# Gemini 2.5 Flash vs Gemini 3.6 Flash

> Gemini 3.6 Flash is the stronger model overall, scoring 54.1 to 39.3 on the Noometry Index. Gemini 2.5 Flash costs 1.8× less per token, which makes it the better buy when Gemini 3.6 Flash's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/gemini-2-5-flash-vs-gemini-3-6-flash
- Last updated: 2026-10-10
- Shared benchmarks: 28

## Summary

- They share 28 benchmarks with published results for both. Gemini 2.5 Flash scores higher in 2 categories and Gemini 3.6 Flash in 8 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Gemini 3.6 Flash leads 58.8 to 18.1.
- The biggest single-benchmark swing is ARC-AGI-2: 2.5% for Gemini 2.5 Flash and 60.4% for Gemini 3.6 Flash.
- Gemini 2.5 Flash is cheaper at $0.30 / $2.50 per million input/output tokens, against $0.75 / $3.75 for Gemini 3.6 Flash.

## Snapshot

| | Gemini 2.5 Flash | Gemini 3.6 Flash |
|---|---|---|
| Provider | Google | Google |
| Noometry Index | 39.3 | 54.1 |
| Rank | 170 | 33 |
| Context | 1.05M | 1.05M |
| Input $/M | $0.30 | $0.75 |
| Output $/M | $2.50 | $3.75 |
| Weights | Proprietary | Proprietary |

## Coding

- Gemini 2.5 Flash: 35.8 (#220)
- Gemini 3.6 Flash: 50.0 (#48)

| Benchmark | Gemini 2.5 Flash | Gemini 3.6 Flash |
|---|---|---|
| WeirdML | 41.9% | 56.1% |
| LMArena Coding | 1424 | 1491 |
| ALE-Bench | 661.88 | 715.52 |
| DeepSWE | — | 46.7% |
| FrontierCode | — | 34.4% |
| SWE-bench Verified (bash only) | 28.7% | — |
| Aider Polyglot | 55.1% | — |
| LMArena WebDev | — | 1538 |
| SciCode | — | 52.7% |

## Agentic & Tool Use

- Gemini 2.5 Flash: 30.8 (#74)
- Gemini 3.6 Flash: 32.3 (#65)

| Benchmark | Gemini 2.5 Flash | Gemini 3.6 Flash |
|---|---|---|
| Terminal-Bench | 17.1% | — |
| APEX-Agents | — | 46.9% |
| Berkeley Function Calling Leaderboard | 56.2% | — |
| TheAgentCompany | 41.1% | — |
| BALROG | 33.5% | — |
| GDP.pdf | — | 14% |
| Vending-Bench 2 | 548.84 | — |

## Reasoning

- Gemini 2.5 Flash: 18.1 (#286)
- Gemini 3.6 Flash: 58.8 (#22)

| Benchmark | Gemini 2.5 Flash | Gemini 3.6 Flash |
|---|---|---|
| ARC-AGI-2 | 2.5% | 60.4% |
| ARC-AGI-1 | 33.3% | 91.2% |
| CritPt | 1.1% | 10.6% |
| LMArena Hard Prompts | 1422 | 1485 |
| DTBench | 76.5% | 95.5% |
| LMCA | 27.5% | 44.9% |
| Epoch Capabilities Index | 143.03 | 154.25 |
| SimpleBench | 41.2% | — |
| Kagi LLM Benchmark | 56.8% | — |
| NYT Connections (extended) | — | 89% |
| Chess Puzzles | — | 43% |
| EnigmaEval | 2.7% | — |
| Mystery Game Puzzles | — | 30% |
| ForecastBench | 60.6 | — |

## Math

- Gemini 2.5 Flash: 39.9 (#98)
- Gemini 3.6 Flash: 57.3 (#40)

| Benchmark | Gemini 2.5 Flash | Gemini 3.6 Flash |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 73.1% | 94.2% |
| LMArena Math | 1415 | 1505 |
| FrontierMath (Tiers 1-3) | — | 58.9% |
| FrontierMath Tier 4 | — | 22% |
| MathArena Final-Answer Competitions | — | 70.8% |
| ProofBench | — | 36% |
| Omni-MATH | 38.5% | — |
| FrontierMath (Feb 2025 set) | 4.8% | — |
| FrontierMath Tier 4 (v1) | 4.2% | — |

## Knowledge

- Gemini 2.5 Flash: 36.4 (#168)
- Gemini 3.6 Flash: 67.8 (#8)

| Benchmark | Gemini 2.5 Flash | Gemini 3.6 Flash |
|---|---|---|
| LMArena Expert | 1426 | 1488 |
| GPQA Diamond | — | 94.1% |
| Humanity's Last Exam | 12.1% | — |
| SimpleQA Verified | — | 66.2% |
| MMLU-Pro | 63.9% | — |
| Confabulations | 16.8% | — |
| Vectara Hallucination Rate | 7.8% | — |
| GPQA (HELM) | 39% | — |

## Multimodal

- Gemini 2.5 Flash: 41.8 (#32)
- Gemini 3.6 Flash: 38.5 (#64)

| Benchmark | Gemini 2.5 Flash | Gemini 3.6 Flash |
|---|---|---|
| LMArena Vision | 1253 | 1298 |
| GeoBench | 76% | — |
| VPCT | 46.2% | — |
| Blueprint-Bench 2 | — | 31.2% |
| Furniture Assembly | — | 23.3% |
| LMArena Document | — | 1456 |
| SpatialViz-Bench | 36.9% | — |

## Multilingual

- Gemini 2.5 Flash: 52.3 (#88)
- Gemini 3.6 Flash: 56.5 (#19)

| Benchmark | Gemini 2.5 Flash | Gemini 3.6 Flash |
|---|---|---|
| LMArena Non-English | 1409 | 1469 |
| LMArena Chinese | 1450 | 1531 |
| LMArena French | 1433 | 1504 |
| LMArena German | 1418 | 1478 |
| LMArena Japanese | 1405 | 1476 |
| LMArena Korean | 1385 | 1431 |
| LMArena Russian | 1415 | 1487 |
| LMArena Spanish | 1421 | 1475 |

## Instruction Following

- Gemini 2.5 Flash: 75.7 (#54)
- Gemini 3.6 Flash: 77.0 (#33)

| Benchmark | Gemini 2.5 Flash | Gemini 3.6 Flash |
|---|---|---|
| LMArena Instruction Following | 1405 | 1466 |
| IFEval | 89.8% | — |

## Long Context

- Gemini 2.5 Flash: 47.5 (#17)
- Gemini 3.6 Flash: 45.1 (#50)

| Benchmark | Gemini 2.5 Flash | Gemini 3.6 Flash |
|---|---|---|
| LMArena Longer Query | 1419 | 1474 |
| Fiction.LiveBench | 77.8% | — |

## Writing & Preference

- Gemini 2.5 Flash: 53.8 (#157)
- Gemini 3.6 Flash: 68.2 (#27)

| Benchmark | Gemini 2.5 Flash | Gemini 3.6 Flash |
|---|---|---|
| LMArena Text | 1417 | 1479 |
| LMArena Creative Writing | 1400 | 1465 |
| EQ-Bench Creative Writing | 1137 | 1604 |
| LMArena Multi-Turn | 1408 | 1481 |
| Short-Story Creative Writing | 76.5% | — |
| WildBench | 81.7% | — |

## FAQ

### Is Gemini 2.5 Flash better than Gemini 3.6 Flash?

Gemini 3.6 Flash is the stronger model overall, scoring 54.1 to 39.3 on the Noometry Index. Gemini 2.5 Flash costs 1.8× less per token, which makes it the better buy when Gemini 3.6 Flash's lead doesn't matter for your workload.

### Which is cheaper, Gemini 2.5 Flash or Gemini 3.6 Flash?

Gemini 2.5 Flash is cheaper. It lists at $0.30 per million input tokens and $2.50 per million output tokens; Gemini 3.6 Flash lists at $0.75 and $3.75.

### Is Gemini 2.5 Flash or Gemini 3.6 Flash better for coding?

Gemini 3.6 Flash scores higher on coding benchmarks: 50.0 versus 35.8 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 3.6 Flash share?

28 benchmarks have published results for both models. Gemini 2.5 Flash has 54 scored results on Noometry and Gemini 3.6 Flash has 46.