Model comparison
Inkling-Small vs o1
Inkling-Small is the stronger model overall, scoring 46.5 to 40.9 on the Noometry Index.
Last verified . 25 shared benchmarks.
Summary
- They share 25 benchmarks with published results for both. Inkling-Small scores higher in 6 categories and o1 in 3 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Inkling-Small leads 38.6 to 27.9.
- The biggest single-benchmark swing is ARC-AGI-1: 84% for Inkling-Small and 30.7% for o1.
- Inkling-Small is cheaper at $0.45 / $1.20 per million input/output tokens, against $15 / $60 for o1.
- Inkling-Small accepts more context: 524K tokens versus 200K.
- Inkling-Small has downloadable open weights; the other is API-only.
Side by side
| Inkling-Small | o1 | |
|---|---|---|
| Provider | Thinking Machines Lab | OpenAI |
| Noometry Index | 46.5 | 40.9 |
| Released | 2026-07-15 | 2024-09-12 |
| Weights | Open | Proprietary |
| Context window | 524K | 200K |
| Max output | 1.05M | 100K |
| Input $ / M tokens | $0.45 | $15 |
| Output $ / M tokens | $1.20 | $60 |
| Results tracked | 33 | 52 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o1 leads
Inkling-Small: 43.6 (#85), o1: 46.1 (#70)
| Benchmark | Inkling-Small | o1 |
|---|---|---|
| LMArena Coding | 1451 | 1367 |
| Aider Polyglot | — | 61.7% |
| LMArena WebDev | 1409 | — |
| SciCode | 48.7% | — |
| WeirdML | — | 47.6% |
| LiveBench Coding | — | 69.7% |
| CadEval | — | 56% |
| HumanEval+ | — | 89% |
| MBPP+ | — | 80.2% |
Agentic & Tool Use Not comparable
Inkling-Small: —, o1: 24.6 (#117)
| Benchmark | Inkling-Small | o1 |
|---|---|---|
| Cybench | — | 10% |
| METR Time Horizons | — | 51.1% |
Reasoning Inkling-Small leads
Inkling-Small: 38.6 (#63), o1: 27.9 (#111)
| Benchmark | Inkling-Small | o1 |
|---|---|---|
| ARC-AGI-1 | 84% | 30.7% |
| Chess Puzzles | 18% | 15% |
| LMArena Hard Prompts | 1423 | 1371 |
| Epoch Capabilities Index | 150.15 | 141.91 |
| ARC-AGI-2 | 40.1% | — |
| SimpleBench | — | 41.7% |
| CritPt | 8.3% | — |
| EnigmaEval | — | 5.7% |
| LiveBench Reasoning | — | 91.6% |
| Mystery Game Puzzles | 6% | — |
| DTBench | — | 74.7% |
| LiveBench Data Analysis | — | 65.5% |
| LMCA | — | 22.3% |
| LiveBench | — | 75.7% |
Math Inkling-Small leads
Inkling-Small: 45.1 (#77), o1: 36.1 (#175)
| Benchmark | Inkling-Small | o1 |
|---|---|---|
| FrontierMath (Tiers 1-3) | 46.3% | 14.7% |
| OTIS Mock AIME 2024-2025 | 90% | 73.3% |
| LMArena Math | 1459 | 1388 |
| FrontierMath Tier 4 | 17.1% | — |
| ProofBench | 6% | — |
| LiveBench Math | — | 80.3% |
| MATH Level 5 | — | 94.7% |
| FrontierMath (Feb 2025 set) | — | 9.3% |
Knowledge Inkling-Small leads
Inkling-Small: 48.2 (#77), o1: 41.5 (#110)
| Benchmark | Inkling-Small | o1 |
|---|---|---|
| GPQA Diamond | 88.5% | 76.8% |
| SimpleQA Verified | 19.1% | 41.1% |
| LMArena Expert | 1442 | 1361 |
| Humanity's Last Exam | — | 8% |
| Confabulations | — | 11.7% |
Multimodal Inkling-Small leads
Inkling-Small: 39.1 (#62), o1: 34.2 (#93)
| Benchmark | Inkling-Small | o1 |
|---|---|---|
| LMArena Vision | 1235 | 1168 |
| GeoBench | — | 80% |
| VPCT | — | 37% |
| SpatialViz-Bench | — | 41.4% |
Multilingual Inkling-Small leads
Inkling-Small: 51.7 (#104), o1: 48.6 (#142)
| Benchmark | Inkling-Small | o1 |
|---|---|---|
| LMArena Non-English | 1402 | 1358 |
| LMArena Chinese | 1465 | 1394 |
| LMArena French | 1436 | 1344 |
| LMArena German | 1405 | 1337 |
| LMArena Japanese | 1405 | 1346 |
| LMArena Korean | 1363 | 1396 |
| LMArena Russian | 1391 | 1356 |
| LMArena Spanish | 1428 | 1345 |
Instruction Following Too close to call
Inkling-Small: 73.8 (#114), o1: 74.8 (#86)
| Benchmark | Inkling-Small | o1 |
|---|---|---|
| LMArena Instruction Following | 1399 | 1367 |
| LiveBench Instruction Following | — | 81.5% |
Long Context o1 leads
Inkling-Small: 42.7 (#118), o1: 50.3 (#9)
| Benchmark | Inkling-Small | o1 |
|---|---|---|
| LMArena Longer Query | 1401 | 1378 |
| Fiction.LiveBench | — | 83.3% |
Writing & Preference Inkling-Small leads
Inkling-Small: 59.6 (#107), o1: 55.6 (#144)
| Benchmark | Inkling-Small | o1 |
|---|---|---|
| LMArena Text | 1414 | 1366 |
| LMArena Creative Writing | 1331 | 1348 |
| LMArena Multi-Turn | 1418 | 1369 |
| Short-Story Creative Writing | — | 70.2% |
| EQ-Bench Creative Writing | 1491 | — |
| LiveBench Language | — | 65.4% |
Frequently asked questions
Is Inkling-Small better than o1?
Inkling-Small is the stronger model overall, scoring 46.5 to 40.9 on the Noometry Index.
Which is cheaper, Inkling-Small or o1?
Inkling-Small is cheaper. It lists at $0.45 per million input tokens and $1.20 per million output tokens; o1 lists at $15 and $60.
Is Inkling-Small or o1 better for coding?
o1 scores higher on coding benchmarks: 46.1 versus 43.6 in the Noometry coding category.
Which has the bigger context window?
Inkling-Small does, with 524K tokens against 200K.
How many benchmarks do Inkling-Small and o1 share?
25 benchmarks have published results for both models. Inkling-Small has 33 scored results on Noometry and o1 has 52.