Model comparison
GPT-5.2 vs GPT-6.1 Sol
GPT-6.1 Sol is the stronger model overall, scoring 65.6 to 54.1 on the Noometry Index.
Last verified . 28 shared benchmarks.
Summary
- They share 28 benchmarks with published results for both. GPT-5.2 scores higher in 2 categories and GPT-6.1 Sol in 8 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-6.1 Sol leads 93.7 to 60.0.
- The biggest single-benchmark swing is ProofBench: 15% for GPT-5.2 and 99% for GPT-6.1 Sol.
- GPT-6.1 Sol is cheaper at $2 / $10 per million input/output tokens, against $1.75 / $14 for GPT-5.2.
- GPT-6.1 Sol accepts more context: 1.05M tokens versus 400K.
Side by side
| GPT-5.2 | GPT-6.1 Sol | |
|---|---|---|
| Provider | OpenAI | OpenAI |
| Noometry Index | 54.1 | 65.6 |
| Released | 2025-12-11 | 2026-09-29 |
| Weights | Proprietary | Proprietary |
| Context window | 400K | 1.05M |
| Max output | 128K | 128K |
| Input $ / M tokens | $1.75 | $2 |
| Output $ / M tokens | $14 | $10 |
| Results tracked | 67 | 34 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-6.1 Sol leads
GPT-5.2: 51.6 (#37), GPT-6.1 Sol: 63.2 (#8)
| Benchmark | GPT-5.2 | GPT-6.1 Sol |
|---|---|---|
| LMArena WebDev | 1416 | 1755 |
| LMArena Coding | 1447 | 1487 |
| SWE-bench Verified | 73.8% | — |
| DeepSWE | — | 75.2% |
| FrontierCode | — | 50.2% |
| SWE-bench Verified (bash only) | 72.8% | — |
| SWE-bench Multilingual | 66.7% | — |
| SciCode | — | 55.8% |
| GSO | 27.4% | — |
| WeirdML | 72.2% | — |
| ALE-Bench | 1,294 | — |
| AlgoTune | 2.05 | — |
Agentic & Tool Use Too close to call
GPT-5.2: 40.2 (#24), GPT-6.1 Sol: 39.6 (#26)
| Benchmark | GPT-5.2 | GPT-6.1 Sol |
|---|---|---|
| Terminal-Bench | 64.9% | — |
| APEX-Agents | — | 60% |
| Berkeley Function Calling Leaderboard | 55.9% | — |
| GDPval | 49.7% | — |
| Remote Labor Index | 2.5% | — |
| τ²-bench Airline | 83% | — |
| τ²-bench Banking | 32.2% | — |
| τ²-bench Retail | 81.6% | — |
| τ²-bench Telecom | 89.7% | — |
| DeepResearch Bench | 41.1% | — |
| GDP.pdf | — | 32% |
| LMArena Search | 1207 | — |
| METR Time Horizons | 75.3% | — |
| Vending-Bench 2 | 3,591 | — |
Reasoning GPT-6.1 Sol leads
GPT-5.2: 50.2 (#35), GPT-6.1 Sol: 81.9 (#2)
| Benchmark | GPT-5.2 | GPT-6.1 Sol |
|---|---|---|
| ARC-AGI-2 | 52.9% | 94.2% |
| NYT Connections (extended) | 83.6% | 95.5% |
| ARC-AGI-1 | 86.2% | 98.5% |
| Chess Puzzles | 49% | 61% |
| EBR-Bench | 23% | 54.3% |
| LMArena Hard Prompts | 1445 | 1466 |
| Mystery Game Puzzles | 23% | 80% |
| Epoch Capabilities Index | 153.45 | 166.09 |
| SimpleBench | 45.8% | — |
| Kagi LLM Benchmark | 73.3% | — |
| CritPt | — | 31.7% |
| EnigmaEval | 10.4% | — |
| DTBench | 90.9% | — |
| LMCA | 43.9% | — |
| ForecastBench | 60.1 | — |
Math GPT-6.1 Sol leads
GPT-5.2: 60.0 (#38), GPT-6.1 Sol: 93.7 (#1)
| Benchmark | GPT-5.2 | GPT-6.1 Sol |
|---|---|---|
| FrontierMath (Tiers 1-3) | 67.4% | 93.7% |
| FrontierMath Tier 4 | 31.7% | 100% |
| OTIS Mock AIME 2024-2025 | 96.1% | 100% |
| ProofBench | 15% | 99% |
| LMArena Math | 1440 | 1464 |
| MathArena Final-Answer Competitions | 72% | — |
| FrontierMath (Feb 2025 set) | 40.7% | — |
| FrontierMath Tier 4 (v1) | 18.8% | — |
Knowledge GPT-6.1 Sol leads
GPT-5.2: 59.3 (#32), GPT-6.1 Sol: 71.8 (#4)
| Benchmark | GPT-5.2 | GPT-6.1 Sol |
|---|---|---|
| GPQA Diamond | 91.4% | 95.4% |
| SimpleQA Verified | 37.1% | 73.9% |
| LMArena Expert | 1445 | 1502 |
| Humanity's Last Exam | 27.8% | — |
| Vectara Hallucination Rate | 8.4% | — |
Multimodal GPT-6.1 Sol leads
GPT-5.2: 51.3 (#7), GPT-6.1 Sol: 52.7 (#5)
| Benchmark | GPT-5.2 | GPT-6.1 Sol |
|---|---|---|
| LMArena Vision | 1268 | 1288 |
| Furniture Assembly | 38.3% | 80% |
| VPCT | 84% | — |
| LMArena Document | 1405 | — |
Multilingual Too close to call
GPT-5.2: 53.4 (#67), GPT-6.1 Sol: 54.3 (#46)
| Benchmark | GPT-5.2 | GPT-6.1 Sol |
|---|---|---|
| LMArena Non-English | 1425 | 1438 |
| LMArena Chinese | 1460 | 1477 |
| LMArena Russian | 1440 | 1455 |
| LMArena French | 1455 | — |
| LMArena German | 1448 | — |
| LMArena Japanese | 1420 | — |
| LMArena Korean | 1392 | — |
| LMArena Spanish | 1433 | — |
Instruction Following GPT-6.1 Sol leads
GPT-5.2: 74.7 (#89), GPT-6.1 Sol: 77.0 (#29)
| Benchmark | GPT-5.2 | GPT-6.1 Sol |
|---|---|---|
| LMArena Instruction Following | 1417 | 1468 |
Long Context Too close to call
GPT-5.2: 44.0 (#78), GPT-6.1 Sol: 44.9 (#54)
| Benchmark | GPT-5.2 | GPT-6.1 Sol |
|---|---|---|
| LMArena Longer Query | 1428 | 1465 |
| CL-bench | 18.2% | — |
Writing & Preference GPT-5.2 leads
GPT-5.2: 66.8 (#32), GPT-6.1 Sol: 63.6 (#63)
| Benchmark | GPT-5.2 | GPT-6.1 Sol |
|---|---|---|
| LMArena Text | 1439 | 1447 |
| LMArena Creative Writing | 1401 | 1432 |
| LMArena Multi-Turn | 1458 | 1449 |
| EQ-Bench Creative Writing | 1703 | — |
Frequently asked questions
Is GPT-5.2 better than GPT-6.1 Sol?
GPT-6.1 Sol is the stronger model overall, scoring 65.6 to 54.1 on the Noometry Index.
Which is cheaper, GPT-5.2 or GPT-6.1 Sol?
GPT-6.1 Sol is cheaper. It lists at $2 per million input tokens and $10 per million output tokens; GPT-5.2 lists at $1.75 and $14.
Is GPT-5.2 or GPT-6.1 Sol better for coding?
GPT-6.1 Sol scores higher on coding benchmarks: 63.2 versus 51.6 in the Noometry coding category.
Which has the bigger context window?
GPT-6.1 Sol does, with 1.05M tokens against 400K.
How many benchmarks do GPT-5.2 and GPT-6.1 Sol share?
28 benchmarks have published results for both models. GPT-5.2 has 67 scored results on Noometry and GPT-6.1 Sol has 34.