# Gemini 2.5 Pro vs Gemini 3.7 Flash

> Gemini 3.7 Flash is the stronger model overall, scoring 59.8 to 45.0 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gemini-2-5-pro-vs-gemini-3-7-flash
- Last updated: 2026-10-11
- Shared benchmarks: 34

## Summary

- They share 34 benchmarks with published results for both. Gemini 2.5 Pro scores higher in 2 categories and Gemini 3.7 Flash in 8 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Gemini 3.7 Flash leads 70.0 to 28.8.
- The biggest single-benchmark swing is ARC-AGI-2: 4.9% for Gemini 2.5 Pro and 84.6% for Gemini 3.7 Flash.
- Gemini 3.7 Flash is cheaper at $0.75 / $3.75 per million input/output tokens, against $1.25 / $10 for Gemini 2.5 Pro.

## Snapshot

| | Gemini 2.5 Pro | Gemini 3.7 Flash |
|---|---|---|
| Provider | Google | Google |
| Noometry Index | 45.0 | 59.8 |
| Rank | 75 | 14 |
| Context | 1.05M | 1.05M |
| Input $/M | $1.25 | $0.75 |
| Output $/M | $10 | $3.75 |
| Weights | Proprietary | Proprietary |

## Coding

- Gemini 2.5 Pro: 42.4 (#101)
- Gemini 3.7 Flash: 56.2 (#22)

| Benchmark | Gemini 2.5 Pro | Gemini 3.7 Flash |
|---|---|---|
| LMArena WebDev | 1227 | 1592 |
| SciCode | 42.8% | 59.8% |
| LMArena Coding | 1452 | 1497 |
| ALE-Bench | 785.52 | 904.3 |
| SWE-bench Verified | 57.6% | — |
| DeepSWE | — | 65.5% |
| FrontierCode | — | 43.6% |
| SWE-bench Verified (bash only) | 53.6% | — |
| Aider Polyglot | 83.1% | — |
| FrontierSWE | — | 20.3% |
| GSO | 3.9% | — |
| WeirdML | 54% | — |
| LiveBench Coding | 85.9% | — |
| CadEval | 64% | — |
| AlgoTune | 1.51 | — |

## Agentic & Tool Use

- Gemini 2.5 Pro: 29.2 (#88)
- Gemini 3.7 Flash: 42.1 (#19)

| Benchmark | Gemini 2.5 Pro | Gemini 3.7 Flash |
|---|---|---|
| Remote Labor Index | 0.8% | 5% |
| Terminal-Bench | 32.6% | — |
| APEX-Agents | — | 67.8% |
| GDPval | 23.3% | — |
| TheAgentCompany | 30.3% | — |
| τ²-bench Banking | 13.7% | — |
| DeepResearch Bench | 42.8% | — |
| BALROG | 43.3% | — |
| GDP.pdf | — | 23.8% |
| LMArena Search | 1142 | — |
| METR Time Horizons | 55.4% | — |
| Vending-Bench 2 | 573.64 | — |

## Reasoning

- Gemini 2.5 Pro: 28.8 (#99)
- Gemini 3.7 Flash: 70.0 (#15)

| Benchmark | Gemini 2.5 Pro | Gemini 3.7 Flash |
|---|---|---|
| ARC-AGI-2 | 4.9% | 84.6% |
| ARC-AGI-1 | 41% | 95.5% |
| CritPt | 2% | 14.3% |
| Chess Puzzles | 20% | 47% |
| LMArena Hard Prompts | 1455 | 1494 |
| DTBench | 82.4% | 96.8% |
| LMCA | 34.8% | 50.4% |
| Epoch Capabilities Index | 145.32 | 157.27 |
| SimpleBench | 62.4% | — |
| Kagi LLM Benchmark | 70.3% | — |
| NYT Connections (extended) | — | 94% |
| EnigmaEval | 5.6% | — |
| LiveBench Reasoning | 89.8% | — |
| Mystery Game Puzzles | — | 37% |
| LiveBench Data Analysis | 79.9% | — |
| ForecastBench | 61.3 | — |
| LiveBench | 82.3% | — |

## Math

- Gemini 2.5 Pro: 32.5 (#213)
- Gemini 3.7 Flash: 69.6 (#23)

| Benchmark | Gemini 2.5 Pro | Gemini 3.7 Flash |
|---|---|---|
| FrontierMath (Tiers 1-3) | 24.6% | 71.6% |
| FrontierMath Tier 4 | 0% | 36.6% |
| OTIS Mock AIME 2024-2025 | 84.7% | 97.2% |
| LMArena Math | 1450 | 1507 |
| ProofBench | — | 58% |
| 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: 56.0 (#46)
- Gemini 3.7 Flash: 69.7 (#5)

| Benchmark | Gemini 2.5 Pro | Gemini 3.7 Flash |
|---|---|---|
| GPQA Diamond | 85.3% | 94.8% |
| LMArena Expert | 1452 | 1508 |
| Humanity's Last Exam | 21.6% | — |
| SimpleQA Verified | — | 69.2% |
| MMLU-Pro | 86.3% | — |
| Confabulations | 10.6% | — |
| Vectara Hallucination Rate | 7% | — |
| GPQA (HELM) | 74.9% | — |

## Multimodal

- Gemini 2.5 Pro: 45.2 (#18)
- Gemini 3.7 Flash: 37.3 (#73)

| Benchmark | Gemini 2.5 Pro | Gemini 3.7 Flash |
|---|---|---|
| LMArena Vision | 1263 | 1316 |
| GeoBench | 86% | — |
| VPCT | 48% | — |
| Furniture Assembly | — | 26.7% |
| LMArena Document | 1421 | — |
| SpatialViz-Bench | 44.7% | — |

## Multilingual

- Gemini 2.5 Pro: 55.3 (#31)
- Gemini 3.7 Flash: 57.6 (#7)

| Benchmark | Gemini 2.5 Pro | Gemini 3.7 Flash |
|---|---|---|
| LMArena Non-English | 1451 | 1484 |
| LMArena Chinese | 1507 | 1548 |
| LMArena French | 1472 | 1505 |
| LMArena German | 1487 | 1498 |
| LMArena Japanese | 1461 | 1512 |
| LMArena Korean | 1434 | 1483 |
| LMArena Russian | 1461 | 1516 |
| LMArena Spanish | 1473 | 1503 |

## Instruction Following

- Gemini 2.5 Pro: 75.0 (#75)
- Gemini 3.7 Flash: 77.7 (#15)

| Benchmark | Gemini 2.5 Pro | Gemini 3.7 Flash |
|---|---|---|
| LMArena Instruction Following | 1437 | 1483 |
| LiveBench Instruction Following | 80.6% | — |
| IFEval | 84% | — |

## Long Context

- Gemini 2.5 Pro: 59.8 (#5)
- Gemini 3.7 Flash: 45.7 (#30)

| Benchmark | Gemini 2.5 Pro | Gemini 3.7 Flash |
|---|---|---|
| LMArena Longer Query | 1449 | 1492 |
| Fiction.LiveBench | 91.7% | — |

## Writing & Preference

- Gemini 2.5 Pro: 63.7 (#62)
- Gemini 3.7 Flash: 71.2 (#20)

| Benchmark | Gemini 2.5 Pro | Gemini 3.7 Flash |
|---|---|---|
| LMArena Text | 1458 | 1486 |
| LMArena Creative Writing | 1454 | 1490 |
| EQ-Bench Creative Writing | 1421 | 1723 |
| LMArena Multi-Turn | 1453 | 1489 |
| Short-Story Creative Writing | 83.8% | — |
| WildBench | 85.7% | — |
| LiveBench Language | 67.8% | — |

## FAQ

### Is Gemini 2.5 Pro better than Gemini 3.7 Flash?

Gemini 3.7 Flash is the stronger model overall, scoring 59.8 to 45.0 on the Noometry Index.

### Which is cheaper, Gemini 2.5 Pro or Gemini 3.7 Flash?

Gemini 3.7 Flash is cheaper. It lists at $0.75 per million input tokens and $3.75 per million output tokens; Gemini 2.5 Pro lists at $1.25 and $10.

### Is Gemini 2.5 Pro or Gemini 3.7 Flash better for coding?

Gemini 3.7 Flash scores higher on coding benchmarks: 56.2 versus 42.4 in the Noometry coding category.

### Which has the bigger context window?

Both accept 1.05M tokens.

### How many benchmarks do Gemini 2.5 Pro and Gemini 3.7 Flash share?

34 benchmarks have published results for both models. Gemini 2.5 Pro has 78 scored results on Noometry and Gemini 3.7 Flash has 44.