# Inkling vs Sonar

> Inkling is the stronger model overall, scoring 44.1 to 37.8 on the Noometry Index. Sonar costs 2.6× less per token, which makes it the better buy when Inkling's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/inkling-vs-sonar
- Last updated: 2026-10-10
- Shared benchmarks: 0

## Summary

- The widest gap is in reasoning, where Inkling leads 40.6 to 20.3.
- Sonar is cheaper at $1 / $1 per million input/output tokens, against $1.87 / $4.68 for Inkling.
- Sonar accepts more context: 128K tokens versus 66K.
- Inkling has downloadable open weights; the other is API-only.

## Snapshot

| | Inkling | Sonar |
|---|---|---|
| Provider | Thinking Machines Lab | Perplexity |
| Noometry Index | 44.1 | 37.8 |
| Rank | 75 | 184 |
| Context | 66K | 128K |
| Input $/M | $1.87 | $1 |
| Output $/M | $4.68 | $1 |
| Weights | Open | Proprietary |

## Coding

- Inkling: 34.1 (#229)
- Sonar: 35.1 (#217)

| Benchmark | Inkling | Sonar |
|---|---|---|
| FrontierCode | 14% | — |
| LMArena WebDev | 1412 | — |
| FrontierSWE | 4.1% | — |
| SciCode | 47% | — |
| WeirdML | 32.3% | — |
| LiveBench Coding | — | 35.1% |
| LMArena Coding | 1463 | — |
| ALE-Bench | 946 | — |

## Agentic & Tool Use

- Inkling: 29.5 (#76)
- Sonar: —

| Benchmark | Inkling | Sonar |
|---|---|---|
| APEX-Agents | 33.8% | — |
| τ²-bench Banking | 25% | — |

## Reasoning

- Inkling: 40.6 (#48)
- Sonar: 20.3 (#221)

| Benchmark | Inkling | Sonar |
|---|---|---|
| ARC-AGI-2 | 36.5% | — |
| SimpleBench | 50% | — |
| ARC-AGI-1 | 79.5% | — |
| CritPt | 5.4% | — |
| Chess Puzzles | 21% | — |
| LiveBench Reasoning | — | 46.3% |
| LMArena Hard Prompts | 1452 | — |
| DTBench | 87.5% | — |
| LiveBench Data Analysis | — | 37.9% |
| LMCA | 37.6% | — |
| Epoch Capabilities Index | 148.6 | — |
| LiveBench | — | 46.9% |

## Math

- Inkling: 31.2 (#198)
- Sonar: 31.3 (#197)

| Benchmark | Inkling | Sonar |
|---|---|---|
| FrontierMath (Tiers 1-3) | 33.3% | — |
| FrontierMath Tier 4 | 4.9% | — |
| OTIS Mock AIME 2024-2025 | 88.9% | — |
| ProofBench | 0% | — |
| LiveBench Math | — | 41.6% |
| LMArena Math | 1482 | — |

## Knowledge

- Inkling: 55.2 (#44)
- Sonar: —

| Benchmark | Inkling | Sonar |
|---|---|---|
| GPQA Diamond | 88.3% | — |
| SimpleQA Verified | 40.3% | — |
| LMArena Expert | 1468 | — |

## Multilingual

- Inkling: 54.2 (#49)
- Sonar: —

| Benchmark | Inkling | Sonar |
|---|---|---|
| LMArena Non-English | 1434 | — |
| LMArena Chinese | 1495 | — |
| LMArena French | 1453 | — |
| LMArena German | 1456 | — |
| LMArena Japanese | 1428 | — |
| LMArena Korean | 1401 | — |
| LMArena Russian | 1430 | — |
| LMArena Spanish | 1442 | — |

## Instruction Following

- Inkling: 75.3 (#65)
- Sonar: 71.5 (#146)

| Benchmark | Inkling | Sonar |
|---|---|---|
| LiveBench Instruction Following | — | 76.2% |
| LMArena Instruction Following | 1427 | — |

## Long Context

- Inkling: 43.9 (#79)
- Sonar: —

| Benchmark | Inkling | Sonar |
|---|---|---|
| LMArena Longer Query | 1436 | — |

## Writing & Preference

- Inkling: 65.5 (#48)
- Sonar: 52.6 (#166)

| Benchmark | Inkling | Sonar |
|---|---|---|
| LMArena Text | 1443 | — |
| LMArena Creative Writing | 1390 | — |
| EQ-Bench Creative Writing | 1611 | — |
| EQ-Bench 4 | 1226 | — |
| LMArena Multi-Turn | 1436 | — |
| LiveBench Language | — | 44.1% |

## FAQ

### Is Inkling better than Sonar?

Inkling is the stronger model overall, scoring 44.1 to 37.8 on the Noometry Index. Sonar costs 2.6× less per token, which makes it the better buy when Inkling's lead doesn't matter for your workload.

### Which is cheaper, Inkling or Sonar?

Sonar is cheaper. It lists at $1 per million input tokens and $1 per million output tokens; Inkling lists at $1.87 and $4.68.

### Is Inkling or Sonar better for coding?

Sonar scores higher on coding benchmarks: 35.1 versus 34.1 in the Noometry coding category.

### Which has the bigger context window?

Sonar does, with 128K tokens against 66K.

### How many benchmarks do Inkling and Sonar share?

0 benchmarks have published results for both models. Inkling has 41 scored results on Noometry and Sonar has 7.