Model comparison
Inkling-Small vs o3-mini
Inkling-Small is the stronger model overall, scoring 46.5 to 36.7 on the Noometry Index.
Last verified . 29 shared benchmarks.
Summary
- They share 29 benchmarks with published results for both. Inkling-Small scores higher in 7 categories and o3-mini in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Inkling-Small leads 38.6 to 16.3.
- The biggest single-benchmark swing is ARC-AGI-1: 84% for Inkling-Small and 34.5% for o3-mini.
- Inkling-Small is cheaper at $0.45 / $1.20 per million input/output tokens, against $1.10 / $4.40 for o3-mini.
- 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 | o3-mini | |
|---|---|---|
| Provider | Thinking Machines Lab | OpenAI |
| Noometry Index | 46.5 | 36.7 |
| Released | 2026-07-15 | 2024-12-20 |
| Weights | Open | Proprietary |
| Context window | 524K | 200K |
| Max output | 1.05M | 100K |
| Input $ / M tokens | $0.45 | $1.10 |
| Output $ / M tokens | $1.20 | $4.40 |
| Results tracked | 33 | 51 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Inkling-Small leads
Inkling-Small: 43.6 (#85), o3-mini: 40.8 (#132)
| Benchmark | Inkling-Small | o3-mini |
|---|---|---|
| SciCode | 48.7% | 39.8% |
| LMArena Coding | 1451 | 1378 |
| Aider Polyglot | — | 60.4% |
| LMArena WebDev | 1409 | — |
| GSO | — | 1.3% |
| WeirdML | — | 43.7% |
| LiveBench Coding | — | 82.7% |
| CadEval | — | 54% |
Agentic & Tool Use Not comparable
Inkling-Small: —, o3-mini: 29.6 (#84)
| Benchmark | Inkling-Small | o3-mini |
|---|---|---|
| Cybench | — | 22.5% |
Reasoning Inkling-Small leads
Inkling-Small: 38.6 (#63), o3-mini: 16.3 (#305)
| Benchmark | Inkling-Small | o3-mini |
|---|---|---|
| ARC-AGI-2 | 40.1% | 3% |
| ARC-AGI-1 | 84% | 34.5% |
| CritPt | 8.3% | 0.3% |
| Chess Puzzles | 18% | 17% |
| LMArena Hard Prompts | 1423 | 1366 |
| Mystery Game Puzzles | 6% | 7% |
| Epoch Capabilities Index | 150.15 | 140.34 |
| SimpleBench | — | 22.8% |
| LiveBench Reasoning | — | 89.6% |
| DTBench | — | 68.8% |
| LiveBench Data Analysis | — | 70.6% |
| LMCA | — | 19% |
| ForecastBench | — | 59.6 |
| LiveBench | — | 75.9% |
Math Inkling-Small leads
Inkling-Small: 45.1 (#77), o3-mini: 28.1 (#244)
| Benchmark | Inkling-Small | o3-mini |
|---|---|---|
| FrontierMath (Tiers 1-3) | 46.3% | 18.6% |
| FrontierMath Tier 4 | 17.1% | 0% |
| OTIS Mock AIME 2024-2025 | 90% | 76.9% |
| LMArena Math | 1459 | 1396 |
| ProofBench | 6% | — |
| LiveBench Math | — | 77.3% |
| MATH Level 5 | — | 96.5% |
| FrontierMath (Feb 2025 set) | — | 12.4% |
| FrontierMath Tier 4 (v1) | — | 4.2% |
Knowledge Inkling-Small leads
Inkling-Small: 48.2 (#77), o3-mini: 38.3 (#146)
| Benchmark | Inkling-Small | o3-mini |
|---|---|---|
| GPQA Diamond | 88.5% | 77% |
| SimpleQA Verified | 19.1% | 15.3% |
| LMArena Expert | 1442 | 1364 |
| Confabulations | — | 17.9% |
Multimodal Not comparable
Inkling-Small: 39.1 (#62), o3-mini: —
| Benchmark | Inkling-Small | o3-mini |
|---|---|---|
| LMArena Vision | 1235 | — |
Multilingual Inkling-Small leads
Inkling-Small: 51.7 (#104), o3-mini: 45.7 (#164)
| Benchmark | Inkling-Small | o3-mini |
|---|---|---|
| LMArena Non-English | 1402 | 1319 |
| LMArena Chinese | 1465 | 1379 |
| LMArena French | 1436 | 1334 |
| LMArena German | 1405 | 1303 |
| LMArena Japanese | 1405 | 1286 |
| LMArena Korean | 1363 | 1314 |
| LMArena Russian | 1391 | 1304 |
| LMArena Spanish | 1428 | 1321 |
Instruction Following o3-mini leads
Inkling-Small: 73.8 (#114), o3-mini: 75.1 (#72)
| Benchmark | Inkling-Small | o3-mini |
|---|---|---|
| LMArena Instruction Following | 1399 | 1337 |
| LiveBench Instruction Following | — | 84.4% |
Long Context Inkling-Small leads
Inkling-Small: 42.7 (#118), o3-mini: 33.8 (#256)
| Benchmark | Inkling-Small | o3-mini |
|---|---|---|
| LMArena Longer Query | 1401 | 1343 |
| Fiction.LiveBench | — | 50% |
Writing & Preference Inkling-Small leads
Inkling-Small: 59.6 (#107), o3-mini: 50.3 (#182)
| Benchmark | Inkling-Small | o3-mini |
|---|---|---|
| LMArena Text | 1414 | 1337 |
| LMArena Creative Writing | 1331 | 1286 |
| LMArena Multi-Turn | 1418 | 1320 |
| Short-Story Creative Writing | — | 61.7% |
| EQ-Bench Creative Writing | 1491 | — |
| LiveBench Language | — | 50.7% |
Frequently asked questions
Is Inkling-Small better than o3-mini?
Inkling-Small is the stronger model overall, scoring 46.5 to 36.7 on the Noometry Index.
Which is cheaper, Inkling-Small or o3-mini?
Inkling-Small is cheaper. It lists at $0.45 per million input tokens and $1.20 per million output tokens; o3-mini lists at $1.10 and $4.40.
Is Inkling-Small or o3-mini better for coding?
Inkling-Small scores higher on coding benchmarks: 43.6 versus 40.8 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 o3-mini share?
29 benchmarks have published results for both models. Inkling-Small has 33 scored results on Noometry and o3-mini has 51.