# Gemini 3.6 Flash vs Gemini 3.8 Flash

> Gemini 3.8 Flash is the stronger model overall, scoring 61.8 to 54.1 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gemini-3-6-flash-vs-gemini-3-8-flash
- Last updated: 2026-10-10
- Shared benchmarks: 44

## Summary

- They share 44 benchmarks with published results for both. Gemini 3.6 Flash scores higher in 0 categories and Gemini 3.8 Flash in 10 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Gemini 3.8 Flash leads 76.9 to 58.8.
- The biggest single-benchmark swing is ARC-AGI-2: 60.4% for Gemini 3.6 Flash and 89.2% for Gemini 3.8 Flash.
- Both cost about the same: $0.75 input and $3.75 output per million tokens.

## Snapshot

| | Gemini 3.6 Flash | Gemini 3.8 Flash |
|---|---|---|
| Provider | Google | Google |
| Noometry Index | 54.1 | 61.8 |
| Rank | 33 | 11 |
| Context | 1.05M | 1.05M |
| Input $/M | $0.75 | $0.75 |
| Output $/M | $3.75 | $3.75 |
| Weights | Proprietary | Proprietary |

## Coding

- Gemini 3.6 Flash: 50.0 (#48)
- Gemini 3.8 Flash: 59.2 (#15)

| Benchmark | Gemini 3.6 Flash | Gemini 3.8 Flash |
|---|---|---|
| DeepSWE | 46.7% | 73.8% |
| FrontierCode | 34.4% | 41.2% |
| LMArena WebDev | 1538 | 1584 |
| SciCode | 52.7% | 56.6% |
| WeirdML | 56.1% | 84.8% |
| LMArena Coding | 1491 | 1510 |
| ALE-Bench | 715.52 | 1,270 |
| CursorBench | — | 39.6% |
| FrontierSWE | — | 19.6% |

## Agentic & Tool Use

- Gemini 3.6 Flash: 32.3 (#65)
- Gemini 3.8 Flash: 41.8 (#21)

| Benchmark | Gemini 3.6 Flash | Gemini 3.8 Flash |
|---|---|---|
| APEX-Agents | 46.9% | 64.3% |
| GDP.pdf | 14% | 23.4% |
| Remote Labor Index | — | 5.8% |
| Vending-Bench 2 | — | 5,094 |

## Reasoning

- Gemini 3.6 Flash: 58.8 (#22)
- Gemini 3.8 Flash: 76.9 (#5)

| Benchmark | Gemini 3.6 Flash | Gemini 3.8 Flash |
|---|---|---|
| ARC-AGI-2 | 60.4% | 89.2% |
| NYT Connections (extended) | 89% | 97.4% |
| ARC-AGI-1 | 91.2% | 98.5% |
| CritPt | 10.6% | 18.3% |
| Chess Puzzles | 43% | 61% |
| LMArena Hard Prompts | 1485 | 1508 |
| Mystery Game Puzzles | 30% | 47% |
| DTBench | 95.5% | 95.7% |
| LMCA | 44.9% | 52.9% |
| Epoch Capabilities Index | 154.25 | 156.71 |
| Surface Evolver Bench | — | 76.9% |

## Math

- Gemini 3.6 Flash: 57.3 (#40)
- Gemini 3.8 Flash: 65.3 (#28)

| Benchmark | Gemini 3.6 Flash | Gemini 3.8 Flash |
|---|---|---|
| FrontierMath (Tiers 1-3) | 58.9% | 68.4% |
| FrontierMath Tier 4 | 22% | 22% |
| OTIS Mock AIME 2024-2025 | 94.2% | 98.9% |
| ProofBench | 36% | 48% |
| LMArena Math | 1505 | 1528 |
| MathArena Final-Answer Competitions | 70.8% | — |

## Knowledge

- Gemini 3.6 Flash: 67.8 (#8)
- Gemini 3.8 Flash: 74.8 (#2)

| Benchmark | Gemini 3.6 Flash | Gemini 3.8 Flash |
|---|---|---|
| GPQA Diamond | 94.1% | 95.4% |
| SimpleQA Verified | 66.2% | 69.7% |
| LMArena Expert | 1488 | 1524 |
| Humanity's Last Exam | — | 44.5% |

## Multimodal

- Gemini 3.6 Flash: 38.5 (#64)
- Gemini 3.8 Flash: 40.7 (#45)

| Benchmark | Gemini 3.6 Flash | Gemini 3.8 Flash |
|---|---|---|
| LMArena Vision | 1298 | 1314 |
| Blueprint-Bench 2 | 31.2% | 38.6% |
| Furniture Assembly | 23.3% | 31.7% |
| LMArena Document | 1456 | — |

## Multilingual

- Gemini 3.6 Flash: 56.5 (#19)
- Gemini 3.8 Flash: 58.0 (#5)

| Benchmark | Gemini 3.6 Flash | Gemini 3.8 Flash |
|---|---|---|
| LMArena Non-English | 1469 | 1491 |
| LMArena Chinese | 1531 | 1554 |
| LMArena French | 1504 | 1498 |
| LMArena German | 1478 | 1493 |
| LMArena Japanese | 1476 | 1502 |
| LMArena Korean | 1431 | 1459 |
| LMArena Russian | 1487 | 1515 |
| LMArena Spanish | 1475 | 1485 |

## Instruction Following

- Gemini 3.6 Flash: 77.0 (#33)
- Gemini 3.8 Flash: 78.0 (#13)

| Benchmark | Gemini 3.6 Flash | Gemini 3.8 Flash |
|---|---|---|
| LMArena Instruction Following | 1466 | 1490 |

## Long Context

- Gemini 3.6 Flash: 45.1 (#50)
- Gemini 3.8 Flash: 46.3 (#24)

| Benchmark | Gemini 3.6 Flash | Gemini 3.8 Flash |
|---|---|---|
| LMArena Longer Query | 1474 | 1508 |

## Writing & Preference

- Gemini 3.6 Flash: 68.2 (#27)
- Gemini 3.8 Flash: 72.2 (#15)

| Benchmark | Gemini 3.6 Flash | Gemini 3.8 Flash |
|---|---|---|
| LMArena Text | 1479 | 1499 |
| LMArena Creative Writing | 1465 | 1492 |
| EQ-Bench Creative Writing | 1604 | 1748 |
| LMArena Multi-Turn | 1481 | 1501 |

## FAQ

### Is Gemini 3.6 Flash better than Gemini 3.8 Flash?

Gemini 3.8 Flash is the stronger model overall, scoring 61.8 to 54.1 on the Noometry Index.

### Which is cheaper, Gemini 3.6 Flash or Gemini 3.8 Flash?

Gemini 3.8 Flash is cheaper. It lists at $0.75 per million input tokens and $3.75 per million output tokens; Gemini 3.6 Flash lists at $0.75 and $3.75.

### Is Gemini 3.6 Flash or Gemini 3.8 Flash better for coding?

Gemini 3.8 Flash scores higher on coding benchmarks: 59.2 versus 50.0 in the Noometry coding category.

### Which has the bigger context window?

Both accept 1.05M tokens.

### How many benchmarks do Gemini 3.6 Flash and Gemini 3.8 Flash share?

44 benchmarks have published results for both models. Gemini 3.6 Flash has 46 scored results on Noometry and Gemini 3.8 Flash has 50.