Model comparison
GPT-6.1 Sol vs o1
GPT-6.1 Sol is the stronger model overall, scoring 65.6 to 40.9 on the Noometry Index.
Last verified . 20 shared benchmarks.
Summary
- They share 20 benchmarks with published results for both. GPT-6.1 Sol scores higher in 9 categories and o1 in 1 category; 10 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-6.1 Sol leads 93.7 to 36.1.
- The biggest single-benchmark swing is FrontierMath (Tiers 1-3): 93.7% for GPT-6.1 Sol and 14.7% for o1.
- GPT-6.1 Sol is cheaper at $2 / $10 per million input/output tokens, against $15 / $60 for o1.
- GPT-6.1 Sol accepts more context: 1.05M tokens versus 200K.
Side by side
| GPT-6.1 Sol | o1 | |
|---|---|---|
| Provider | OpenAI | OpenAI |
| Noometry Index | 65.6 | 40.9 |
| Released | 2026-09-29 | 2024-09-12 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | 200K |
| Max output | 128K | 100K |
| Input $ / M tokens | $2 | $15 |
| Output $ / M tokens | $10 | $60 |
| Results tracked | 34 | 52 |
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), o1: 46.1 (#70)
| Benchmark | GPT-6.1 Sol | o1 |
|---|---|---|
| LMArena Coding | 1487 | 1367 |
| DeepSWE | 75.2% | — |
| FrontierCode | 50.2% | — |
| Aider Polyglot | — | 61.7% |
| LMArena WebDev | 1755 | — |
| SciCode | 55.8% | — |
| WeirdML | — | 47.6% |
| LiveBench Coding | — | 69.7% |
| CadEval | — | 56% |
| HumanEval+ | — | 89% |
| MBPP+ | — | 80.2% |
Agentic & Tool Use GPT-6.1 Sol leads
GPT-6.1 Sol: 39.6 (#26), o1: 24.6 (#117)
| Benchmark | GPT-6.1 Sol | o1 |
|---|---|---|
| APEX-Agents | 60% | — |
| Cybench | — | 10% |
| GDP.pdf | 32% | — |
| METR Time Horizons | — | 51.1% |
Reasoning GPT-6.1 Sol leads
GPT-6.1 Sol: 81.9 (#2), o1: 27.9 (#111)
| Benchmark | GPT-6.1 Sol | o1 |
|---|---|---|
| ARC-AGI-1 | 98.5% | 30.7% |
| Chess Puzzles | 61% | 15% |
| LMArena Hard Prompts | 1466 | 1371 |
| Epoch Capabilities Index | 166.09 | 141.91 |
| ARC-AGI-2 | 94.2% | — |
| SimpleBench | — | 41.7% |
| NYT Connections (extended) | 95.5% | — |
| CritPt | 31.7% | — |
| EnigmaEval | — | 5.7% |
| EBR-Bench | 54.3% | — |
| LiveBench Reasoning | — | 91.6% |
| Mystery Game Puzzles | 80% | — |
| DTBench | — | 74.7% |
| LiveBench Data Analysis | — | 65.5% |
| LMCA | — | 22.3% |
| LiveBench | — | 75.7% |
Math GPT-6.1 Sol leads
GPT-6.1 Sol: 93.7 (#1), o1: 36.1 (#175)
| Benchmark | GPT-6.1 Sol | o1 |
|---|---|---|
| FrontierMath (Tiers 1-3) | 93.7% | 14.7% |
| OTIS Mock AIME 2024-2025 | 100% | 73.3% |
| LMArena Math | 1464 | 1388 |
| FrontierMath Tier 4 | 100% | — |
| ProofBench | 99% | — |
| LiveBench Math | — | 80.3% |
| MATH Level 5 | — | 94.7% |
| FrontierMath (Feb 2025 set) | — | 9.3% |
Knowledge GPT-6.1 Sol leads
GPT-6.1 Sol: 71.8 (#4), o1: 41.5 (#110)
| Benchmark | GPT-6.1 Sol | o1 |
|---|---|---|
| GPQA Diamond | 95.4% | 76.8% |
| SimpleQA Verified | 73.9% | 41.1% |
| LMArena Expert | 1502 | 1361 |
| Humanity's Last Exam | — | 8% |
| Confabulations | — | 11.7% |
Multimodal GPT-6.1 Sol leads
GPT-6.1 Sol: 52.7 (#5), o1: 34.2 (#93)
| Benchmark | GPT-6.1 Sol | o1 |
|---|---|---|
| LMArena Vision | 1288 | 1168 |
| GeoBench | — | 80% |
| VPCT | — | 37% |
| Furniture Assembly | 80% | — |
| SpatialViz-Bench | — | 41.4% |
Multilingual GPT-6.1 Sol leads
GPT-6.1 Sol: 54.3 (#46), o1: 48.6 (#142)
| Benchmark | GPT-6.1 Sol | o1 |
|---|---|---|
| LMArena Non-English | 1438 | 1358 |
| LMArena Chinese | 1477 | 1394 |
| LMArena Russian | 1455 | 1356 |
| LMArena French | — | 1344 |
| LMArena German | — | 1337 |
| LMArena Japanese | — | 1346 |
| LMArena Korean | — | 1396 |
| LMArena Spanish | — | 1345 |
Instruction Following GPT-6.1 Sol leads
GPT-6.1 Sol: 77.0 (#29), o1: 74.8 (#86)
| Benchmark | GPT-6.1 Sol | o1 |
|---|---|---|
| LMArena Instruction Following | 1468 | 1367 |
| LiveBench Instruction Following | — | 81.5% |
Long Context o1 leads
GPT-6.1 Sol: 44.9 (#54), o1: 50.3 (#9)
| Benchmark | GPT-6.1 Sol | o1 |
|---|---|---|
| LMArena Longer Query | 1465 | 1378 |
| Fiction.LiveBench | — | 83.3% |
Writing & Preference GPT-6.1 Sol leads
GPT-6.1 Sol: 63.6 (#63), o1: 55.6 (#144)
| Benchmark | GPT-6.1 Sol | o1 |
|---|---|---|
| LMArena Text | 1447 | 1366 |
| LMArena Creative Writing | 1432 | 1348 |
| LMArena Multi-Turn | 1449 | 1369 |
| Short-Story Creative Writing | — | 70.2% |
| LiveBench Language | — | 65.4% |
Frequently asked questions
Is GPT-6.1 Sol better than o1?
GPT-6.1 Sol is the stronger model overall, scoring 65.6 to 40.9 on the Noometry Index.
Which is cheaper, GPT-6.1 Sol or o1?
GPT-6.1 Sol is cheaper. It lists at $2 per million input tokens and $10 per million output tokens; o1 lists at $15 and $60.
Is GPT-6.1 Sol or o1 better for coding?
GPT-6.1 Sol scores higher on coding benchmarks: 63.2 versus 46.1 in the Noometry coding category.
Which has the bigger context window?
GPT-6.1 Sol does, with 1.05M tokens against 200K.
How many benchmarks do GPT-6.1 Sol and o1 share?
20 benchmarks have published results for both models. GPT-6.1 Sol has 34 scored results on Noometry and o1 has 52.