Model comparison
Inkling vs o1-mini
Inkling is the stronger model overall, scoring 44.1 to 33.7 on the Noometry Index.
Last verified . 24 shared benchmarks.
Summary
- They share 24 benchmarks with published results for both. Inkling scores higher in 7 categories and o1-mini in 2 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Inkling leads 40.6 to 8.9.
- The biggest single-benchmark swing is ARC-AGI-1: 79.5% for Inkling and 14% for o1-mini.
- Inkling has downloadable open weights; the other is API-only.
Side by side
| Inkling | o1-mini | |
|---|---|---|
| Provider | Thinking Machines Lab | OpenAI |
| Noometry Index | 44.1 | 33.7 |
| Released | 2026-07-15 | 2024-09-12 |
| Weights | Open | Proprietary |
| Context window | 66K | — |
| Max output | 66K | — |
| Input $ / M tokens | $1.87 | — |
| Output $ / M tokens | $4.68 | — |
| Results tracked | 41 | 39 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Inkling: 34.1 (#229), o1-mini: 35.1 (#218)
| Benchmark | Inkling | o1-mini |
|---|---|---|
| WeirdML | 32.3% | 36.3% |
| LMArena Coding | 1463 | 1362 |
| FrontierCode | 14% | — |
| Aider Polyglot | — | 32.9% |
| LMArena WebDev | 1412 | — |
| FrontierSWE | 4.1% | — |
| SciCode | 47% | — |
| LiveBench Coding | — | 48% |
| ALE-Bench | 946 | — |
| HumanEval+ | — | 89% |
| MBPP+ | — | 78.8% |
Agentic & Tool Use Inkling leads
Inkling: 29.5 (#76), o1-mini: 24.3 (#112)
| Benchmark | Inkling | o1-mini |
|---|---|---|
| APEX-Agents | 33.8% | — |
| τ²-bench Banking | 25% | — |
| Cybench | — | 10% |
Reasoning Inkling leads
Inkling: 40.6 (#48), o1-mini: 8.9 (#340)
| Benchmark | Inkling | o1-mini |
|---|---|---|
| ARC-AGI-2 | 36.5% | 0.8% |
| SimpleBench | 50% | 18.1% |
| ARC-AGI-1 | 79.5% | 14% |
| LMArena Hard Prompts | 1452 | 1333 |
| Epoch Capabilities Index | 148.6 | 135.82 |
| CritPt | 5.4% | — |
| Chess Puzzles | 21% | — |
| LiveBench Reasoning | — | 72.3% |
| DTBench | 87.5% | — |
| LiveBench Data Analysis | — | 57.9% |
| LMCA | 37.6% | — |
| LiveBench | — | 57.8% |
Math o1-mini leads
Inkling: 31.2 (#198), o1-mini: 33.7 (#168)
| Benchmark | Inkling | o1-mini |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 88.9% | 46.9% |
| LMArena Math | 1482 | 1358 |
| FrontierMath (Tiers 1-3) | 33.3% | — |
| FrontierMath Tier 4 | 4.9% | — |
| ProofBench | 0% | — |
| LiveBench Math | — | 62% |
| MATH Level 5 | — | 89.2% |
| FrontierMath (Feb 2025 set) | — | 1.7% |
Knowledge Inkling leads
Inkling: 55.2 (#44), o1-mini: 34.8 (#180)
| Benchmark | Inkling | o1-mini |
|---|---|---|
| GPQA Diamond | 88.3% | 62.4% |
| LMArena Expert | 1468 | 1316 |
| SimpleQA Verified | 40.3% | — |
| Confabulations | — | 18.6% |
Multilingual Inkling leads
Inkling: 54.2 (#49), o1-mini: 43.8 (#177)
| Benchmark | Inkling | o1-mini |
|---|---|---|
| LMArena Non-English | 1434 | 1289 |
| LMArena Chinese | 1495 | 1314 |
| LMArena French | 1453 | 1292 |
| LMArena German | 1456 | 1278 |
| LMArena Japanese | 1428 | 1245 |
| LMArena Korean | 1401 | 1223 |
| LMArena Russian | 1430 | 1283 |
| LMArena Spanish | 1442 | 1302 |
Instruction Following Inkling leads
Inkling: 75.3 (#65), o1-mini: 67.0 (#200)
| Benchmark | Inkling | o1-mini |
|---|---|---|
| LMArena Instruction Following | 1427 | 1304 |
| LiveBench Instruction Following | — | 65.4% |
Long Context Inkling leads
Inkling: 43.9 (#79), o1-mini: 40.1 (#156)
| Benchmark | Inkling | o1-mini |
|---|---|---|
| LMArena Longer Query | 1436 | 1321 |
Writing & Preference Inkling leads
Inkling: 65.5 (#48), o1-mini: 48.6 (#196)
| Benchmark | Inkling | o1-mini |
|---|---|---|
| LMArena Text | 1443 | 1317 |
| LMArena Creative Writing | 1390 | 1244 |
| LMArena Multi-Turn | 1436 | 1314 |
| Short-Story Creative Writing | — | 64.9% |
| EQ-Bench Creative Writing | 1611 | — |
| EQ-Bench 4 | 1226 | — |
| LiveBench Language | — | 40.9% |
Frequently asked questions
Is Inkling better than o1-mini?
Inkling is the stronger model overall, scoring 44.1 to 33.7 on the Noometry Index.
Is Inkling or o1-mini better for coding?
They score almost the same on coding (34.1 vs 35.1); test both on your own repository before choosing.
How many benchmarks do Inkling and o1-mini share?
24 benchmarks have published results for both models. Inkling has 41 scored results on Noometry and o1-mini has 39.