Model comparison
Inkling vs o3-pro
Inkling is the stronger model overall, scoring 44.1 to 42.9 on the Noometry Index.
Last verified . 6 shared benchmarks.
Summary
- They share 6 benchmarks with published results for both. Inkling 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 72.2 to 43.8.
- The biggest single-benchmark swing is ARC-AGI-2: 36.5% for Inkling and 4.9% for o3-pro.
- Inkling is cheaper at $1.87 / $4.68 per million input/output tokens, against $20 / $80 for o3-pro.
- o3-pro accepts more context: 200K tokens versus 66K.
- Inkling has downloadable open weights; the other is API-only.
Side by side
| Inkling | o3-pro | |
|---|---|---|
| Provider | Thinking Machines Lab | OpenAI |
| Noometry Index | 44.1 | 42.9 |
| Released | 2026-07-15 | 2025-06-10 |
| Weights | Open | Proprietary |
| Context window | 66K | 200K |
| Max output | 66K | 100K |
| Input $ / M tokens | $1.87 | $20 |
| Output $ / M tokens | $4.68 | $80 |
| Results tracked | 41 | 12 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o3-pro leads
Inkling: 34.5 (#234), o3-pro: 55.5 (#24)
| Benchmark | Inkling | o3-pro |
|---|---|---|
| WeirdML | 32.3% | 58.2% |
| FrontierCode | 14% | — |
| Aider Polyglot | — | 84.9% |
| LMArena WebDev | 1413 | — |
| FrontierSWE | 4.1% | — |
| SciCode | 47% | — |
| LMArena Coding | 1464 | — |
| ALE-Bench | 946 | — |
Agentic & Tool Use Not comparable
Inkling: 29.6 (#85), o3-pro: —
| Benchmark | Inkling | o3-pro |
|---|---|---|
| APEX-Agents | 33.8% | — |
| τ²-bench Banking | 25% | — |
Reasoning Inkling leads
Inkling: 40.4 (#56), o3-pro: 23.8 (#171)
| Benchmark | Inkling | o3-pro |
|---|---|---|
| ARC-AGI-2 | 36.5% | 4.9% |
| ARC-AGI-1 | 79.5% | 59.3% |
| DTBench | 87.5% | 86.9% |
| LMCA | 37.6% | 38.5% |
| Epoch Capabilities Index | 148.54 | 147.42 |
| SimpleBench | 50% | — |
| Kagi LLM Benchmark | — | 72.1% |
| CritPt | 5.4% | — |
| Chess Puzzles | 21% | — |
| LMArena Hard Prompts | 1451 | — |
Math Not comparable
Inkling: 31.3 (#225), o3-pro: —
| Benchmark | Inkling | o3-pro |
|---|---|---|
| FrontierMath (Tiers 1-3) | 33.3% | — |
| FrontierMath Tier 4 | 4.9% | — |
| OTIS Mock AIME 2024-2025 | 88.9% | — |
| ProofBench | 0% | — |
| LMArena Math | 1479 | — |
Knowledge Inkling leads
Inkling: 55.1 (#49), o3-pro: 29.5 (#238)
| Benchmark | Inkling | o3-pro |
|---|---|---|
| GPQA Diamond | 88.3% | — |
| SimpleQA Verified | 40.3% | — |
| Confabulations | — | 14.2% |
| Vectara Hallucination Rate | — | 23.3% |
| LMArena Expert | 1465 | — |
Multilingual Not comparable
Inkling: 54.0 (#52), o3-pro: —
| Benchmark | Inkling | o3-pro |
|---|---|---|
| LMArena Non-English | 1434 | — |
| LMArena Chinese | 1490 | — |
| LMArena French | 1458 | — |
| LMArena German | 1446 | — |
| LMArena Japanese | 1429 | — |
| LMArena Korean | 1404 | — |
| LMArena Russian | 1429 | — |
| LMArena Spanish | 1448 | — |
Instruction Following Not comparable
Inkling: 75.1 (#71), o3-pro: —
| Benchmark | Inkling | o3-pro |
|---|---|---|
| LMArena Instruction Following | 1426 | — |
Long Context o3-pro leads
Inkling: 43.8 (#86), o3-pro: 72.2 (#1)
| Benchmark | Inkling | o3-pro |
|---|---|---|
| Fiction.LiveBench | — | 97.2% |
| LMArena Longer Query | 1434 | — |
Writing & Preference Inkling leads
Inkling: 65.2 (#51), o3-pro: 57.1 (#133)
| Benchmark | Inkling | o3-pro |
|---|---|---|
| LMArena Text | 1441 | — |
| LMArena Creative Writing | 1387 | — |
| Short-Story Creative Writing | — | 84.4% |
| EQ-Bench Creative Writing | 1611 | — |
| EQ-Bench 4 | 1226 | — |
| LMArena Multi-Turn | 1436 | — |
Frequently asked questions
Is Inkling better than o3-pro?
Inkling is the stronger model overall, scoring 44.1 to 42.9 on the Noometry Index.
Which is cheaper, Inkling or o3-pro?
Inkling is cheaper. It lists at $1.87 per million input tokens and $4.68 per million output tokens; o3-pro lists at $20 and $80.
Is Inkling or o3-pro better for coding?
o3-pro scores higher on coding benchmarks: 55.5 versus 34.5 in the Noometry coding category.
Which has the bigger context window?
o3-pro does, with 200K tokens against 66K.
How many benchmarks do Inkling and o3-pro share?
6 benchmarks have published results for both models. Inkling has 41 scored results on Noometry and o3-pro has 12.