# Gemini 3.1 Pro Preview vs Inkling

> Gemini 3.1 Pro Preview is the stronger model overall, scoring 56.7 to 44.1 on the Noometry Index. Inkling costs 1.7× less per token, which makes it the better buy when Gemini 3.1 Pro Preview's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/gemini-3-1-pro-preview-vs-inkling
- Last updated: 2026-10-11
- Shared benchmarks: 39

## Summary

- They share 39 benchmarks with published results for both. Gemini 3.1 Pro Preview scores higher in 9 categories and Inkling in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Gemini 3.1 Pro Preview leads 71.7 to 40.4.
- The biggest single-benchmark swing is ARC-AGI-2: 77.1% for Gemini 3.1 Pro Preview and 36.5% for Inkling.
- Inkling is cheaper at $1.87 / $4.68 per million input/output tokens, against $2 / $12 for Gemini 3.1 Pro Preview.
- Gemini 3.1 Pro Preview accepts more context: 1.05M tokens versus 66K.
- Inkling has downloadable open weights; the other is API-only.

## Snapshot

| | Gemini 3.1 Pro Preview | Inkling |
|---|---|---|
| Provider | Google | Thinking Machines Lab |
| Noometry Index | 56.7 | 44.1 |
| Rank | 23 | 80 |
| Context | 1.05M | 66K |
| Input $/M | $2 | $1.87 |
| Output $/M | $12 | $4.68 |
| Weights | Proprietary | Open |

## Coding

- Gemini 3.1 Pro Preview: 42.5 (#99)
- Inkling: 34.5 (#234)

| Benchmark | Gemini 3.1 Pro Preview | Inkling |
|---|---|---|
| LMArena WebDev | 1447 | 1413 |
| SciCode | 58.9% | 47% |
| WeirdML | 72.1% | 32.3% |
| LMArena Coding | 1484 | 1464 |
| ALE-Bench | 1,161 | 946 |
| SWE-bench Verified | 75.6% | — |
| DeepSWE | 11.7% | — |
| FrontierCode | — | 14% |
| FrontierSWE | — | 4.1% |
| GSO | 22.6% | — |
| MirrorCode | 8.9% | — |
| AlgoTune | 2.02 | — |

## Agentic & Tool Use

- Gemini 3.1 Pro Preview: 37.7 (#34)
- Inkling: 29.6 (#85)

| Benchmark | Gemini 3.1 Pro Preview | Inkling |
|---|---|---|
| APEX-Agents | 35.3% | 33.8% |
| τ²-bench Banking | 26% | 25% |
| Terminal-Bench | 80.2% | — |
| DeepResearch Bench | 47.8% | — |
| PostTrainBench | 22% | — |
| BALROG | 57% | — |
| ExploitBench | 26.1% | — |
| GBAEval | 0.8% | — |
| GDP.pdf | 17% | — |
| LMArena Search | 1211 | — |
| METR Time Horizons | 77% | — |
| Vending-Bench 2 | 3,774 | — |

## Reasoning

- Gemini 3.1 Pro Preview: 71.7 (#12)
- Inkling: 40.4 (#56)

| Benchmark | Gemini 3.1 Pro Preview | Inkling |
|---|---|---|
| ARC-AGI-2 | 77.1% | 36.5% |
| SimpleBench | 79.6% | 50% |
| ARC-AGI-1 | 98% | 79.5% |
| CritPt | 17.7% | 5.4% |
| Chess Puzzles | 55% | 21% |
| LMArena Hard Prompts | 1485 | 1451 |
| DTBench | 97.1% | 87.5% |
| LMCA | 53.8% | 37.6% |
| Epoch Capabilities Index | 154.77 | 148.54 |
| NYT Connections (extended) | 97.4% | — |
| EnigmaEval | 36.8% | — |
| Thematic Generalization | 79.4% | — |
| EBR-Bench | 14.3% | — |
| Mystery Game Puzzles | 34% | — |
| ForecastBench | 59 | — |

## Math

- Gemini 3.1 Pro Preview: 62.1 (#34)
- Inkling: 31.3 (#225)

| Benchmark | Gemini 3.1 Pro Preview | Inkling |
|---|---|---|
| FrontierMath (Tiers 1-3) | 59.6% | 33.3% |
| FrontierMath Tier 4 | 26.8% | 4.9% |
| OTIS Mock AIME 2024-2025 | 95.6% | 88.9% |
| ProofBench | 26% | 0% |
| LMArena Math | 1485 | 1479 |
| MathArena Final-Answer Competitions | 86.5% | — |
| FrontierMath (Feb 2025 set) | 36.9% | — |
| FrontierMath Tier 4 (v1) | 16.7% | — |

## Knowledge

- Gemini 3.1 Pro Preview: 71.8 (#3)
- Inkling: 55.1 (#49)

| Benchmark | Gemini 3.1 Pro Preview | Inkling |
|---|---|---|
| GPQA Diamond | 94.4% | 88.3% |
| SimpleQA Verified | 73.5% | 40.3% |
| LMArena Expert | 1485 | 1465 |
| Humanity's Last Exam | 46.4% | — |
| Vectara Hallucination Rate | 10.4% | — |

## Multimodal

- Gemini 3.1 Pro Preview: 37.9 (#69)
- Inkling: —

| Benchmark | Gemini 3.1 Pro Preview | Inkling |
|---|---|---|
| LMArena Vision | 1296 | — |
| Blueprint-Bench 2 | 26.5% | — |
| Furniture Assembly | 26.7% | — |
| LMArena Document | 1444 | — |

## Multilingual

- Gemini 3.1 Pro Preview: 57.0 (#12)
- Inkling: 54.0 (#52)

| Benchmark | Gemini 3.1 Pro Preview | Inkling |
|---|---|---|
| LMArena Non-English | 1477 | 1434 |
| LMArena Chinese | 1529 | 1490 |
| LMArena French | 1487 | 1458 |
| LMArena German | 1491 | 1446 |
| LMArena Japanese | 1493 | 1429 |
| LMArena Korean | 1455 | 1404 |
| LMArena Russian | 1498 | 1429 |
| LMArena Spanish | 1479 | 1448 |

## Instruction Following

- Gemini 3.1 Pro Preview: 77.0 (#32)
- Inkling: 75.1 (#71)

| Benchmark | Gemini 3.1 Pro Preview | Inkling |
|---|---|---|
| LMArena Instruction Following | 1466 | 1426 |

## Long Context

- Gemini 3.1 Pro Preview: 47.4 (#18)
- Inkling: 43.8 (#86)

| Benchmark | Gemini 3.1 Pro Preview | Inkling |
|---|---|---|
| LMArena Longer Query | 1483 | 1434 |
| CL-bench | 20.8% | — |
| CL-bench Life | 16.9% | — |

## Writing & Preference

- Gemini 3.1 Pro Preview: 66.1 (#37)
- Inkling: 65.2 (#51)

| Benchmark | Gemini 3.1 Pro Preview | Inkling |
|---|---|---|
| LMArena Text | 1481 | 1441 |
| LMArena Creative Writing | 1482 | 1387 |
| EQ-Bench Creative Writing | 1491 | 1611 |
| EQ-Bench 4 | 1142 | 1226 |
| LMArena Multi-Turn | 1488 | 1436 |

## FAQ

### Is Gemini 3.1 Pro Preview better than Inkling?

Gemini 3.1 Pro Preview is the stronger model overall, scoring 56.7 to 44.1 on the Noometry Index. Inkling costs 1.7× less per token, which makes it the better buy when Gemini 3.1 Pro Preview's lead doesn't matter for your workload.

### Which is cheaper, Gemini 3.1 Pro Preview or Inkling?

Inkling is cheaper. It lists at $1.87 per million input tokens and $4.68 per million output tokens; Gemini 3.1 Pro Preview lists at $2 and $12.

### Is Gemini 3.1 Pro Preview or Inkling better for coding?

Gemini 3.1 Pro Preview scores higher on coding benchmarks: 42.5 versus 34.5 in the Noometry coding category.

### Which has the bigger context window?

Gemini 3.1 Pro Preview does, with 1.05M tokens against 66K.

### How many benchmarks do Gemini 3.1 Pro Preview and Inkling share?

39 benchmarks have published results for both models. Gemini 3.1 Pro Preview has 71 scored results on Noometry and Inkling has 41.