# Gemini 2.5 Pro vs QwQ-32B

> Gemini 2.5 Pro is the stronger model overall, scoring 44.9 to 39.4 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gemini-2-5-pro-vs-qwq-32b
- Last updated: 2026-10-10
- Shared benchmarks: 34

## Summary

- They share 34 benchmarks with published results for both. Gemini 2.5 Pro scores higher in 7 categories and QwQ-32B in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Gemini 2.5 Pro leads 55.8 to 37.2.
- The biggest single-benchmark swing is Aider Polyglot: 83.1% for Gemini 2.5 Pro and 20.9% for QwQ-32B.
- QwQ-32B has downloadable open weights; the other is API-only.

## Snapshot

| | Gemini 2.5 Pro | QwQ-32B |
|---|---|---|
| Provider | Google | Alibaba (Qwen) |
| Noometry Index | 44.9 | 39.4 |
| Rank | 67 | 153 |
| Context | 1.05M | — |
| Input $/M | $1.25 | — |
| Output $/M | $10 | — |
| Weights | Proprietary | Open |

## Coding

- Gemini 2.5 Pro: 42.8 (#86)
- QwQ-32B: 34.9 (#220)

| Benchmark | Gemini 2.5 Pro | QwQ-32B |
|---|---|---|
| Aider Polyglot | 83.1% | 20.9% |
| LiveBench Coding | 85.9% | 72.2% |
| LMArena Coding | 1452 | 1333 |
| SWE-bench Verified | 57.6% | — |
| SWE-bench Verified (bash only) | 53.6% | — |
| LMArena WebDev | 1227 | — |
| SciCode | 42.8% | — |
| GSO | 3.9% | — |
| WeirdML | 54% | — |
| BigCodeBench Instruct | — | 44.6% |
| BigCodeBench Complete | — | 54.4% |
| CadEval | 64% | — |
| ALE-Bench | 785.52 | — |
| AlgoTune | 1.51 | — |

## Agentic & Tool Use

- Gemini 2.5 Pro: 29.1 (#81)
- QwQ-32B: —

| Benchmark | Gemini 2.5 Pro | QwQ-32B |
|---|---|---|
| Terminal-Bench | 32.6% | — |
| GDPval | 23.3% | — |
| Remote Labor Index | 0.8% | — |
| TheAgentCompany | 30.3% | — |
| τ²-bench Banking | 13.7% | — |
| DeepResearch Bench | 42.8% | — |
| BALROG | 43.3% | — |
| LMArena Search | 1142 | — |
| METR Time Horizons | 55.4% | — |
| Vending-Bench 2 | 573.64 | — |

## Reasoning

- Gemini 2.5 Pro: 28.8 (#85)
- QwQ-32B: 22.9 (#171)

| Benchmark | Gemini 2.5 Pro | QwQ-32B |
|---|---|---|
| Chess Puzzles | 20% | 5% |
| LiveBench Reasoning | 89.8% | 83.5% |
| LMArena Hard Prompts | 1455 | 1326 |
| LiveBench Data Analysis | 79.9% | 65% |
| Epoch Capabilities Index | 145.32 | 137.6 |
| ForecastBench | 61.3 | 58.3 |
| LiveBench | 82.3% | 72% |
| ARC-AGI-2 | 4.9% | — |
| SimpleBench | 62.4% | — |
| Kagi LLM Benchmark | 70.3% | — |
| ARC-AGI-1 | 41% | — |
| CritPt | 2% | — |
| EnigmaEval | 5.6% | — |
| DTBench | 82.4% | — |
| LMCA | 34.8% | — |

## Math

- Gemini 2.5 Pro: 31.9 (#191)
- QwQ-32B: 36.2 (#123)

| Benchmark | Gemini 2.5 Pro | QwQ-32B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 84.7% | 59.2% |
| LiveBench Math | 90.2% | 77.8% |
| LMArena Math | 1450 | 1359 |
| FrontierMath (Tiers 1-3) | 24.6% | — |
| FrontierMath Tier 4 | 0% | — |
| Omni-MATH | 41.6% | — |
| MATH Level 5 | 95.9% | — |
| FrontierMath (Feb 2025 set) | 14.1% | — |
| FrontierMath Tier 4 (v1) | 4.2% | — |

## Knowledge

- Gemini 2.5 Pro: 55.8 (#41)
- QwQ-32B: 37.2 (#150)

| Benchmark | Gemini 2.5 Pro | QwQ-32B |
|---|---|---|
| GPQA Diamond | 85.3% | 65.3% |
| Confabulations | 10.6% | 15.6% |
| LMArena Expert | 1452 | 1323 |
| Humanity's Last Exam | 21.6% | — |
| MMLU-Pro | 86.3% | — |
| Vectara Hallucination Rate | 7% | — |
| GPQA (HELM) | 74.9% | — |

## Multimodal

- Gemini 2.5 Pro: 44.5 (#16)
- QwQ-32B: —

| Benchmark | Gemini 2.5 Pro | QwQ-32B |
|---|---|---|
| LMArena Vision | 1263 | — |
| GeoBench | 86% | — |
| VPCT | 48% | — |
| LMArena Document | 1421 | — |
| SpatialViz-Bench | 44.7% | — |

## Multilingual

- Gemini 2.5 Pro: 55.5 (#30)
- QwQ-32B: 45.0 (#171)

| Benchmark | Gemini 2.5 Pro | QwQ-32B |
|---|---|---|
| LMArena Non-English | 1452 | 1306 |
| LMArena Chinese | 1507 | 1378 |
| LMArena French | 1473 | 1337 |
| LMArena German | 1487 | 1313 |
| LMArena Japanese | 1462 | 1263 |
| LMArena Korean | 1435 | 1278 |
| LMArena Russian | 1460 | 1297 |
| LMArena Spanish | 1473 | 1353 |

## Instruction Following

- Gemini 2.5 Pro: 75.2 (#71)
- QwQ-32B: 72.8 (#131)

| Benchmark | Gemini 2.5 Pro | QwQ-32B |
|---|---|---|
| LiveBench Instruction Following | 80.6% | 81.8% |
| LMArena Instruction Following | 1436 | 1297 |
| IFEval | 84% | — |

## Long Context

- Gemini 2.5 Pro: 59.7 (#5)
- QwQ-32B: 49.0 (#11)

| Benchmark | Gemini 2.5 Pro | QwQ-32B |
|---|---|---|
| Fiction.LiveBench | 91.7% | 83.3% |
| LMArena Longer Query | 1449 | 1308 |

## Writing & Preference

- Gemini 2.5 Pro: 63.9 (#60)
- QwQ-32B: 50.9 (#175)

| Benchmark | Gemini 2.5 Pro | QwQ-32B |
|---|---|---|
| LMArena Text | 1458 | 1329 |
| LMArena Creative Writing | 1453 | 1288 |
| Short-Story Creative Writing | 83.8% | 80.2% |
| EQ-Bench Creative Writing | 1421 | 1257 |
| LMArena Multi-Turn | 1453 | 1314 |
| LiveBench Language | 67.8% | 51.4% |
| WildBench | 85.7% | — |

## FAQ

### Is Gemini 2.5 Pro better than QwQ-32B?

Gemini 2.5 Pro is the stronger model overall, scoring 44.9 to 39.4 on the Noometry Index.

### Is Gemini 2.5 Pro or QwQ-32B better for coding?

Gemini 2.5 Pro scores higher on coding benchmarks: 42.8 versus 34.9 in the Noometry coding category.

### How many benchmarks do Gemini 2.5 Pro and QwQ-32B share?

34 benchmarks have published results for both models. Gemini 2.5 Pro has 78 scored results on Noometry and QwQ-32B has 36.