Model comparison
Inkling-Small vs o3-pro
Inkling-Small is the stronger model overall, scoring 46.5 to 42.7 on the Noometry Index.
Last verified . 3 shared benchmarks.
Summary
- They share 3 benchmarks with published results for both. Inkling-Small scores higher in 3 categories and o3-pro in 2 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in long context, where o3-pro leads 72.1 to 42.7.
- The biggest single-benchmark swing is ARC-AGI-2: 40.1% for Inkling-Small and 4.9% for o3-pro.
- Inkling-Small is cheaper at $0.45 / $1.20 per million input/output tokens, against $20 / $80 for o3-pro.
- 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-pro | |
|---|---|---|
| Provider | Thinking Machines Lab | OpenAI |
| Noometry Index | 46.5 | 42.7 |
| Released | 2026-07-15 | 2025-06-10 |
| Weights | Open | Proprietary |
| Context window | 524K | 200K |
| Max output | 1.05M | 100K |
| Input $ / M tokens | $0.45 | $20 |
| Output $ / M tokens | $1.20 | $80 |
| Results tracked | 33 | 12 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o3-pro leads
Inkling-Small: 43.3 (#80), o3-pro: 55.1 (#22)
| Benchmark | Inkling-Small | o3-pro |
|---|---|---|
| Aider Polyglot | — | 84.9% |
| LMArena WebDev | 1408 | — |
| SciCode | 48.7% | — |
| WeirdML | — | 58.2% |
| LMArena Coding | 1451 | — |
Reasoning Inkling-Small leads
Inkling-Small: 39.0 (#53), o3-pro: 24.1 (#152)
| Benchmark | Inkling-Small | o3-pro |
|---|---|---|
| ARC-AGI-2 | 40.1% | 4.9% |
| ARC-AGI-1 | 84% | 59.3% |
| Epoch Capabilities Index | 150.13 | 147.43 |
| Kagi LLM Benchmark | — | 72.1% |
| CritPt | 8.3% | — |
| Chess Puzzles | 18% | — |
| LMArena Hard Prompts | 1424 | — |
| Mystery Game Puzzles | 6% | — |
| DTBench | — | 86.9% |
| LMCA | — | 38.5% |
Math Not comparable
Inkling-Small: 44.9 (#65), o3-pro: —
| Benchmark | Inkling-Small | o3-pro |
|---|---|---|
| FrontierMath (Tiers 1-3) | 46.3% | — |
| FrontierMath Tier 4 | 17.1% | — |
| OTIS Mock AIME 2024-2025 | 90% | — |
| ProofBench | 6% | — |
| LMArena Math | 1453 | — |
Knowledge Inkling-Small leads
Inkling-Small: 48.3 (#71), o3-pro: 29.0 (#234)
| Benchmark | Inkling-Small | o3-pro |
|---|---|---|
| GPQA Diamond | 88.5% | — |
| SimpleQA Verified | 19.1% | — |
| Confabulations | — | 14.2% |
| Vectara Hallucination Rate | — | 23.3% |
| LMArena Expert | 1442 | — |
Multimodal Not comparable
Inkling-Small: 38.4 (#59), o3-pro: —
| Benchmark | Inkling-Small | o3-pro |
|---|---|---|
| LMArena Vision | 1235 | — |
Multilingual Not comparable
Inkling-Small: 51.7 (#102), o3-pro: —
| Benchmark | Inkling-Small | o3-pro |
|---|---|---|
| LMArena Non-English | 1400 | — |
| LMArena Chinese | 1458 | — |
| LMArena French | 1438 | — |
| LMArena German | 1412 | — |
| LMArena Japanese | 1399 | — |
| LMArena Korean | 1355 | — |
| LMArena Russian | 1392 | — |
| LMArena Spanish | 1426 | — |
Instruction Following Not comparable
Inkling-Small: 73.9 (#112), o3-pro: —
| Benchmark | Inkling-Small | o3-pro |
|---|---|---|
| LMArena Instruction Following | 1397 | — |
Long Context o3-pro leads
Inkling-Small: 42.7 (#113), o3-pro: 72.1 (#1)
| Benchmark | Inkling-Small | o3-pro |
|---|---|---|
| Fiction.LiveBench | — | 97.2% |
| LMArena Longer Query | 1401 | — |
Writing & Preference Inkling-Small leads
Inkling-Small: 59.8 (#102), o3-pro: 57.1 (#128)
| Benchmark | Inkling-Small | o3-pro |
|---|---|---|
| LMArena Text | 1413 | — |
| LMArena Creative Writing | 1330 | — |
| Short-Story Creative Writing | — | 84.4% |
| EQ-Bench Creative Writing | 1491 | — |
| LMArena Multi-Turn | 1420 | — |
Frequently asked questions
Is Inkling-Small better than o3-pro?
Inkling-Small is the stronger model overall, scoring 46.5 to 42.7 on the Noometry Index.
Which is cheaper, Inkling-Small or o3-pro?
Inkling-Small is cheaper. It lists at $0.45 per million input tokens and $1.20 per million output tokens; o3-pro lists at $20 and $80.
Is Inkling-Small or o3-pro better for coding?
o3-pro scores higher on coding benchmarks: 55.1 versus 43.3 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-pro share?
3 benchmarks have published results for both models. Inkling-Small has 33 scored results on Noometry and o3-pro has 12.