# Gemini 3.7 Flash vs Inkling

> Gemini 3.7 Flash is the stronger model overall, scoring 59.8 to 44.1 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gemini-3-7-flash-vs-inkling
- Last updated: 2026-10-10
- Shared benchmarks: 37

## Summary

- They share 37 benchmarks with published results for both. Gemini 3.7 Flash scores higher in 9 categories and Inkling in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Gemini 3.7 Flash leads 69.5 to 31.2.
- The biggest single-benchmark swing is ProofBench: 58% for Gemini 3.7 Flash and 0% for Inkling.
- Gemini 3.7 Flash is cheaper at $0.75 / $3.75 per million input/output tokens, against $1.87 / $4.68 for Inkling.
- Gemini 3.7 Flash accepts more context: 1.05M tokens versus 66K.
- Inkling has downloadable open weights; the other is API-only.

## Snapshot

| | Gemini 3.7 Flash | Inkling |
|---|---|---|
| Provider | Google | Thinking Machines Lab |
| Noometry Index | 59.8 | 44.1 |
| Rank | 11 | 75 |
| Context | 1.05M | 66K |
| Input $/M | $0.75 | $1.87 |
| Output $/M | $3.75 | $4.68 |
| Weights | Proprietary | Open |

## Coding

- Gemini 3.7 Flash: 55.7 (#19)
- Inkling: 34.1 (#229)

| Benchmark | Gemini 3.7 Flash | Inkling |
|---|---|---|
| FrontierCode | 43.6% | 14% |
| LMArena WebDev | 1593 | 1412 |
| FrontierSWE | 20.3% | 4.1% |
| SciCode | 59.8% | 47% |
| LMArena Coding | 1499 | 1463 |
| ALE-Bench | 904.3 | 946 |
| DeepSWE | 65.5% | — |
| WeirdML | — | 32.3% |

## Agentic & Tool Use

- Gemini 3.7 Flash: 42.2 (#18)
- Inkling: 29.5 (#76)

| Benchmark | Gemini 3.7 Flash | Inkling |
|---|---|---|
| APEX-Agents | 67.8% | 33.8% |
| Remote Labor Index | 5% | — |
| τ²-bench Banking | — | 25% |
| GDP.pdf | 23.8% | — |

## Reasoning

- Gemini 3.7 Flash: 70.1 (#12)
- Inkling: 40.6 (#48)

| Benchmark | Gemini 3.7 Flash | Inkling |
|---|---|---|
| ARC-AGI-2 | 84.6% | 36.5% |
| ARC-AGI-1 | 95.5% | 79.5% |
| CritPt | 14.3% | 5.4% |
| Chess Puzzles | 47% | 21% |
| LMArena Hard Prompts | 1497 | 1452 |
| DTBench | 96.8% | 87.5% |
| LMCA | 50.4% | 37.6% |
| Epoch Capabilities Index | 157.72 | 148.6 |
| SimpleBench | — | 50% |
| NYT Connections (extended) | 94% | — |
| Mystery Game Puzzles | 37% | — |

## Math

- Gemini 3.7 Flash: 69.5 (#18)
- Inkling: 31.2 (#198)

| Benchmark | Gemini 3.7 Flash | Inkling |
|---|---|---|
| FrontierMath (Tiers 1-3) | 71.6% | 33.3% |
| FrontierMath Tier 4 | 36.6% | 4.9% |
| OTIS Mock AIME 2024-2025 | 97.2% | 88.9% |
| ProofBench | 58% | 0% |
| LMArena Math | 1511 | 1482 |

## Knowledge

- Gemini 3.7 Flash: 69.8 (#4)
- Inkling: 55.2 (#44)

| Benchmark | Gemini 3.7 Flash | Inkling |
|---|---|---|
| GPQA Diamond | 94.8% | 88.3% |
| SimpleQA Verified | 69.2% | 40.3% |
| LMArena Expert | 1508 | 1468 |

## Multimodal

- Gemini 3.7 Flash: 36.9 (#69)
- Inkling: —

| Benchmark | Gemini 3.7 Flash | Inkling |
|---|---|---|
| LMArena Vision | 1314 | — |
| Furniture Assembly | 26.7% | — |

## Multilingual

- Gemini 3.7 Flash: 57.8 (#7)
- Inkling: 54.2 (#49)

| Benchmark | Gemini 3.7 Flash | Inkling |
|---|---|---|
| LMArena Non-English | 1485 | 1434 |
| LMArena Chinese | 1553 | 1495 |
| LMArena French | 1512 | 1453 |
| LMArena German | 1485 | 1456 |
| LMArena Japanese | 1506 | 1428 |
| LMArena Korean | 1486 | 1401 |
| LMArena Russian | 1519 | 1430 |
| LMArena Spanish | 1507 | 1442 |

## Instruction Following

- Gemini 3.7 Flash: 78.0 (#12)
- Inkling: 75.3 (#65)

| Benchmark | Gemini 3.7 Flash | Inkling |
|---|---|---|
| LMArena Instruction Following | 1486 | 1427 |

## Long Context

- Gemini 3.7 Flash: 45.8 (#28)
- Inkling: 43.9 (#79)

| Benchmark | Gemini 3.7 Flash | Inkling |
|---|---|---|
| LMArena Longer Query | 1493 | 1436 |

## Writing & Preference

- Gemini 3.7 Flash: 71.4 (#19)
- Inkling: 65.5 (#48)

| Benchmark | Gemini 3.7 Flash | Inkling |
|---|---|---|
| LMArena Text | 1487 | 1443 |
| LMArena Creative Writing | 1490 | 1390 |
| EQ-Bench Creative Writing | 1723 | 1611 |
| LMArena Multi-Turn | 1495 | 1436 |
| EQ-Bench 4 | — | 1226 |

## FAQ

### Is Gemini 3.7 Flash better than Inkling?

Gemini 3.7 Flash is the stronger model overall, scoring 59.8 to 44.1 on the Noometry Index.

### Which is cheaper, Gemini 3.7 Flash or Inkling?

Gemini 3.7 Flash is cheaper. It lists at $0.75 per million input tokens and $3.75 per million output tokens; Inkling lists at $1.87 and $4.68.

### Is Gemini 3.7 Flash or Inkling better for coding?

Gemini 3.7 Flash scores higher on coding benchmarks: 55.7 versus 34.1 in the Noometry coding category.

### Which has the bigger context window?

Gemini 3.7 Flash does, with 1.05M tokens against 66K.

### How many benchmarks do Gemini 3.7 Flash and Inkling share?

37 benchmarks have published results for both models. Gemini 3.7 Flash has 44 scored results on Noometry and Inkling has 41.