# Gemini 2.5 Pro vs Qwen3 32B

> Gemini 2.5 Pro is the stronger model overall, scoring 44.9 to 38.8 on the Noometry Index. Qwen3 32B costs 2.8× less per token, which makes it the better buy when Gemini 2.5 Pro's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/gemini-2-5-pro-vs-qwen3-32b
- Last updated: 2026-10-10
- Shared benchmarks: 25

## Summary

- They share 25 benchmarks with published results for both. Gemini 2.5 Pro scores higher in 7 categories and Qwen3 32B in 2 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in long context, where Gemini 2.5 Pro leads 59.7 to 43.7.
- The biggest single-benchmark swing is Aider Polyglot: 83.1% for Gemini 2.5 Pro and 40% for Qwen3 32B.
- Qwen3 32B is cheaper at $0.70 / $2.80 per million input/output tokens, against $1.25 / $10 for Gemini 2.5 Pro.
- Gemini 2.5 Pro accepts more context: 1.05M tokens versus 131K.
- Qwen3 32B has downloadable open weights; the other is API-only.

## Snapshot

| | Gemini 2.5 Pro | Qwen3 32B |
|---|---|---|
| Provider | Google | Alibaba (Qwen) |
| Noometry Index | 44.9 | 38.8 |
| Rank | 67 | 166 |
| Context | 1.05M | 131K |
| Input $/M | $1.25 | $0.70 |
| Output $/M | $10 | $2.80 |
| Weights | Proprietary | Open |

## Coding

- Gemini 2.5 Pro: 42.8 (#86)
- Qwen3 32B: 37.3 (#184)

| Benchmark | Gemini 2.5 Pro | Qwen3 32B |
|---|---|---|
| Aider Polyglot | 83.1% | 40% |
| SciCode | 42.8% | 35.4% |
| LMArena Coding | 1452 | 1358 |
| SWE-bench Verified | 57.6% | — |
| SWE-bench Verified (bash only) | 53.6% | — |
| LMArena WebDev | 1227 | — |
| GSO | 3.9% | — |
| WeirdML | 54% | — |
| LiveBench Coding | 85.9% | — |
| CadEval | 64% | — |
| ALE-Bench | 785.52 | — |
| AlgoTune | 1.51 | — |

## Agentic & Tool Use

- Gemini 2.5 Pro: 29.1 (#81)
- Qwen3 32B: 32.3 (#58)

| Benchmark | Gemini 2.5 Pro | Qwen3 32B |
|---|---|---|
| Terminal-Bench | 32.6% | — |
| Berkeley Function Calling Leaderboard | — | 48.7% |
| 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)
- Qwen3 32B: 19.6 (#233)

| Benchmark | Gemini 2.5 Pro | Qwen3 32B |
|---|---|---|
| Kagi LLM Benchmark | 70.3% | 54.9% |
| CritPt | 2% | 0.3% |
| Chess Puzzles | 20% | 5% |
| LMArena Hard Prompts | 1455 | 1335 |
| DTBench | 82.4% | 67.5% |
| LMCA | 34.8% | 17.3% |
| Epoch Capabilities Index | 145.32 | 138.51 |
| ARC-AGI-2 | 4.9% | — |
| SimpleBench | 62.4% | — |
| ARC-AGI-1 | 41% | — |
| EnigmaEval | 5.6% | — |
| LiveBench Reasoning | 89.8% | — |
| LiveBench Data Analysis | 79.9% | — |
| ForecastBench | 61.3 | — |
| LiveBench | 82.3% | — |

## Math

- Gemini 2.5 Pro: 31.9 (#191)
- Qwen3 32B: 37.9 (#89)

| Benchmark | Gemini 2.5 Pro | Qwen3 32B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 84.7% | 66.9% |
| LMArena Math | 1450 | 1399 |
| FrontierMath (Tiers 1-3) | 24.6% | — |
| FrontierMath Tier 4 | 0% | — |
| Omni-MATH | 41.6% | — |
| LiveBench Math | 90.2% | — |
| 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)
- Qwen3 32B: 40.0 (#112)

| Benchmark | Gemini 2.5 Pro | Qwen3 32B |
|---|---|---|
| GPQA Diamond | 85.3% | 65.7% |
| Vectara Hallucination Rate | 7% | 5.9% |
| LMArena Expert | 1452 | 1362 |
| Humanity's Last Exam | 21.6% | — |
| MMLU-Pro | 86.3% | — |
| Confabulations | 10.6% | — |
| GPQA (HELM) | 74.9% | — |

## Multimodal

- Gemini 2.5 Pro: 44.5 (#16)
- Qwen3 32B: —

| Benchmark | Gemini 2.5 Pro | Qwen3 32B |
|---|---|---|
| LMArena Vision | 1263 | — |
| GeoBench | 86% | — |
| VPCT | 48% | — |
| LMArena Document | 1421 | — |
| SpatialViz-Bench | 44.7% | — |

## Multilingual

- Gemini 2.5 Pro: 55.5 (#30)
- Qwen3 32B: 45.8 (#162)

| Benchmark | Gemini 2.5 Pro | Qwen3 32B |
|---|---|---|
| LMArena Non-English | 1452 | 1317 |
| LMArena Chinese | 1507 | 1357 |
| LMArena German | 1487 | 1341 |
| LMArena Russian | 1460 | 1311 |
| LMArena French | 1473 | — |
| LMArena Japanese | 1462 | — |
| LMArena Korean | 1435 | — |
| LMArena Spanish | 1473 | — |

## Instruction Following

- Gemini 2.5 Pro: 75.2 (#71)
- Qwen3 32B: 69.1 (#174)

| Benchmark | Gemini 2.5 Pro | Qwen3 32B |
|---|---|---|
| LMArena Instruction Following | 1436 | 1305 |
| LiveBench Instruction Following | 80.6% | — |
| IFEval | 84% | — |

## Long Context

- Gemini 2.5 Pro: 59.7 (#5)
- Qwen3 32B: 43.7 (#83)

| Benchmark | Gemini 2.5 Pro | Qwen3 32B |
|---|---|---|
| Fiction.LiveBench | 91.7% | 74.2% |
| LMArena Longer Query | 1449 | 1327 |

## Writing & Preference

- Gemini 2.5 Pro: 63.9 (#60)
- Qwen3 32B: 53.1 (#158)

| Benchmark | Gemini 2.5 Pro | Qwen3 32B |
|---|---|---|
| LMArena Text | 1458 | 1340 |
| LMArena Creative Writing | 1453 | 1297 |
| LMArena Multi-Turn | 1453 | 1331 |
| Short-Story Creative Writing | 83.8% | — |
| EQ-Bench Creative Writing | 1421 | — |
| WildBench | 85.7% | — |
| LiveBench Language | 67.8% | — |

## FAQ

### Is Gemini 2.5 Pro better than Qwen3 32B?

Gemini 2.5 Pro is the stronger model overall, scoring 44.9 to 38.8 on the Noometry Index. Qwen3 32B costs 2.8× less per token, which makes it the better buy when Gemini 2.5 Pro's lead doesn't matter for your workload.

### Which is cheaper, Gemini 2.5 Pro or Qwen3 32B?

Qwen3 32B is cheaper. It lists at $0.70 per million input tokens and $2.80 per million output tokens; Gemini 2.5 Pro lists at $1.25 and $10.

### Is Gemini 2.5 Pro or Qwen3 32B better for coding?

Gemini 2.5 Pro scores higher on coding benchmarks: 42.8 versus 37.3 in the Noometry coding category.

### Which has the bigger context window?

Gemini 2.5 Pro does, with 1.05M tokens against 131K.

### How many benchmarks do Gemini 2.5 Pro and Qwen3 32B share?

25 benchmarks have published results for both models. Gemini 2.5 Pro has 78 scored results on Noometry and Qwen3 32B has 26.