Model comparison
GPT-5.1 vs GPT-5.6 Sol
GPT-5.6 Sol is the stronger model overall, scoring 65.0 to 49.0 on the Noometry Index. GPT-5.1 costs 2.3× less per token, which makes it the better buy when GPT-5.6 Sol's lead doesn't matter for your workload.
Last verified . 40 shared benchmarks.
Summary
- They share 40 benchmarks with published results for both. GPT-5.1 scores higher in 2 categories and GPT-5.6 Sol in 8 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GPT-5.6 Sol leads 74.8 to 39.8.
- The biggest single-benchmark swing is ARC-AGI-2: 17.6% for GPT-5.1 and 92.5% for GPT-5.6 Sol.
- GPT-5.1 is cheaper at $1.25 / $10 per million input/output tokens, against $4 / $20 for GPT-5.6 Sol.
- GPT-5.6 Sol accepts more context: 1.05M tokens versus 400K.
Side by side
| GPT-5.1 | GPT-5.6 Sol | |
|---|---|---|
| Provider | OpenAI | OpenAI |
| Noometry Index | 49.0 | 65.0 |
| Released | 2025-11-13 | 2026-07-09 |
| Weights | Proprietary | Proprietary |
| Context window | 400K | 1.05M |
| Max output | 128K | 128K |
| Input $ / M tokens | $1.25 | $4 |
| Output $ / M tokens | $10 | $20 |
| Results tracked | 63 | 65 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.6 Sol leads
GPT-5.1: 46.4 (#66), GPT-5.6 Sol: 65.1 (#7)
| Benchmark | GPT-5.1 | GPT-5.6 Sol |
|---|---|---|
| LMArena WebDev | 1395 | 1618 |
| SciCode | 43.3% | 57.1% |
| GSO | 13.7% | 76.5% |
| WeirdML | 60.8% | 89.4% |
| LMArena Coding | 1454 | 1498 |
| ALE-Bench | 1,192 | 2,177 |
| SWE-bench Verified | 68% | — |
| DeepSWE | — | 72.7% |
| FrontierCode | — | 47.5% |
| SWE-bench Verified (bash only) | 66% | — |
| CursorBench | — | 41.7% |
| FrontierSWE | — | 32.2% |
| LiveBench Coding | 72.5% | — |
| MirrorCode | — | 20% |
Agentic & Tool Use GPT-5.6 Sol leads
GPT-5.1: 32.7 (#60), GPT-5.6 Sol: 50.3 (#7)
| Benchmark | GPT-5.1 | GPT-5.6 Sol |
|---|---|---|
| LMArena Search | 1199 | 1257 |
| Vending-Bench 2 | 1,473 | 9,619 |
| Terminal-Bench | 47.6% | — |
| APEX-Agents | — | 51.4% |
| OSWorld 2.0 | — | 27.3% |
| τ²-bench Banking | — | 46.9% |
| DeepResearch Bench | 42.8% | — |
| PostTrainBench | — | 36.2% |
| BALROG | — | 60% |
| GBAEval | — | 52.6% |
| GDP.pdf | — | 30.7% |
Reasoning GPT-5.6 Sol leads
GPT-5.1: 39.8 (#58), GPT-5.6 Sol: 74.8 (#8)
| Benchmark | GPT-5.1 | GPT-5.6 Sol |
|---|---|---|
| ARC-AGI-2 | 17.6% | 92.5% |
| SimpleBench | 53.2% | 71.7% |
| ARC-AGI-1 | 72.8% | 97.5% |
| CritPt | 4.9% | 32.3% |
| Chess Puzzles | 32% | 64% |
| EnigmaEval | 11.2% | 37.1% |
| LMArena Hard Prompts | 1457 | 1484 |
| Mystery Game Puzzles | 19% | 58% |
| DTBench | 90.1% | 96% |
| LMCA | 43.9% | 59.2% |
| Epoch Capabilities Index | 149.64 | 161.66 |
| Kagi LLM Benchmark | — | 67% |
| NYT Connections (extended) | — | 93.8% |
| EBR-Bench | — | 44.8% |
| LiveBench Reasoning | 95.8% | — |
| LiveBench Data Analysis | 72.1% | — |
| Surface Evolver Bench | — | 93.1% |
| Bench to the Future 3 | — | 0.14 |
| ForecastBench | 58.1 | — |
| LiveBench | 78.8% | — |
Math GPT-5.6 Sol leads
GPT-5.1: 52.2 (#51), GPT-5.6 Sol: 85.6 (#9)
| Benchmark | GPT-5.1 | GPT-5.6 Sol |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 88.6% | 100% |
| LMArena Math | 1447 | 1474 |
| FrontierMath (Tiers 1-3) | — | 89.1% |
| FrontierMath Tier 4 | — | 82.9% |
| ProofBench | — | 83% |
| Omni-MATH | 46.4% | — |
| LiveBench Math | 94.5% | — |
| FrontierMath (Feb 2025 set) | 31% | — |
| FrontierMath Erdős | — | 0% |
| FrontierMath Tier 4 (v1) | 12.5% | — |
Knowledge GPT-5.6 Sol leads
GPT-5.1: 50.6 (#71), GPT-5.6 Sol: 64.3 (#18)
| Benchmark | GPT-5.1 | GPT-5.6 Sol |
|---|---|---|
| GPQA Diamond | 87.6% | 93.5% |
| SimpleQA Verified | 48% | 69.7% |
| Vectara Hallucination Rate | 10.9% | 12.4% |
| LMArena Expert | 1470 | 1516 |
| Humanity's Last Exam | 23.7% | — |
| MMLU-Pro | 57.9% | — |
| GPQA (HELM) | 44.2% | — |
Multimodal GPT-5.6 Sol leads
GPT-5.1: 44.8 (#19), GPT-5.6 Sol: 48.6 (#9)
| Benchmark | GPT-5.1 | GPT-5.6 Sol |
|---|---|---|
| LMArena Vision | 1250 | 1281 |
| LMArena Document | 1403 | 1483 |
| VPCT | 58.7% | — |
| Blueprint-Bench 2 | — | 33.6% |
| Furniture Assembly | — | 56.7% |
Multilingual GPT-5.6 Sol leads
GPT-5.1: 53.8 (#56), GPT-5.6 Sol: 55.3 (#32)
| Benchmark | GPT-5.1 | GPT-5.6 Sol |
|---|---|---|
| LMArena Non-English | 1431 | 1452 |
| LMArena Chinese | 1495 | 1527 |
| LMArena French | 1450 | 1477 |
| LMArena German | 1438 | 1476 |
| LMArena Japanese | 1453 | 1471 |
| LMArena Korean | 1401 | 1442 |
| LMArena Russian | 1435 | 1468 |
| LMArena Spanish | 1433 | 1441 |
Instruction Following GPT-5.1 leads
GPT-5.1: 83.9 (#1), GPT-5.6 Sol: 77.7 (#16)
| Benchmark | GPT-5.1 | GPT-5.6 Sol |
|---|---|---|
| LMArena Instruction Following | 1443 | 1482 |
| LiveBench Instruction Following | 93.3% | — |
| IFEval | 93.5% | — |
Long Context GPT-5.1 leads
GPT-5.1: 47.6 (#14), GPT-5.6 Sol: 45.4 (#42)
| Benchmark | GPT-5.1 | GPT-5.6 Sol |
|---|---|---|
| LMArena Longer Query | 1447 | 1480 |
| CL-bench | 23.7% | — |
| CL-bench Life | 17.3% | — |
Writing & Preference GPT-5.6 Sol leads
GPT-5.1: 64.5 (#55), GPT-5.6 Sol: 73.3 (#12)
| Benchmark | GPT-5.1 | GPT-5.6 Sol |
|---|---|---|
| LMArena Text | 1443 | 1457 |
| LMArena Creative Writing | 1427 | 1448 |
| LMArena Multi-Turn | 1450 | 1460 |
| EQ-Bench Creative Writing | — | 1972 |
| WildBench | 86.3% | — |
| EQ-Bench 4 | — | 1250 |
| LiveBench Language | 80.2% | — |
Frequently asked questions
Is GPT-5.1 better than GPT-5.6 Sol?
GPT-5.6 Sol is the stronger model overall, scoring 65.0 to 49.0 on the Noometry Index. GPT-5.1 costs 2.3× less per token, which makes it the better buy when GPT-5.6 Sol's lead doesn't matter for your workload.
Which is cheaper, GPT-5.1 or GPT-5.6 Sol?
GPT-5.1 is cheaper. It lists at $1.25 per million input tokens and $10 per million output tokens; GPT-5.6 Sol lists at $4 and $20.
Is GPT-5.1 or GPT-5.6 Sol better for coding?
GPT-5.6 Sol scores higher on coding benchmarks: 65.1 versus 46.4 in the Noometry coding category.
Which has the bigger context window?
GPT-5.6 Sol does, with 1.05M tokens against 400K.
How many benchmarks do GPT-5.1 and GPT-5.6 Sol share?
40 benchmarks have published results for both models. GPT-5.1 has 63 scored results on Noometry and GPT-5.6 Sol has 65.