# Gemini 3.5 Flash vs Inkling

> Gemini 3.5 Flash is the stronger model overall, scoring 54.2 to 44.1 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gemini-3-5-flash-vs-inkling
- Last updated: 2026-10-11
- Shared benchmarks: 37

## Summary

- They share 37 benchmarks with published results for both. Gemini 3.5 Flash scores higher in 8 categories and Inkling in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Gemini 3.5 Flash leads 60.7 to 31.3.
- The biggest single-benchmark swing is ARC-AGI-2: 72.1% for Gemini 3.5 Flash and 36.5% for Inkling.
- Inkling is cheaper at $1.87 / $4.68 per million input/output tokens, against $1.50 / $9 for Gemini 3.5 Flash.
- Gemini 3.5 Flash accepts more context: 1.05M tokens versus 66K.
- Inkling has downloadable open weights; the other is API-only.

## Snapshot

| | Gemini 3.5 Flash | Inkling |
|---|---|---|
| Provider | Google | Thinking Machines Lab |
| Noometry Index | 54.2 | 44.1 |
| Rank | 32 | 80 |
| Context | 1.05M | 66K |
| Input $/M | $1.50 | $1.87 |
| Output $/M | $9 | $4.68 |
| Weights | Proprietary | Open |

## Coding

- Gemini 3.5 Flash: 49.4 (#49)
- Inkling: 34.5 (#234)

| Benchmark | Gemini 3.5 Flash | Inkling |
|---|---|---|
| LMArena WebDev | 1499 | 1413 |
| SciCode | 53.1% | 47% |
| WeirdML | 62.6% | 32.3% |
| LMArena Coding | 1492 | 1464 |
| ALE-Bench | 911.02 | 946 |
| SWE-bench Verified | 79.3% | — |
| DeepSWE | 37.4% | — |
| FrontierCode | — | 14% |
| FrontierSWE | — | 4.1% |

## Agentic & Tool Use

- Gemini 3.5 Flash: 24.7 (#114)
- Inkling: 29.6 (#85)

| Benchmark | Gemini 3.5 Flash | Inkling |
|---|---|---|
| APEX-Agents | 27.5% | 33.8% |
| τ²-bench Banking | — | 25% |
| GBAEval | 6.7% | — |
| GDP.pdf | 14% | — |
| Vending-Bench 2 | 5,396 | — |

## Reasoning

- Gemini 3.5 Flash: 62.8 (#18)
- Inkling: 40.4 (#56)

| Benchmark | Gemini 3.5 Flash | Inkling |
|---|---|---|
| ARC-AGI-2 | 72.1% | 36.5% |
| SimpleBench | 76.7% | 50% |
| ARC-AGI-1 | 92.5% | 79.5% |
| CritPt | 13.1% | 5.4% |
| Chess Puzzles | 50% | 21% |
| LMArena Hard Prompts | 1488 | 1451 |
| DTBench | 94.7% | 87.5% |
| LMCA | 47.1% | 37.6% |
| Epoch Capabilities Index | 154.46 | 148.54 |
| NYT Connections (extended) | 92.6% | — |
| EnigmaEval | 25.4% | — |
| EBR-Bench | 4.8% | — |
| Mystery Game Puzzles | 32% | — |
| Surface Evolver Bench | 58.1% | — |
| ForecastBench | 59 | — |

## Math

- Gemini 3.5 Flash: 60.7 (#36)
- Inkling: 31.3 (#225)

| Benchmark | Gemini 3.5 Flash | Inkling |
|---|---|---|
| FrontierMath (Tiers 1-3) | 62.8% | 33.3% |
| FrontierMath Tier 4 | 26.8% | 4.9% |
| OTIS Mock AIME 2024-2025 | 95.6% | 88.9% |
| ProofBench | 31% | 0% |
| LMArena Math | 1504 | 1479 |
| MathArena Final-Answer Competitions | 76.3% | — |
| FrontierMath (Feb 2025 set) | 39% | — |
| FrontierMath Tier 4 (v1) | 14.6% | — |

## Knowledge

- Gemini 3.5 Flash: 66.3 (#11)
- Inkling: 55.1 (#49)

| Benchmark | Gemini 3.5 Flash | Inkling |
|---|---|---|
| GPQA Diamond | 92.8% | 88.3% |
| SimpleQA Verified | 66.2% | 40.3% |
| LMArena Expert | 1495 | 1465 |

## Multimodal

- Gemini 3.5 Flash: 45.7 (#15)
- Inkling: —

| Benchmark | Gemini 3.5 Flash | Inkling |
|---|---|---|
| LMArena Vision | 1310 | — |
| Blueprint-Bench 2 | 33.6% | — |
| LMArena Document | 1463 | — |

## Multilingual

- Gemini 3.5 Flash: 57.0 (#13)
- Inkling: 54.0 (#52)

| Benchmark | Gemini 3.5 Flash | Inkling |
|---|---|---|
| LMArena Non-English | 1476 | 1434 |
| LMArena Chinese | 1526 | 1490 |
| LMArena French | 1490 | 1458 |
| LMArena German | 1492 | 1446 |
| LMArena Japanese | 1486 | 1429 |
| LMArena Korean | 1451 | 1404 |
| LMArena Russian | 1493 | 1429 |
| LMArena Spanish | 1480 | 1448 |

## Instruction Following

- Gemini 3.5 Flash: 77.0 (#30)
- Inkling: 75.1 (#71)

| Benchmark | Gemini 3.5 Flash | Inkling |
|---|---|---|
| LMArena Instruction Following | 1467 | 1426 |

## Long Context

- Gemini 3.5 Flash: 45.4 (#38)
- Inkling: 43.8 (#86)

| Benchmark | Gemini 3.5 Flash | Inkling |
|---|---|---|
| LMArena Longer Query | 1482 | 1434 |

## Writing & Preference

- Gemini 3.5 Flash: 65.5 (#47)
- Inkling: 65.2 (#51)

| Benchmark | Gemini 3.5 Flash | Inkling |
|---|---|---|
| LMArena Text | 1482 | 1441 |
| LMArena Creative Writing | 1470 | 1387 |
| EQ-Bench 4 | 1087 | 1226 |
| LMArena Multi-Turn | 1481 | 1436 |
| EQ-Bench Creative Writing | — | 1611 |

## FAQ

### Is Gemini 3.5 Flash better than Inkling?

Gemini 3.5 Flash is the stronger model overall, scoring 54.2 to 44.1 on the Noometry Index.

### Which is cheaper, Gemini 3.5 Flash or Inkling?

Inkling is cheaper. It lists at $1.87 per million input tokens and $4.68 per million output tokens; Gemini 3.5 Flash lists at $1.50 and $9.

### Is Gemini 3.5 Flash or Inkling better for coding?

Gemini 3.5 Flash scores higher on coding benchmarks: 49.4 versus 34.5 in the Noometry coding category.

### Which has the bigger context window?

Gemini 3.5 Flash does, with 1.05M tokens against 66K.

### How many benchmarks do Gemini 3.5 Flash and Inkling share?

37 benchmarks have published results for both models. Gemini 3.5 Flash has 54 scored results on Noometry and Inkling has 41.