Model comparison
Inkling vs Inkling-Small
Inkling-Small is the stronger model overall, scoring 46.5 to 44.1 on the Noometry Index.
Last verified . 31 shared benchmarks.
Summary
- They share 31 benchmarks with published results for both. Inkling scores higher in 6 categories and Inkling-Small in 2 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Inkling-Small leads 45.1 to 31.3.
- The biggest single-benchmark swing is SimpleQA Verified: 40.3% for Inkling and 19.1% for Inkling-Small.
- Inkling-Small is cheaper at $0.45 / $1.20 per million input/output tokens, against $1.87 / $4.68 for Inkling.
- Inkling-Small accepts more context: 524K tokens versus 66K.
Side by side
| Inkling | Inkling-Small | |
|---|---|---|
| Provider | Thinking Machines Lab | Thinking Machines Lab |
| Noometry Index | 44.1 | 46.5 |
| Released | 2026-07-15 | 2026-07-15 |
| Weights | Open | Open |
| Context window | 66K | 524K |
| Max output | 66K | 1.05M |
| Input $ / M tokens | $1.87 | $0.45 |
| Output $ / M tokens | $4.68 | $1.20 |
| Results tracked | 41 | 33 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Inkling-Small leads
Inkling: 34.5 (#234), Inkling-Small: 43.6 (#85)
| Benchmark | Inkling | Inkling-Small |
|---|---|---|
| LMArena WebDev | 1413 | 1409 |
| SciCode | 47% | 48.7% |
| LMArena Coding | 1464 | 1451 |
| FrontierCode | 14% | — |
| FrontierSWE | 4.1% | — |
| WeirdML | 32.3% | — |
| ALE-Bench | 946 | — |
Agentic & Tool Use Not comparable
Inkling: 29.6 (#85), Inkling-Small: —
| Benchmark | Inkling | Inkling-Small |
|---|---|---|
| APEX-Agents | 33.8% | — |
| τ²-bench Banking | 25% | — |
Reasoning Inkling leads
Inkling: 40.4 (#56), Inkling-Small: 38.6 (#63)
| Benchmark | Inkling | Inkling-Small |
|---|---|---|
| ARC-AGI-2 | 36.5% | 40.1% |
| ARC-AGI-1 | 79.5% | 84% |
| CritPt | 5.4% | 8.3% |
| Chess Puzzles | 21% | 18% |
| LMArena Hard Prompts | 1451 | 1423 |
| Epoch Capabilities Index | 148.54 | 150.15 |
| SimpleBench | 50% | — |
| Mystery Game Puzzles | — | 6% |
| DTBench | 87.5% | — |
| LMCA | 37.6% | — |
Math Inkling-Small leads
Inkling: 31.3 (#225), Inkling-Small: 45.1 (#77)
| Benchmark | Inkling | Inkling-Small |
|---|---|---|
| FrontierMath (Tiers 1-3) | 33.3% | 46.3% |
| FrontierMath Tier 4 | 4.9% | 17.1% |
| OTIS Mock AIME 2024-2025 | 88.9% | 90% |
| ProofBench | 0% | 6% |
| LMArena Math | 1479 | 1459 |
Knowledge Inkling leads
Inkling: 55.1 (#49), Inkling-Small: 48.2 (#77)
| Benchmark | Inkling | Inkling-Small |
|---|---|---|
| GPQA Diamond | 88.3% | 88.5% |
| SimpleQA Verified | 40.3% | 19.1% |
| LMArena Expert | 1465 | 1442 |
Multimodal Not comparable
Inkling: —, Inkling-Small: 39.1 (#62)
| Benchmark | Inkling | Inkling-Small |
|---|---|---|
| LMArena Vision | — | 1235 |
Multilingual Inkling leads
Inkling: 54.0 (#52), Inkling-Small: 51.7 (#104)
| Benchmark | Inkling | Inkling-Small |
|---|---|---|
| LMArena Non-English | 1434 | 1402 |
| LMArena Chinese | 1490 | 1465 |
| LMArena French | 1458 | 1436 |
| LMArena German | 1446 | 1405 |
| LMArena Japanese | 1429 | 1405 |
| LMArena Korean | 1404 | 1363 |
| LMArena Russian | 1429 | 1391 |
| LMArena Spanish | 1448 | 1428 |
Instruction Following Inkling leads
Inkling: 75.1 (#71), Inkling-Small: 73.8 (#114)
| Benchmark | Inkling | Inkling-Small |
|---|---|---|
| LMArena Instruction Following | 1426 | 1399 |
Long Context Inkling leads
Inkling: 43.8 (#86), Inkling-Small: 42.7 (#118)
| Benchmark | Inkling | Inkling-Small |
|---|---|---|
| LMArena Longer Query | 1434 | 1401 |
Writing & Preference Inkling leads
Inkling: 65.2 (#51), Inkling-Small: 59.6 (#107)
| Benchmark | Inkling | Inkling-Small |
|---|---|---|
| LMArena Text | 1441 | 1414 |
| LMArena Creative Writing | 1387 | 1331 |
| EQ-Bench Creative Writing | 1611 | 1491 |
| LMArena Multi-Turn | 1436 | 1418 |
| EQ-Bench 4 | 1226 | — |
Frequently asked questions
Is Inkling better than Inkling-Small?
Inkling-Small is the stronger model overall, scoring 46.5 to 44.1 on the Noometry Index.
Which is cheaper, Inkling or Inkling-Small?
Inkling-Small is cheaper. It lists at $0.45 per million input tokens and $1.20 per million output tokens; Inkling lists at $1.87 and $4.68.
Is Inkling or Inkling-Small better for coding?
Inkling-Small scores higher on coding benchmarks: 43.6 versus 34.5 in the Noometry coding category.
Which has the bigger context window?
Inkling-Small does, with 524K tokens against 66K.
How many benchmarks do Inkling and Inkling-Small share?
31 benchmarks have published results for both models. Inkling has 41 scored results on Noometry and Inkling-Small has 33.