Model comparison
Claude Sonnet 4.6 vs Inkling-Small
Claude Sonnet 4.6 is the stronger model overall, scoring 50.3 to 46.5 on the Noometry Index. Inkling-Small costs 9.4× less per token, which makes it the better buy when Claude Sonnet 4.6's lead doesn't matter for your workload.
Last verified . 31 shared benchmarks.
Summary
- They share 31 benchmarks with published results for both. Claude Sonnet 4.6 scores higher in 8 categories and Inkling-Small in 1 category; 9 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Claude Sonnet 4.6 leads 70.2 to 59.6.
- The biggest single-benchmark swing is ProofBench: 45% for Claude Sonnet 4.6 and 6% for Inkling-Small.
- Inkling-Small is cheaper at $0.45 / $1.20 per million input/output tokens, against $3 / $15 for Claude Sonnet 4.6.
- Claude Sonnet 4.6 accepts more context: 1M tokens versus 524K.
- Inkling-Small has downloadable open weights; the other is API-only.
Side by side
| Claude Sonnet 4.6 | Inkling-Small | |
|---|---|---|
| Provider | Anthropic | Thinking Machines Lab |
| Noometry Index | 50.3 | 46.5 |
| Released | 2026-02-17 | 2026-07-15 |
| Weights | Proprietary | Open |
| Context window | 1M | 524K |
| Max output | 128K | 1.05M |
| Input $ / M tokens | $3 | $0.45 |
| Output $ / M tokens | $15 | $1.20 |
| Results tracked | 57 | 33 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Sonnet 4.6 leads
Claude Sonnet 4.6: 46.3 (#67), Inkling-Small: 43.6 (#85)
| Benchmark | Claude Sonnet 4.6 | Inkling-Small |
|---|---|---|
| LMArena WebDev | 1522 | 1409 |
| SciCode | 46.8% | 48.7% |
| LMArena Coding | 1504 | 1451 |
| SWE-bench Verified | 75.2% | — |
| DeepSWE | 29.9% | — |
| FrontierCode | 24.3% | — |
| WeirdML | 66.1% | — |
| ALE-Bench | 1,327 | — |
Agentic & Tool Use Not comparable
Claude Sonnet 4.6: 39.1 (#28), Inkling-Small: —
| Benchmark | Claude Sonnet 4.6 | Inkling-Small |
|---|---|---|
| Terminal-Bench | 53.4% | — |
| APEX-Agents | 43% | — |
| OSWorld 2.0 | 9.3% | — |
| DeepResearch Bench | 54.9% | — |
| OSWorld | 72.1% | — |
| ExploitBench | 23.6% | — |
| GBAEval | 48.8% | — |
| GDP.pdf | 18% | — |
| LMArena Search | 1221 | — |
| Vending-Bench 2 | 7,204 | — |
Reasoning Claude Sonnet 4.6 leads
Claude Sonnet 4.6: 46.1 (#45), Inkling-Small: 38.6 (#63)
| Benchmark | Claude Sonnet 4.6 | Inkling-Small |
|---|---|---|
| ARC-AGI-2 | 60.4% | 40.1% |
| ARC-AGI-1 | 86.5% | 84% |
| CritPt | 3.1% | 8.3% |
| Chess Puzzles | 13% | 18% |
| LMArena Hard Prompts | 1484 | 1423 |
| Mystery Game Puzzles | 16% | 6% |
| Epoch Capabilities Index | 152.24 | 150.15 |
| NYT Connections (extended) | 80.9% | — |
| Thematic Generalization | 76.3% | — |
| DTBench | 89.9% | — |
| LMCA | 46.5% | — |
| ForecastBench | 62 | — |
Math Claude Sonnet 4.6 leads
Claude Sonnet 4.6: 52.9 (#49), Inkling-Small: 45.1 (#77)
| Benchmark | Claude Sonnet 4.6 | Inkling-Small |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 85.8% | 90% |
| ProofBench | 45% | 6% |
| LMArena Math | 1462 | 1459 |
| FrontierMath (Tiers 1-3) | — | 46.3% |
| FrontierMath Tier 4 | — | 17.1% |
| FrontierMath (Feb 2025 set) | 32.4% | — |
| FrontierMath Tier 4 (v1) | 8.3% | — |
Knowledge Claude Sonnet 4.6 leads
Claude Sonnet 4.6: 51.7 (#65), Inkling-Small: 48.2 (#77)
| Benchmark | Claude Sonnet 4.6 | Inkling-Small |
|---|---|---|
| GPQA Diamond | 87.4% | 88.5% |
| SimpleQA Verified | 35.5% | 19.1% |
| LMArena Expert | 1500 | 1442 |
| Vectara Hallucination Rate | 10.6% | — |
Multimodal Inkling-Small leads
Claude Sonnet 4.6: 38.0 (#68), Inkling-Small: 39.1 (#62)
| Benchmark | Claude Sonnet 4.6 | Inkling-Small |
|---|---|---|
| LMArena Vision | 1283 | 1235 |
| Blueprint-Bench 2 | 6.7% | — |
| LMArena Document | 1482 | — |
Multilingual Claude Sonnet 4.6 leads
Claude Sonnet 4.6: 54.4 (#41), Inkling-Small: 51.7 (#104)
| Benchmark | Claude Sonnet 4.6 | Inkling-Small |
|---|---|---|
| LMArena Non-English | 1440 | 1402 |
| LMArena Chinese | 1491 | 1465 |
| LMArena French | 1465 | 1436 |
| LMArena German | 1428 | 1405 |
| LMArena Japanese | 1420 | 1405 |
| LMArena Korean | 1411 | 1363 |
| LMArena Russian | 1440 | 1391 |
| LMArena Spanish | 1464 | 1428 |
Instruction Following Claude Sonnet 4.6 leads
Claude Sonnet 4.6: 77.4 (#25), Inkling-Small: 73.8 (#114)
| Benchmark | Claude Sonnet 4.6 | Inkling-Small |
|---|---|---|
| LMArena Instruction Following | 1475 | 1399 |
Long Context Claude Sonnet 4.6 leads
Claude Sonnet 4.6: 45.3 (#44), Inkling-Small: 42.7 (#118)
| Benchmark | Claude Sonnet 4.6 | Inkling-Small |
|---|---|---|
| LMArena Longer Query | 1479 | 1401 |
Writing & Preference Claude Sonnet 4.6 leads
Claude Sonnet 4.6: 70.2 (#22), Inkling-Small: 59.6 (#107)
| Benchmark | Claude Sonnet 4.6 | Inkling-Small |
|---|---|---|
| LMArena Text | 1458 | 1414 |
| LMArena Creative Writing | 1435 | 1331 |
| EQ-Bench Creative Writing | 1810 | 1491 |
| LMArena Multi-Turn | 1464 | 1418 |
| EQ-Bench 4 | 1207 | — |
Frequently asked questions
Is Claude Sonnet 4.6 better than Inkling-Small?
Claude Sonnet 4.6 is the stronger model overall, scoring 50.3 to 46.5 on the Noometry Index. Inkling-Small costs 9.4× less per token, which makes it the better buy when Claude Sonnet 4.6's lead doesn't matter for your workload.
Which is cheaper, Claude Sonnet 4.6 or Inkling-Small?
Inkling-Small is cheaper. It lists at $0.45 per million input tokens and $1.20 per million output tokens; Claude Sonnet 4.6 lists at $3 and $15.
Is Claude Sonnet 4.6 or Inkling-Small better for coding?
Claude Sonnet 4.6 scores higher on coding benchmarks: 46.3 versus 43.6 in the Noometry coding category.
Which has the bigger context window?
Claude Sonnet 4.6 does, with 1M tokens against 524K.
How many benchmarks do Claude Sonnet 4.6 and Inkling-Small share?
31 benchmarks have published results for both models. Claude Sonnet 4.6 has 57 scored results on Noometry and Inkling-Small has 33.