Model comparison
Inkling-Small vs Sonar
Inkling-Small is the stronger model overall, scoring 46.5 to 38.5 on the Noometry Index.
Last verified . 0 shared benchmarks.
PerplexitySummary
- The widest gap is in reasoning, where Inkling-Small leads 38.6 to 21.1.
- Inkling-Small is cheaper at $0.45 / $1.20 per million input/output tokens, against $1 / $1 for Sonar.
- Inkling-Small accepts more context: 524K tokens versus 128K.
- Inkling-Small has downloadable open weights; the other is API-only.
Side by side
| Inkling-Small | Sonar | |
|---|---|---|
| Provider | Thinking Machines Lab | Perplexity |
| Noometry Index | 46.5 | 38.5 |
| Released | 2026-07-15 | 2024-01-01 |
| Weights | Open | Proprietary |
| Context window | 524K | 128K |
| Max output | 1.05M | 4K |
| Input $ / M tokens | $0.45 | $1 |
| Output $ / M tokens | $1.20 | $1 |
| Results tracked | 33 | 7 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Inkling-Small leads
Inkling-Small: 43.6 (#85), Sonar: 35.7 (#221)
| Benchmark | Inkling-Small | Sonar |
|---|---|---|
| LMArena WebDev | 1409 | — |
| SciCode | 48.7% | — |
| LiveBench Coding | — | 35.1% |
| LMArena Coding | 1451 | — |
Reasoning Inkling-Small leads
Inkling-Small: 38.6 (#63), Sonar: 21.1 (#227)
| Benchmark | Inkling-Small | Sonar |
|---|---|---|
| ARC-AGI-2 | 40.1% | — |
| ARC-AGI-1 | 84% | — |
| CritPt | 8.3% | — |
| Chess Puzzles | 18% | — |
| LiveBench Reasoning | — | 46.3% |
| LMArena Hard Prompts | 1423 | — |
| Mystery Game Puzzles | 6% | — |
| LiveBench Data Analysis | — | 37.9% |
| Epoch Capabilities Index | 150.15 | — |
| LiveBench | — | 46.9% |
Math Inkling-Small leads
Inkling-Small: 45.1 (#77), Sonar: 33.7 (#200)
| Benchmark | Inkling-Small | Sonar |
|---|---|---|
| FrontierMath (Tiers 1-3) | 46.3% | — |
| FrontierMath Tier 4 | 17.1% | — |
| OTIS Mock AIME 2024-2025 | 90% | — |
| ProofBench | 6% | — |
| LiveBench Math | — | 41.6% |
| LMArena Math | 1459 | — |
Knowledge Not comparable
Inkling-Small: 48.2 (#77), Sonar: —
| Benchmark | Inkling-Small | Sonar |
|---|---|---|
| GPQA Diamond | 88.5% | — |
| SimpleQA Verified | 19.1% | — |
| LMArena Expert | 1442 | — |
Multimodal Not comparable
Inkling-Small: 39.1 (#62), Sonar: —
| Benchmark | Inkling-Small | Sonar |
|---|---|---|
| LMArena Vision | 1235 | — |
Multilingual Not comparable
Inkling-Small: 51.7 (#104), Sonar: —
| Benchmark | Inkling-Small | Sonar |
|---|---|---|
| LMArena Non-English | 1402 | — |
| LMArena Chinese | 1465 | — |
| LMArena French | 1436 | — |
| LMArena German | 1405 | — |
| LMArena Japanese | 1405 | — |
| LMArena Korean | 1363 | — |
| LMArena Russian | 1391 | — |
| LMArena Spanish | 1428 | — |
Instruction Following Inkling-Small leads
Inkling-Small: 73.8 (#114), Sonar: 71.4 (#150)
| Benchmark | Inkling-Small | Sonar |
|---|---|---|
| LiveBench Instruction Following | — | 76.2% |
| LMArena Instruction Following | 1399 | — |
Long Context Not comparable
Inkling-Small: 42.7 (#118), Sonar: —
| Benchmark | Inkling-Small | Sonar |
|---|---|---|
| LMArena Longer Query | 1401 | — |
Writing & Preference Inkling-Small leads
Inkling-Small: 59.6 (#107), Sonar: 52.6 (#167)
| Benchmark | Inkling-Small | Sonar |
|---|---|---|
| LMArena Text | 1414 | — |
| LMArena Creative Writing | 1331 | — |
| EQ-Bench Creative Writing | 1491 | — |
| LMArena Multi-Turn | 1418 | — |
| LiveBench Language | — | 44.1% |
Frequently asked questions
Is Inkling-Small better than Sonar?
Inkling-Small is the stronger model overall, scoring 46.5 to 38.5 on the Noometry Index.
Which is cheaper, Inkling-Small or Sonar?
Inkling-Small is cheaper. It lists at $0.45 per million input tokens and $1.20 per million output tokens; Sonar lists at $1 and $1.
Is Inkling-Small or Sonar better for coding?
Inkling-Small scores higher on coding benchmarks: 43.6 versus 35.7 in the Noometry coding category.
Which has the bigger context window?
Inkling-Small does, with 524K tokens against 128K.
How many benchmarks do Inkling-Small and Sonar share?
0 benchmarks have published results for both models. Inkling-Small has 33 scored results on Noometry and Sonar has 7.