# Gemini 3.6 Flash vs Step 3.5 Flash

> Gemini 3.6 Flash is the stronger model overall, scoring 54.1 to 42.3 on the Noometry Index. Step 3.5 Flash costs 10.0× 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-3-6-flash-vs-step-3-5-flash
- Last updated: 2026-10-10
- Shared benchmarks: 19

## Summary

- They share 19 benchmarks with published results for both. Gemini 3.6 Flash scores higher in 8 categories and Step 3.5 Flash in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Gemini 3.6 Flash leads 58.8 to 22.2.
- The biggest single-benchmark swing is NYT Connections (extended): 89% for Gemini 3.6 Flash and 28.4% for Step 3.5 Flash.
- Step 3.5 Flash is cheaper at $0.10 / $0.30 per million input/output tokens, against $0.75 / $3.75 for Gemini 3.6 Flash.
- Gemini 3.6 Flash accepts more context: 1.05M tokens versus 256K.
- Step 3.5 Flash has downloadable open weights; the other is API-only.

## Snapshot

| | Gemini 3.6 Flash | Step 3.5 Flash |
|---|---|---|
| Provider | Google | StepFun |
| Noometry Index | 54.1 | 42.3 |
| Rank | 33 | 116 |
| Context | 1.05M | 256K |
| Input $/M | $0.75 | $0.10 |
| Output $/M | $3.75 | $0.30 |
| Weights | Proprietary | Open |

## Coding

- Gemini 3.6 Flash: 50.0 (#48)
- Step 3.5 Flash: 42.4 (#105)

| Benchmark | Gemini 3.6 Flash | Step 3.5 Flash |
|---|---|---|
| LMArena Coding | 1491 | 1436 |
| DeepSWE | 46.7% | — |
| FrontierCode | 34.4% | — |
| LMArena WebDev | 1538 | — |
| SciCode | 52.7% | — |
| WeirdML | 56.1% | — |
| ALE-Bench | 715.52 | — |

## Agentic & Tool Use

- Gemini 3.6 Flash: 32.3 (#65)
- Step 3.5 Flash: —

| Benchmark | Gemini 3.6 Flash | Step 3.5 Flash |
|---|---|---|
| APEX-Agents | 46.9% | — |
| GDP.pdf | 14% | — |

## Reasoning

- Gemini 3.6 Flash: 58.8 (#22)
- Step 3.5 Flash: 22.2 (#202)

| Benchmark | Gemini 3.6 Flash | Step 3.5 Flash |
|---|---|---|
| NYT Connections (extended) | 89% | 28.4% |
| LMArena Hard Prompts | 1485 | 1411 |
| ARC-AGI-2 | 60.4% | — |
| ARC-AGI-1 | 91.2% | — |
| CritPt | 10.6% | — |
| Chess Puzzles | 43% | — |
| Mystery Game Puzzles | 30% | — |
| DTBench | 95.5% | — |
| LMCA | 44.9% | — |
| Epoch Capabilities Index | 154.25 | — |

## Math

- Gemini 3.6 Flash: 57.3 (#40)
- Step 3.5 Flash: 42.6 (#84)

| Benchmark | Gemini 3.6 Flash | Step 3.5 Flash |
|---|---|---|
| MathArena Final-Answer Competitions | 70.8% | 66.8% |
| LMArena Math | 1505 | 1408 |
| FrontierMath (Tiers 1-3) | 58.9% | — |
| FrontierMath Tier 4 | 22% | — |
| OTIS Mock AIME 2024-2025 | 94.2% | — |
| ProofBench | 36% | — |

## Knowledge

- Gemini 3.6 Flash: 67.8 (#8)
- Step 3.5 Flash: 39.6 (#132)

| Benchmark | Gemini 3.6 Flash | Step 3.5 Flash |
|---|---|---|
| LMArena Expert | 1488 | 1421 |
| GPQA Diamond | 94.1% | — |
| SimpleQA Verified | 66.2% | — |

## Multimodal

- Gemini 3.6 Flash: 38.5 (#64)
- Step 3.5 Flash: —

| Benchmark | Gemini 3.6 Flash | Step 3.5 Flash |
|---|---|---|
| LMArena Vision | 1298 | — |
| Blueprint-Bench 2 | 31.2% | — |
| Furniture Assembly | 23.3% | — |
| LMArena Document | 1456 | — |

## Multilingual

- Gemini 3.6 Flash: 56.5 (#19)
- Step 3.5 Flash: 50.5 (#119)

| Benchmark | Gemini 3.6 Flash | Step 3.5 Flash |
|---|---|---|
| LMArena Non-English | 1469 | 1385 |
| LMArena Chinese | 1531 | 1447 |
| LMArena French | 1504 | 1421 |
| LMArena German | 1478 | 1405 |
| LMArena Japanese | 1476 | 1354 |
| LMArena Korean | 1431 | 1352 |
| LMArena Russian | 1487 | 1385 |
| LMArena Spanish | 1475 | 1419 |

## Instruction Following

- Gemini 3.6 Flash: 77.0 (#33)
- Step 3.5 Flash: 73.1 (#124)

| Benchmark | Gemini 3.6 Flash | Step 3.5 Flash |
|---|---|---|
| LMArena Instruction Following | 1466 | 1385 |

## Long Context

- Gemini 3.6 Flash: 45.1 (#50)
- Step 3.5 Flash: 42.8 (#117)

| Benchmark | Gemini 3.6 Flash | Step 3.5 Flash |
|---|---|---|
| LMArena Longer Query | 1474 | 1402 |

## Writing & Preference

- Gemini 3.6 Flash: 68.2 (#27)
- Step 3.5 Flash: 58.8 (#113)

| Benchmark | Gemini 3.6 Flash | Step 3.5 Flash |
|---|---|---|
| LMArena Text | 1479 | 1403 |
| LMArena Creative Writing | 1465 | 1357 |
| LMArena Multi-Turn | 1481 | 1405 |
| EQ-Bench Creative Writing | 1604 | — |

## FAQ

### Is Gemini 3.6 Flash better than Step 3.5 Flash?

Gemini 3.6 Flash is the stronger model overall, scoring 54.1 to 42.3 on the Noometry Index. Step 3.5 Flash costs 10.0× 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 3.6 Flash or Step 3.5 Flash?

Step 3.5 Flash is cheaper. It lists at $0.10 per million input tokens and $0.30 per million output tokens; Gemini 3.6 Flash lists at $0.75 and $3.75.

### Is Gemini 3.6 Flash or Step 3.5 Flash better for coding?

Gemini 3.6 Flash scores higher on coding benchmarks: 50.0 versus 42.4 in the Noometry coding category.

### Which has the bigger context window?

Gemini 3.6 Flash does, with 1.05M tokens against 256K.

### How many benchmarks do Gemini 3.6 Flash and Step 3.5 Flash share?

19 benchmarks have published results for both models. Gemini 3.6 Flash has 46 scored results on Noometry and Step 3.5 Flash has 19.