Model comparison
Inkling vs o3-mini
Inkling is the stronger model overall, scoring 44.1 to 36.7 on the Noometry Index.
Last verified . 32 shared benchmarks.
Summary
- They share 32 benchmarks with published results for both. Inkling scores higher in 8 categories and o3-mini in 1 category; 7 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Inkling leads 40.6 to 16.3.
- The biggest single-benchmark swing is ARC-AGI-1: 79.5% for Inkling and 34.5% for o3-mini.
- o3-mini is cheaper at $1.10 / $4.40 per million input/output tokens, against $1.87 / $4.68 for Inkling.
- o3-mini accepts more context: 200K tokens versus 66K.
- Inkling has downloadable open weights; the other is API-only.
Side by side
| Inkling | o3-mini | |
|---|---|---|
| Provider | Thinking Machines Lab | OpenAI |
| Noometry Index | 44.1 | 36.7 |
| Released | 2026-07-15 | 2024-12-20 |
| Weights | Open | Proprietary |
| Context window | 66K | 200K |
| Max output | 66K | 100K |
| Input $ / M tokens | $1.87 | $1.10 |
| Output $ / M tokens | $4.68 | $4.40 |
| Results tracked | 41 | 51 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o3-mini leads
Inkling: 34.1 (#229), o3-mini: 41.4 (#116)
| Benchmark | Inkling | o3-mini |
|---|---|---|
| SciCode | 47% | 39.8% |
| WeirdML | 32.3% | 43.7% |
| LMArena Coding | 1463 | 1378 |
| FrontierCode | 14% | — |
| Aider Polyglot | — | 60.4% |
| LMArena WebDev | 1412 | — |
| FrontierSWE | 4.1% | — |
| GSO | — | 1.3% |
| LiveBench Coding | — | 82.7% |
| CadEval | — | 54% |
| ALE-Bench | 946 | — |
Agentic & Tool Use Too close to call
Inkling: 29.5 (#76), o3-mini: 29.3 (#79)
| Benchmark | Inkling | o3-mini |
|---|---|---|
| APEX-Agents | 33.8% | — |
| τ²-bench Banking | 25% | — |
| Cybench | — | 22.5% |
Reasoning Inkling leads
Inkling: 40.6 (#48), o3-mini: 16.3 (#295)
| Benchmark | Inkling | o3-mini |
|---|---|---|
| ARC-AGI-2 | 36.5% | 3% |
| SimpleBench | 50% | 22.8% |
| ARC-AGI-1 | 79.5% | 34.5% |
| CritPt | 5.4% | 0.3% |
| Chess Puzzles | 21% | 17% |
| LMArena Hard Prompts | 1452 | 1366 |
| DTBench | 87.5% | 68.8% |
| LMCA | 37.6% | 19% |
| Epoch Capabilities Index | 148.6 | 140.35 |
| LiveBench Reasoning | — | 89.6% |
| Mystery Game Puzzles | — | 7% |
| LiveBench Data Analysis | — | 70.6% |
| ForecastBench | — | 59.6 |
| LiveBench | — | 75.9% |
Math Inkling leads
Inkling: 31.2 (#198), o3-mini: 27.6 (#236)
| Benchmark | Inkling | o3-mini |
|---|---|---|
| FrontierMath (Tiers 1-3) | 33.3% | 18.6% |
| FrontierMath Tier 4 | 4.9% | 0% |
| OTIS Mock AIME 2024-2025 | 88.9% | 76.9% |
| LMArena Math | 1482 | 1396 |
| ProofBench | 0% | — |
| LiveBench Math | — | 77.3% |
| MATH Level 5 | — | 96.5% |
| FrontierMath (Feb 2025 set) | — | 12.4% |
| FrontierMath Tier 4 (v1) | — | 4.2% |
Knowledge Inkling leads
Inkling: 55.2 (#44), o3-mini: 38.3 (#135)
| Benchmark | Inkling | o3-mini |
|---|---|---|
| GPQA Diamond | 88.3% | 77% |
| SimpleQA Verified | 40.3% | 15.3% |
| LMArena Expert | 1468 | 1364 |
| Confabulations | — | 17.9% |
Multilingual Inkling leads
Inkling: 54.2 (#49), o3-mini: 45.9 (#159)
| Benchmark | Inkling | o3-mini |
|---|---|---|
| LMArena Non-English | 1434 | 1319 |
| LMArena Chinese | 1495 | 1379 |
| LMArena French | 1453 | 1333 |
| LMArena German | 1456 | 1303 |
| LMArena Japanese | 1428 | 1286 |
| LMArena Korean | 1401 | 1314 |
| LMArena Russian | 1430 | 1304 |
| LMArena Spanish | 1442 | 1321 |
Instruction Following Too close to call
Inkling: 75.3 (#65), o3-mini: 75.3 (#67)
| Benchmark | Inkling | o3-mini |
|---|---|---|
| LMArena Instruction Following | 1427 | 1338 |
| LiveBench Instruction Following | — | 84.4% |
Long Context Inkling leads
Inkling: 43.9 (#79), o3-mini: 33.8 (#251)
| Benchmark | Inkling | o3-mini |
|---|---|---|
| LMArena Longer Query | 1436 | 1343 |
| Fiction.LiveBench | — | 50% |
Writing & Preference Inkling leads
Inkling: 65.5 (#48), o3-mini: 50.4 (#177)
| Benchmark | Inkling | o3-mini |
|---|---|---|
| LMArena Text | 1443 | 1337 |
| LMArena Creative Writing | 1390 | 1286 |
| LMArena Multi-Turn | 1436 | 1320 |
| Short-Story Creative Writing | — | 61.7% |
| EQ-Bench Creative Writing | 1611 | — |
| EQ-Bench 4 | 1226 | — |
| LiveBench Language | — | 50.7% |
Frequently asked questions
Is Inkling better than o3-mini?
Inkling is the stronger model overall, scoring 44.1 to 36.7 on the Noometry Index.
Which is cheaper, Inkling or o3-mini?
o3-mini is cheaper. It lists at $1.10 per million input tokens and $4.40 per million output tokens; Inkling lists at $1.87 and $4.68.
Is Inkling or o3-mini better for coding?
o3-mini scores higher on coding benchmarks: 41.4 versus 34.1 in the Noometry coding category.
Which has the bigger context window?
o3-mini does, with 200K tokens against 66K.
How many benchmarks do Inkling and o3-mini share?
32 benchmarks have published results for both models. Inkling has 41 scored results on Noometry and o3-mini has 51.