Model comparison
Inkling-Small vs o3
o3 is the stronger model overall, scoring 47.5 to 46.5 on the Noometry Index. Inkling-Small costs 5.5× less per token, which makes it the better buy when o3's lead doesn't matter for your workload.
Last verified . 29 shared benchmarks.
Summary
- They share 29 benchmarks with published results for both. Inkling-Small scores higher in 3 categories and o3 in 6 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in long context, where o3 leads 53.3 to 42.7.
- The biggest single-benchmark swing is ARC-AGI-2: 40.1% for Inkling-Small and 6.5% for o3.
- Inkling-Small is cheaper at $0.45 / $1.20 per million input/output tokens, against $2 / $8 for o3.
- 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 | |
|---|---|---|
| Provider | Thinking Machines Lab | OpenAI |
| Noometry Index | 46.5 | 47.5 |
| Released | 2026-07-15 | 2025-04-16 |
| Weights | Open | Proprietary |
| Context window | 524K | 200K |
| Max output | 1.05M | 100K |
| Input $ / M tokens | $0.45 | $2 |
| Output $ / M tokens | $1.20 | $8 |
| Results tracked | 33 | 63 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o3 leads
Inkling-Small: 43.6 (#85), o3: 46.8 (#64)
| Benchmark | Inkling-Small | o3 |
|---|---|---|
| LMArena Coding | 1451 | 1408 |
| SWE-bench Verified | — | 62.3% |
| SWE-bench Verified (bash only) | — | 58.4% |
| Aider Polyglot | — | 81.3% |
| LMArena WebDev | 1409 | — |
| SciCode | 48.7% | — |
| GSO | — | 8.8% |
| WeirdML | — | 52.4% |
| CadEval | — | 74% |
| ALE-Bench | — | 933.55 |
Agentic & Tool Use Not comparable
Inkling-Small: —, o3: 34.5 (#44)
| Benchmark | Inkling-Small | o3 |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 63% |
| GDPval | — | 30.8% |
| DeepResearch Bench | — | 45.2% |
| OSWorld | — | 23% |
| LMArena Search | — | 1144 |
| METR Time Horizons | — | 65.4% |
Reasoning Inkling-Small leads
Inkling-Small: 38.6 (#63), o3: 32.0 (#78)
| Benchmark | Inkling-Small | o3 |
|---|---|---|
| ARC-AGI-2 | 40.1% | 6.5% |
| ARC-AGI-1 | 84% | 60.8% |
| CritPt | 8.3% | 1.4% |
| Chess Puzzles | 18% | 38% |
| LMArena Hard Prompts | 1423 | 1402 |
| Mystery Game Puzzles | 6% | 29% |
| Epoch Capabilities Index | 150.15 | 146.86 |
| SimpleBench | — | 53.1% |
| Kagi LLM Benchmark | — | 67.6% |
| EnigmaEval | — | 13.1% |
| DTBench | — | 84.8% |
| LMCA | — | 39.7% |
| ForecastBench | — | 62.5 |
Math o3 leads
Inkling-Small: 45.1 (#77), o3: 50.2 (#58)
| Benchmark | Inkling-Small | o3 |
|---|---|---|
| FrontierMath (Tiers 1-3) | 46.3% | 33.3% |
| OTIS Mock AIME 2024-2025 | 90% | 84.4% |
| LMArena Math | 1459 | 1426 |
| FrontierMath Tier 4 | 17.1% | — |
| ProofBench | 6% | — |
| Omni-MATH | — | 71.4% |
| MATH Level 5 | — | 97.8% |
| FrontierMath (Feb 2025 set) | — | 18.7% |
| FrontierMath Tier 4 (v1) | — | 2.1% |
Knowledge o3 leads
Inkling-Small: 48.2 (#77), o3: 54.6 (#52)
| Benchmark | Inkling-Small | o3 |
|---|---|---|
| GPQA Diamond | 88.5% | 81.8% |
| SimpleQA Verified | 19.1% | 49.4% |
| LMArena Expert | 1442 | 1402 |
| Humanity's Last Exam | — | 20.3% |
| MMLU-Pro | — | 85.9% |
| Confabulations | — | 14.4% |
| GPQA (HELM) | — | 75.3% |
Multimodal o3 leads
Inkling-Small: 39.1 (#62), o3: 41.4 (#36)
| Benchmark | Inkling-Small | o3 |
|---|---|---|
| LMArena Vision | 1235 | 1214 |
| GeoBench | — | 74% |
| VPCT | — | 52% |
Multilingual Too close to call
Inkling-Small: 51.7 (#104), o3: 51.7 (#105)
| Benchmark | Inkling-Small | o3 |
|---|---|---|
| LMArena Non-English | 1402 | 1401 |
| LMArena Chinese | 1465 | 1437 |
| LMArena French | 1436 | 1430 |
| LMArena German | 1405 | 1420 |
| LMArena Japanese | 1405 | 1403 |
| LMArena Korean | 1363 | 1370 |
| LMArena Russian | 1391 | 1406 |
| LMArena Spanish | 1428 | 1395 |
Instruction Following Inkling-Small leads
Inkling-Small: 73.8 (#114), o3: 72.8 (#127)
| Benchmark | Inkling-Small | o3 |
|---|---|---|
| LMArena Instruction Following | 1399 | 1368 |
| IFEval | — | 86.9% |
Long Context o3 leads
Inkling-Small: 42.7 (#118), o3: 53.3 (#6)
| Benchmark | Inkling-Small | o3 |
|---|---|---|
| LMArena Longer Query | 1401 | 1372 |
| Fiction.LiveBench | — | 88.9% |
| CL-bench | — | 17.8% |
Writing & Preference o3 leads
Inkling-Small: 59.6 (#107), o3: 63.5 (#64)
| Benchmark | Inkling-Small | o3 |
|---|---|---|
| LMArena Text | 1414 | 1410 |
| LMArena Creative Writing | 1331 | 1359 |
| EQ-Bench Creative Writing | 1491 | 1676 |
| LMArena Multi-Turn | 1418 | 1405 |
| Short-Story Creative Writing | — | 83.9% |
| WildBench | — | 86.1% |
Frequently asked questions
Is Inkling-Small better than o3?
o3 is the stronger model overall, scoring 47.5 to 46.5 on the Noometry Index. Inkling-Small costs 5.5× less per token, which makes it the better buy when o3's lead doesn't matter for your workload.
Which is cheaper, Inkling-Small or o3?
Inkling-Small is cheaper. It lists at $0.45 per million input tokens and $1.20 per million output tokens; o3 lists at $2 and $8.
Is Inkling-Small or o3 better for coding?
o3 scores higher on coding benchmarks: 46.8 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 o3 share?
29 benchmarks have published results for both models. Inkling-Small has 33 scored results on Noometry and o3 has 63.