# Gemini 2.5 Flash vs Gemini 2.5 Pro

> Gemini 2.5 Pro is the stronger model overall, scoring 44.9 to 39.0 on the Noometry Index. Gemini 2.5 Flash costs 4.0× 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-flash-vs-gemini-2-5-pro
- Last updated: 2026-10-10
- Shared benchmarks: 53

## Summary

- They share 53 benchmarks with published results for both. Gemini 2.5 Flash scores higher in 3 categories and Gemini 2.5 Pro in 7 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Gemini 2.5 Pro leads 55.8 to 36.1.
- The biggest single-benchmark swing is GPQA (HELM): 39% for Gemini 2.5 Flash and 74.9% for Gemini 2.5 Pro.
- Gemini 2.5 Flash is cheaper at $0.30 / $2.50 per million input/output tokens, against $1.25 / $10 for Gemini 2.5 Pro.

## Snapshot

| | Gemini 2.5 Flash | Gemini 2.5 Pro |
|---|---|---|
| Provider | Google | Google |
| Noometry Index | 39.0 | 44.9 |
| Rank | 162 | 67 |
| Context | 1.05M | 1.05M |
| Input $/M | $0.30 | $1.25 |
| Output $/M | $2.50 | $10 |
| Weights | Proprietary | Proprietary |

## Coding

- Gemini 2.5 Flash: 35.5 (#210)
- Gemini 2.5 Pro: 42.8 (#86)

| Benchmark | Gemini 2.5 Flash | Gemini 2.5 Pro |
|---|---|---|
| SWE-bench Verified (bash only) | 28.7% | 53.6% |
| Aider Polyglot | 55.1% | 83.1% |
| WeirdML | 41.9% | 54% |
| LMArena Coding | 1424 | 1452 |
| ALE-Bench | 661.88 | 785.52 |
| SWE-bench Verified | — | 57.6% |
| LMArena WebDev | — | 1227 |
| SciCode | — | 42.8% |
| GSO | — | 3.9% |
| LiveBench Coding | — | 85.9% |
| CadEval | — | 64% |
| AlgoTune | — | 1.51 |

## Agentic & Tool Use

- Gemini 2.5 Flash: 30.6 (#67)
- Gemini 2.5 Pro: 29.1 (#81)

| Benchmark | Gemini 2.5 Flash | Gemini 2.5 Pro |
|---|---|---|
| Terminal-Bench | 17.1% | 32.6% |
| TheAgentCompany | 41.1% | 30.3% |
| BALROG | 33.5% | 43.3% |
| Vending-Bench 2 | 548.84 | 573.64 |
| Berkeley Function Calling Leaderboard | 56.2% | — |
| GDPval | — | 23.3% |
| Remote Labor Index | — | 0.8% |
| τ²-bench Banking | — | 13.7% |
| DeepResearch Bench | — | 42.8% |
| LMArena Search | — | 1142 |
| METR Time Horizons | — | 55.4% |

## Reasoning

- Gemini 2.5 Flash: 18.2 (#271)
- Gemini 2.5 Pro: 28.8 (#85)

| Benchmark | Gemini 2.5 Flash | Gemini 2.5 Pro |
|---|---|---|
| ARC-AGI-2 | 2.5% | 4.9% |
| SimpleBench | 41.2% | 62.4% |
| Kagi LLM Benchmark | 56.8% | 70.3% |
| ARC-AGI-1 | 33.3% | 41% |
| CritPt | 1.1% | 2% |
| EnigmaEval | 2.7% | 5.6% |
| LMArena Hard Prompts | 1422 | 1455 |
| DTBench | 76.5% | 82.4% |
| LMCA | 27.5% | 34.8% |
| Epoch Capabilities Index | 143.04 | 145.32 |
| ForecastBench | 60.6 | 61.3 |
| Chess Puzzles | — | 20% |
| LiveBench Reasoning | — | 89.8% |
| LiveBench Data Analysis | — | 79.9% |
| LiveBench | — | 82.3% |

## Math

- Gemini 2.5 Flash: 38.1 (#87)
- Gemini 2.5 Pro: 31.9 (#191)

| Benchmark | Gemini 2.5 Flash | Gemini 2.5 Pro |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 73.1% | 84.7% |
| Omni-MATH | 38.5% | 41.6% |
| LMArena Math | 1415 | 1450 |
| FrontierMath (Feb 2025 set) | 4.8% | 14.1% |
| FrontierMath Tier 4 (v1) | 4.2% | 4.2% |
| FrontierMath (Tiers 1-3) | — | 24.6% |
| FrontierMath Tier 4 | — | 0% |
| LiveBench Math | — | 90.2% |
| MATH Level 5 | — | 95.9% |

## Knowledge

- Gemini 2.5 Flash: 36.1 (#162)
- Gemini 2.5 Pro: 55.8 (#41)

| Benchmark | Gemini 2.5 Flash | Gemini 2.5 Pro |
|---|---|---|
| Humanity's Last Exam | 12.1% | 21.6% |
| MMLU-Pro | 63.9% | 86.3% |
| Confabulations | 16.8% | 10.6% |
| Vectara Hallucination Rate | 7.8% | 7% |
| GPQA (HELM) | 39% | 74.9% |
| LMArena Expert | 1426 | 1452 |
| GPQA Diamond | — | 85.3% |

## Multimodal

- Gemini 2.5 Flash: 41.2 (#31)
- Gemini 2.5 Pro: 44.5 (#16)

| Benchmark | Gemini 2.5 Flash | Gemini 2.5 Pro |
|---|---|---|
| LMArena Vision | 1254 | 1263 |
| GeoBench | 76% | 86% |
| VPCT | 46.2% | 48% |
| SpatialViz-Bench | 36.9% | 44.7% |
| LMArena Document | — | 1421 |

## Multilingual

- Gemini 2.5 Flash: 52.5 (#83)
- Gemini 2.5 Pro: 55.5 (#30)

| Benchmark | Gemini 2.5 Flash | Gemini 2.5 Pro |
|---|---|---|
| LMArena Non-English | 1410 | 1452 |
| LMArena Chinese | 1450 | 1507 |
| LMArena French | 1433 | 1473 |
| LMArena German | 1419 | 1487 |
| LMArena Japanese | 1403 | 1462 |
| LMArena Korean | 1385 | 1435 |
| LMArena Russian | 1415 | 1460 |
| LMArena Spanish | 1421 | 1473 |

## Instruction Following

- Gemini 2.5 Flash: 75.9 (#50)
- Gemini 2.5 Pro: 75.2 (#71)

| Benchmark | Gemini 2.5 Flash | Gemini 2.5 Pro |
|---|---|---|
| IFEval | 89.8% | 84% |
| LMArena Instruction Following | 1405 | 1436 |
| LiveBench Instruction Following | — | 80.6% |

## Long Context

- Gemini 2.5 Flash: 47.5 (#16)
- Gemini 2.5 Pro: 59.7 (#5)

| Benchmark | Gemini 2.5 Flash | Gemini 2.5 Pro |
|---|---|---|
| Fiction.LiveBench | 77.8% | 91.7% |
| LMArena Longer Query | 1419 | 1449 |

## Writing & Preference

- Gemini 2.5 Flash: 54.0 (#153)
- Gemini 2.5 Pro: 63.9 (#60)

| Benchmark | Gemini 2.5 Flash | Gemini 2.5 Pro |
|---|---|---|
| LMArena Text | 1417 | 1458 |
| LMArena Creative Writing | 1400 | 1453 |
| Short-Story Creative Writing | 76.5% | 83.8% |
| EQ-Bench Creative Writing | 1137 | 1421 |
| WildBench | 81.7% | 85.7% |
| LMArena Multi-Turn | 1408 | 1453 |
| LiveBench Language | — | 67.8% |

## FAQ

### Is Gemini 2.5 Flash better than Gemini 2.5 Pro?

Gemini 2.5 Pro is the stronger model overall, scoring 44.9 to 39.0 on the Noometry Index. Gemini 2.5 Flash costs 4.0× 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 Flash or Gemini 2.5 Pro?

Gemini 2.5 Flash is cheaper. It lists at $0.30 per million input tokens and $2.50 per million output tokens; Gemini 2.5 Pro lists at $1.25 and $10.

### Is Gemini 2.5 Flash or Gemini 2.5 Pro better for coding?

Gemini 2.5 Pro scores higher on coding benchmarks: 42.8 versus 35.5 in the Noometry coding category.

### Which has the bigger context window?

Both accept 1.05M tokens.

### How many benchmarks do Gemini 2.5 Flash and Gemini 2.5 Pro share?

53 benchmarks have published results for both models. Gemini 2.5 Flash has 54 scored results on Noometry and Gemini 2.5 Pro has 78.