Model comparison
Inkling vs Sonar
Inkling is the stronger model overall, scoring 44.1 to 38.5 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.
Last verified . 0 shared benchmarks.
PerplexitySummary
- The widest gap is in reasoning, where Inkling leads 40.4 to 21.1.
- 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.
Side by side
| Inkling | Sonar | |
|---|---|---|
| Provider | Thinking Machines Lab | Perplexity |
| Noometry Index | 44.1 | 38.5 |
| Released | 2026-07-15 | 2024-01-01 |
| Weights | Open | Proprietary |
| Context window | 66K | 128K |
| Max output | 66K | 4K |
| Input $ / M tokens | $1.87 | $1 |
| Output $ / M tokens | $4.68 | $1 |
| Results tracked | 41 | 7 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Sonar leads
Inkling: 34.5 (#234), Sonar: 35.7 (#221)
| Benchmark | Inkling | Sonar |
|---|---|---|
| FrontierCode | 14% | — |
| LMArena WebDev | 1413 | — |
| FrontierSWE | 4.1% | — |
| SciCode | 47% | — |
| WeirdML | 32.3% | — |
| LiveBench Coding | — | 35.1% |
| LMArena Coding | 1464 | — |
| ALE-Bench | 946 | — |
Agentic & Tool Use Not comparable
Inkling: 29.6 (#85), Sonar: —
| Benchmark | Inkling | Sonar |
|---|---|---|
| APEX-Agents | 33.8% | — |
| τ²-bench Banking | 25% | — |
Reasoning Inkling leads
Inkling: 40.4 (#56), Sonar: 21.1 (#227)
| 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 | 1451 | — |
| DTBench | 87.5% | — |
| LiveBench Data Analysis | — | 37.9% |
| LMCA | 37.6% | — |
| Epoch Capabilities Index | 148.54 | — |
| LiveBench | — | 46.9% |
Math Sonar leads
Inkling: 31.3 (#225), Sonar: 33.7 (#200)
| 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 | 1479 | — |
Knowledge Not comparable
Inkling: 55.1 (#49), Sonar: —
| Benchmark | Inkling | Sonar |
|---|---|---|
| GPQA Diamond | 88.3% | — |
| SimpleQA Verified | 40.3% | — |
| LMArena Expert | 1465 | — |
Multilingual Not comparable
Inkling: 54.0 (#52), Sonar: —
| Benchmark | Inkling | Sonar |
|---|---|---|
| LMArena Non-English | 1434 | — |
| LMArena Chinese | 1490 | — |
| LMArena French | 1458 | — |
| LMArena German | 1446 | — |
| LMArena Japanese | 1429 | — |
| LMArena Korean | 1404 | — |
| LMArena Russian | 1429 | — |
| LMArena Spanish | 1448 | — |
Instruction Following Inkling leads
Inkling: 75.1 (#71), Sonar: 71.4 (#150)
| Benchmark | Inkling | Sonar |
|---|---|---|
| LiveBench Instruction Following | — | 76.2% |
| LMArena Instruction Following | 1426 | — |
Long Context Not comparable
Inkling: 43.8 (#86), Sonar: —
| Benchmark | Inkling | Sonar |
|---|---|---|
| LMArena Longer Query | 1434 | — |
Writing & Preference Inkling leads
Inkling: 65.2 (#51), Sonar: 52.6 (#167)
| Benchmark | Inkling | Sonar |
|---|---|---|
| LMArena Text | 1441 | — |
| LMArena Creative Writing | 1387 | — |
| EQ-Bench Creative Writing | 1611 | — |
| EQ-Bench 4 | 1226 | — |
| LMArena Multi-Turn | 1436 | — |
| LiveBench Language | — | 44.1% |
Frequently asked questions
Is Inkling better than Sonar?
Inkling is the stronger model overall, scoring 44.1 to 38.5 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: 35.7 versus 34.5 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.