chess Puzzles | — | 5% |
| LiveBench Reasoning | — | 83.5% |
| DTBench | 59% | — |
| LiveBench Data Analysis | — | 65% |
| BIG-Bench Hard | 89.2% | — |
| LiveBench | — | 72% |
Math QwQ-32B leads
Gemini 1.5 Pro (May 2024): 25.8 (#266), QwQ-32B: 38.0 (#143)
| Benchmark | Gemini 1.5 Pro (May 2024) | QwQ-32B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 23.1% | 59.2% |
| LMArena Math | 1315 | 1359 |
| Omni-MATH | 36.4% | — |
| LiveBench Math | — | 77.8% |
| MATH Level 5 | 70.4% | — |
Knowledge QwQ-32B leads
Gemini 1.5 Pro (May 2024): 29.4 (#239), QwQ-32B: 37.2 (#158)
| Benchmark | Gemini 1.5 Pro (May 2024) | QwQ-32B |
|---|---|---|
| GPQA Diamond | 57.2% | 65.3% |
| Confabulations | 13.5% | 15.6% |
| LMArena Expert | 1279 | 1324 |
| Humanity's Last Exam | 4.6% | — |
| MMLU-Pro | 73.7% | — |
| GPQA (HELM) | 53.4% | — |
| MMLU | 86.9% | — |
Multimodal Not comparable
Gemini 1.5 Pro (May 2024): 36.8 (#77), QwQ-32B: —
| Benchmark | Gemini 1.5 Pro (May 2024) | QwQ-32B |
|---|---|---|
| LMArena Vision | 1161 | — |
| Video-MME | 75% | — |
Multilingual Too close to call
Gemini 1.5 Pro (May 2024): 45.3 (#174), QwQ-32B: 44.8 (#176)
| Benchmark | Gemini 1.5 Pro (May 2024) | QwQ-32B |
|---|---|---|
| LMArena Non-English | 1312 | 1305 |
| LMArena Chinese | 1331 | 1378 |
| LMArena French | 1302 | 1336 |
| LMArena German | 1286 | 1313 |
| LMArena Japanese | 1292 | 1262 |
| LMArena Korean | 1298 | 1279 |
| LMArena Russian | 1320 | 1297 |
| LMArena Spanish | 1311 | 1354 |
Instruction Following QwQ-32B leads
Gemini 1.5 Pro (May 2024): 68.6 (#185), QwQ-32B: 72.6 (#137)
| Benchmark | Gemini 1.5 Pro (May 2024) | QwQ-32B |
|---|---|---|
| LMArena Instruction Following | 1297 | 1297 |
| LiveBench Instruction Following | — | 81.8% |
| IFEval | 83.7% | — |
Long Context QwQ-32B leads
Gemini 1.5 Pro (May 2024): 39.8 (#169), QwQ-32B: 49.0 (#11)
| Benchmark | Gemini 1.5 Pro (May 2024) | QwQ-32B |
|---|---|---|
| LMArena Longer Query | 1308 | 1308 |
| Fiction.LiveBench | — | 83.3% |
Writing & Preference Gemini 1.5 Pro (May 2024) leads
Gemini 1.5 Pro (May 2024): 52.4 (#172), QwQ-32B: 50.6 (#180)
| Benchmark | Gemini 1.5 Pro (May 2024) | QwQ-32B |
|---|---|---|
| LMArena Text | 1319 | 1329 |
| LMArena Creative Writing | 1333 | 1288 |
| LMArena Multi-Turn | 1296 | 1314 |
| Short-Story Creative Writing | — | 80.2% |
| EQ-Bench Creative Writing | — | 1257 |
| WildBench | 81.3% | — |
| LiveBench Language | — | 51.4% |
Frequently asked questions
Is Gemini 1.5 Pro (May 2024) better than QwQ-32B?
QwQ-32B is the stronger model overall, scoring 39.8 to 32.1 on the Noometry Index.
Is Gemini 1.5 Pro (May 2024) or QwQ-32B better for coding?
QwQ-32B scores higher on coding benchmarks: 35.4 versus 34.2 in the Noometry coding category.
How many benchmarks do Gemini 1.5 Pro (May 2024) and QwQ-32B share?
24 benchmarks have published results for both models. Gemini 1.5 Pro (May 2024) has 45 scored results on Noometry and QwQ-32B has 36.