# Gemini 4 Argon vs Inkling

> Gemini 4 Argon is the stronger model overall, scoring 56.5 to 44.1 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gemini-4-argon-vs-inkling
- Last updated: 2026-10-11
- Shared benchmarks: 19

## Summary

- They share 19 benchmarks with published results for both. Gemini 4 Argon scores higher in 8 categories and Inkling in 1 category; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Gemini 4 Argon leads 73.9 to 31.3.
- The biggest single-benchmark swing is ProofBench: 99% for Gemini 4 Argon and 0% for Inkling.
- Inkling has downloadable open weights; the other is API-only.

## Snapshot

| | Gemini 4 Argon | Inkling |
|---|---|---|
| Provider | Google | Thinking Machines Lab |
| Noometry Index | 56.5 | 44.1 |
| Rank | 24 | 80 |
| Context | — | 66K |
| Input $/M | — | $1.87 |
| Output $/M | — | $4.68 |
| Weights | Proprietary | Open |

## Coding

- Gemini 4 Argon: 62.0 (#9)
- Inkling: 34.5 (#234)

| Benchmark | Gemini 4 Argon | Inkling |
|---|---|---|
| LMArena WebDev | 1678 | 1413 |
| FrontierSWE | 55% | 4.1% |
| SciCode | 61.8% | 47% |
| LMArena Coding | 1550 | 1464 |
| FrontierCode | — | 14% |
| WeirdML | — | 32.3% |
| ALE-Bench | — | 946 |

## Agentic & Tool Use

- Gemini 4 Argon: 49.2 (#8)
- Inkling: 29.6 (#85)

| Benchmark | Gemini 4 Argon | Inkling |
|---|---|---|
| APEX-Agents | 82.2% | 33.8% |
| τ²-bench Banking | — | 25% |
| Vending-Bench 2 | 13,718 | — |

## Reasoning

- Gemini 4 Argon: 44.2 (#47)
- Inkling: 40.4 (#56)

| Benchmark | Gemini 4 Argon | Inkling |
|---|---|---|
| CritPt | 27.1% | 5.4% |
| LMArena Hard Prompts | 1548 | 1451 |
| ARC-AGI-2 | — | 36.5% |
| SimpleBench | — | 50% |
| ARC-AGI-1 | — | 79.5% |
| Chess Puzzles | — | 21% |
| DTBench | — | 87.5% |
| LMCA | — | 37.6% |
| Epoch Capabilities Index | — | 148.54 |

## Math

- Gemini 4 Argon: 73.9 (#17)
- Inkling: 31.3 (#225)

| Benchmark | Gemini 4 Argon | Inkling |
|---|---|---|
| ProofBench | 99% | 0% |
| LMArena Math | 1536 | 1479 |
| FrontierMath (Tiers 1-3) | — | 33.3% |
| FrontierMath Tier 4 | — | 4.9% |
| OTIS Mock AIME 2024-2025 | — | 88.9% |

## Knowledge

- Gemini 4 Argon: 43.9 (#89)
- Inkling: 55.1 (#49)

| Benchmark | Gemini 4 Argon | Inkling |
|---|---|---|
| LMArena Expert | 1553 | 1465 |
| GPQA Diamond | — | 88.3% |
| SimpleQA Verified | — | 40.3% |

## Multimodal

- Gemini 4 Argon: 46.5 (#14)
- Inkling: —

| Benchmark | Gemini 4 Argon | Inkling |
|---|---|---|
| Blueprint-Bench 2 | 54.4% | — |

## Multilingual

- Gemini 4 Argon: 60.3 (#1)
- Inkling: 54.0 (#52)

| Benchmark | Gemini 4 Argon | Inkling |
|---|---|---|
| LMArena Non-English | 1523 | 1434 |
| LMArena Chinese | 1610 | 1490 |
| LMArena Russian | 1537 | 1429 |
| LMArena Spanish | 1497 | 1448 |
| LMArena French | — | 1458 |
| LMArena German | — | 1446 |
| LMArena Japanese | — | 1429 |
| LMArena Korean | — | 1404 |

## Instruction Following

- Gemini 4 Argon: 80.1 (#2)
- Inkling: 75.1 (#71)

| Benchmark | Gemini 4 Argon | Inkling |
|---|---|---|
| LMArena Instruction Following | 1538 | 1426 |

## Long Context

- Gemini 4 Argon: 47.6 (#15)
- Inkling: 43.8 (#86)

| Benchmark | Gemini 4 Argon | Inkling |
|---|---|---|
| LMArena Longer Query | 1549 | 1434 |

## Writing & Preference

- Gemini 4 Argon: 71.4 (#19)
- Inkling: 65.2 (#51)

| Benchmark | Gemini 4 Argon | Inkling |
|---|---|---|
| LMArena Text | 1534 | 1441 |
| LMArena Creative Writing | 1531 | 1387 |
| LMArena Multi-Turn | 1557 | 1436 |
| EQ-Bench Creative Writing | — | 1611 |
| EQ-Bench 4 | — | 1226 |

## FAQ

### Is Gemini 4 Argon better than Inkling?

Gemini 4 Argon is the stronger model overall, scoring 56.5 to 44.1 on the Noometry Index.

### Is Gemini 4 Argon or Inkling better for coding?

Gemini 4 Argon scores higher on coding benchmarks: 62.0 versus 34.5 in the Noometry coding category.

### How many benchmarks do Gemini 4 Argon and Inkling share?

19 benchmarks have published results for both models. Gemini 4 Argon has 21 scored results on Noometry and Inkling has 41.