Model comparison
GPT-6.1 Sol vs Inkling
GPT-6.1 Sol is the stronger model overall, scoring 65.6 to 44.1 on the Noometry Index. Inkling costs 1.6× less per token, which makes it the better buy when GPT-6.1 Sol's lead doesn't matter for your workload.
Last verified . 27 shared benchmarks.
Summary
- They share 27 benchmarks with published results for both. GPT-6.1 Sol scores higher in 8 categories and Inkling in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-6.1 Sol leads 93.7 to 31.3.
- The biggest single-benchmark swing is ProofBench: 99% for GPT-6.1 Sol and 0% for Inkling.
- Inkling is cheaper at $1.87 / $4.68 per million input/output tokens, against $2 / $10 for GPT-6.1 Sol.
- GPT-6.1 Sol accepts more context: 1.05M tokens versus 66K.
- Inkling has downloadable open weights; the other is API-only.
Side by side
| GPT-6.1 Sol | Inkling | |
|---|---|---|
| Provider | OpenAI | Thinking Machines Lab |
| Noometry Index | 65.6 | 44.1 |
| Released | 2026-09-29 | 2026-07-15 |
| Weights | Proprietary | Open |
| Context window | 1.05M | 66K |
| Max output | 128K | 66K |
| Input $ / M tokens | $2 | $1.87 |
| Output $ / M tokens | $10 | $4.68 |
| Results tracked | 34 | 41 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-6.1 Sol leads
GPT-6.1 Sol: 63.2 (#8), Inkling: 34.5 (#234)
| Benchmark | GPT-6.1 Sol | Inkling |
|---|---|---|
| FrontierCode | 50.2% | 14% |
| LMArena WebDev | 1755 | 1413 |
| SciCode | 55.8% | 47% |
| LMArena Coding | 1487 | 1464 |
| DeepSWE | 75.2% | — |
| FrontierSWE | — | 4.1% |
| WeirdML | — | 32.3% |
| ALE-Bench | — | 946 |
Agentic & Tool Use GPT-6.1 Sol leads
GPT-6.1 Sol: 39.6 (#26), Inkling: 29.6 (#85)
| Benchmark | GPT-6.1 Sol | Inkling |
|---|---|---|
| APEX-Agents | 60% | 33.8% |
| τ²-bench Banking | — | 25% |
| GDP.pdf | 32% | — |
Reasoning GPT-6.1 Sol leads
GPT-6.1 Sol: 81.9 (#2), Inkling: 40.4 (#56)
| Benchmark | GPT-6.1 Sol | Inkling |
|---|---|---|
| ARC-AGI-2 | 94.2% | 36.5% |
| ARC-AGI-1 | 98.5% | 79.5% |
| CritPt | 31.7% | 5.4% |
| Chess Puzzles | 61% | 21% |
| LMArena Hard Prompts | 1466 | 1451 |
| Epoch Capabilities Index | 166.09 | 148.54 |
| SimpleBench | — | 50% |
| NYT Connections (extended) | 95.5% | — |
| EBR-Bench | 54.3% | — |
| Mystery Game Puzzles | 80% | — |
| DTBench | — | 87.5% |
| LMCA | — | 37.6% |
Math GPT-6.1 Sol leads
GPT-6.1 Sol: 93.7 (#1), Inkling: 31.3 (#225)
| Benchmark | GPT-6.1 Sol | Inkling |
|---|---|---|
| FrontierMath (Tiers 1-3) | 93.7% | 33.3% |
| FrontierMath Tier 4 | 100% | 4.9% |
| OTIS Mock AIME 2024-2025 | 100% | 88.9% |
| ProofBench | 99% | 0% |
| LMArena Math | 1464 | 1479 |
Knowledge GPT-6.1 Sol leads
GPT-6.1 Sol: 71.8 (#4), Inkling: 55.1 (#49)
| Benchmark | GPT-6.1 Sol | Inkling |
|---|---|---|
| GPQA Diamond | 95.4% | 88.3% |
| SimpleQA Verified | 73.9% | 40.3% |
| LMArena Expert | 1502 | 1465 |
Multimodal Not comparable
GPT-6.1 Sol: 52.7 (#5), Inkling: —
| Benchmark | GPT-6.1 Sol | Inkling |
|---|---|---|
| LMArena Vision | 1288 | — |
| Furniture Assembly | 80% | — |
Multilingual Too close to call
GPT-6.1 Sol: 54.3 (#46), Inkling: 54.0 (#52)
| Benchmark | GPT-6.1 Sol | Inkling |
|---|---|---|
| LMArena Non-English | 1438 | 1434 |
| LMArena Chinese | 1477 | 1490 |
| LMArena Russian | 1455 | 1429 |
| LMArena French | — | 1458 |
| LMArena German | — | 1446 |
| LMArena Japanese | — | 1429 |
| LMArena Korean | — | 1404 |
| LMArena Spanish | — | 1448 |
Instruction Following GPT-6.1 Sol leads
GPT-6.1 Sol: 77.0 (#29), Inkling: 75.1 (#71)
| Benchmark | GPT-6.1 Sol | Inkling |
|---|---|---|
| LMArena Instruction Following | 1468 | 1426 |
Long Context GPT-6.1 Sol leads
GPT-6.1 Sol: 44.9 (#54), Inkling: 43.8 (#86)
| Benchmark | GPT-6.1 Sol | Inkling |
|---|---|---|
| LMArena Longer Query | 1465 | 1434 |
Writing & Preference Inkling leads
GPT-6.1 Sol: 63.6 (#63), Inkling: 65.2 (#51)
| Benchmark | GPT-6.1 Sol | Inkling |
|---|---|---|
| LMArena Text | 1447 | 1441 |
| LMArena Creative Writing | 1432 | 1387 |
| LMArena Multi-Turn | 1449 | 1436 |
| EQ-Bench Creative Writing | — | 1611 |
| EQ-Bench 4 | — | 1226 |
Frequently asked questions
Is GPT-6.1 Sol better than Inkling?
GPT-6.1 Sol is the stronger model overall, scoring 65.6 to 44.1 on the Noometry Index. Inkling costs 1.6× less per token, which makes it the better buy when GPT-6.1 Sol's lead doesn't matter for your workload.
Which is cheaper, GPT-6.1 Sol or Inkling?
Inkling is cheaper. It lists at $1.87 per million input tokens and $4.68 per million output tokens; GPT-6.1 Sol lists at $2 and $10.
Is GPT-6.1 Sol or Inkling better for coding?
GPT-6.1 Sol scores higher on coding benchmarks: 63.2 versus 34.5 in the Noometry coding category.
Which has the bigger context window?
GPT-6.1 Sol does, with 1.05M tokens against 66K.
How many benchmarks do GPT-6.1 Sol and Inkling share?
27 benchmarks have published results for both models. GPT-6.1 Sol has 34 scored results on Noometry and Inkling has 41.