Model comparison
GPT-5.6 Sol vs GPT-5 Nano
GPT-5.6 Sol is the stronger model overall, scoring 64.4 to 33.4 on the Noometry Index. GPT-5 Nano costs 58× less per token, which makes it the better buy when GPT-5.6 Sol's lead doesn't matter for your workload.
Last verified . 34 shared benchmarks.
Summary
- They share 34 benchmarks with published results for both. GPT-5.6 Sol scores higher in 10 categories and GPT-5 Nano in 0 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GPT-5.6 Sol leads 74.7 to 16.4.
- The biggest single-benchmark swing is ARC-AGI-2: 92.5% for GPT-5.6 Sol and 2.6% for GPT-5 Nano.
- GPT-5 Nano is cheaper at $0.05 / $0.40 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-5.6 Sol | GPT-5 Nano | |
|---|---|---|
| Provider | OpenAI | OpenAI |
| Noometry Index | 64.4 | 33.4 |
| Released | 2026-07-09 | 2025-08-07 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | 400K |
| Max output | 128K | 128K |
| Input $ / M tokens | $4 | $0.05 |
| Output $ / M tokens | $20 | $0.40 |
| Results tracked | 64 | 48 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.6 Sol leads
GPT-5.6 Sol: 61.1 (#7), GPT-5 Nano: 33.3 (#248)
| Benchmark | GPT-5.6 Sol | GPT-5 Nano |
|---|---|---|
| WeirdML | 89.4% | 38.1% |
| LMArena Coding | 1493 | 1351 |
| ALE-Bench | 2,177 | 718.67 |
| DeepSWE | 72.7% | — |
| FrontierCode | 47.5% | — |
| SWE-bench Verified (bash only) | — | 34.8% |
| CursorBench | 41.7% | — |
| LMArena WebDev | 1619 | — |
| FrontierSWE | 32.2% | — |
| SciCode | 57.1% | — |
| MirrorCode | 20% | — |
Agentic & Tool Use GPT-5.6 Sol leads
GPT-5.6 Sol: 50.2 (#7), GPT-5 Nano: 25.6 (#99)
| Benchmark | GPT-5.6 Sol | GPT-5 Nano |
|---|---|---|
| Terminal-Bench | — | 21.8% |
| APEX-Agents | 51.4% | — |
| Berkeley Function Calling Leaderboard | — | 51.5% |
| OSWorld 2.0 | 27.3% | — |
| τ²-bench Banking | 46.9% | — |
| PostTrainBench | 36.2% | — |
| BALROG | 60% | — |
| GBAEval | 52.6% | — |
| GDP.pdf | 30.7% | — |
| LMArena Search | 1257 | — |
| Vending-Bench 2 | 9,619 | — |
Reasoning GPT-5.6 Sol leads
GPT-5.6 Sol: 74.7 (#6), GPT-5 Nano: 16.4 (#291)
| Benchmark | GPT-5.6 Sol | GPT-5 Nano |
|---|---|---|
| ARC-AGI-2 | 92.5% | 2.6% |
| Kagi LLM Benchmark | 67% | 62.2% |
| ARC-AGI-1 | 97.5% | 20.7% |
| Chess Puzzles | 64% | 27% |
| LMArena Hard Prompts | 1481 | 1329 |
| Mystery Game Puzzles | 58% | 9% |
| DTBench | 96% | 62.7% |
| LMCA | 59.2% | 7.9% |
| Epoch Capabilities Index | 161.99 | 139.39 |
| SimpleBench | 71.7% | — |
| NYT Connections (extended) | 93.8% | — |
| CritPt | 32.3% | — |
| EnigmaEval | 37.1% | — |
| EBR-Bench | 44.8% | — |
| Surface Evolver Bench | 93.1% | — |
| Bench to the Future 3 | 0.14 | — |
| ForecastBench | — | 59.1 |
Math GPT-5.6 Sol leads
GPT-5.6 Sol: 85.5 (#7), GPT-5 Nano: 29.1 (#221)
| Benchmark | GPT-5.6 Sol | GPT-5 Nano |
|---|---|---|
| FrontierMath (Tiers 1-3) | 89.1% | 20% |
| FrontierMath Tier 4 | 82.9% | 2.4% |
| OTIS Mock AIME 2024-2025 | 100% | 81.1% |
| ProofBench | 83% | 12% |
| LMArena Math | 1472 | 1318 |
| Omni-MATH | — | 54.6% |
| MATH Level 5 | — | 95.2% |
| FrontierMath (Feb 2025 set) | — | 8.3% |
| FrontierMath Erdős | 0% | — |
| FrontierMath Tier 4 (v1) | — | 2.1% |
Knowledge GPT-5.6 Sol leads
GPT-5.6 Sol: 64.3 (#16), GPT-5 Nano: 35.8 (#166)
| Benchmark | GPT-5.6 Sol | GPT-5 Nano |
|---|---|---|
| GPQA Diamond | 93.5% | 69.4% |
| SimpleQA Verified | 69.7% | 11.7% |
| Vectara Hallucination Rate | 12.4% | 10.5% |
| LMArena Expert | 1517 | 1321 |
| MMLU-Pro | — | 77.8% |
| GPQA (HELM) | — | 67.9% |
Multimodal GPT-5.6 Sol leads
GPT-5.6 Sol: 48.9 (#8), GPT-5 Nano: 30.7 (#102)
| Benchmark | GPT-5.6 Sol | GPT-5 Nano |
|---|---|---|
| LMArena Vision | 1281 | 1159 |
| VPCT | — | 37.2% |
| Blueprint-Bench 2 | 33.6% | — |
| Furniture Assembly | 56.7% | — |
| LMArena Document | 1483 | — |
Multilingual GPT-5.6 Sol leads
GPT-5.6 Sol: 55.4 (#32), GPT-5 Nano: 45.5 (#167)
| Benchmark | GPT-5.6 Sol | GPT-5 Nano |
|---|---|---|
| LMArena Non-English | 1450 | 1313 |
| LMArena Chinese | 1523 | 1355 |
| LMArena German | 1476 | 1329 |
| LMArena Korean | 1434 | 1269 |
| LMArena Russian | 1466 | 1296 |
| LMArena Spanish | 1449 | 1360 |
| LMArena French | 1475 | — |
| LMArena Japanese | 1475 | — |
Instruction Following GPT-5.6 Sol leads
GPT-5.6 Sol: 77.8 (#16), GPT-5 Nano: 75.2 (#72)
| Benchmark | GPT-5.6 Sol | GPT-5 Nano |
|---|---|---|
| LMArena Instruction Following | 1480 | 1306 |
| IFEval | — | 93.2% |
Long Context GPT-5.6 Sol leads
GPT-5.6 Sol: 45.3 (#42), GPT-5 Nano: 31.3 (#275)
| Benchmark | GPT-5.6 Sol | GPT-5 Nano |
|---|---|---|
| LMArena Longer Query | 1479 | 1313 |
| Fiction.LiveBench | — | 44.4% |
Writing & Preference GPT-5.6 Sol leads
GPT-5.6 Sol: 73.5 (#12), GPT-5 Nano: 39.4 (#244)
| Benchmark | GPT-5.6 Sol | GPT-5 Nano |
|---|---|---|
| LMArena Text | 1456 | 1320 |
| LMArena Creative Writing | 1450 | 1250 |
| EQ-Bench Creative Writing | 1972 | 705 |
| LMArena Multi-Turn | 1456 | 1311 |
| WildBench | — | 80.6% |
| EQ-Bench 4 | 1250 | — |
Frequently asked questions
Is GPT-5.6 Sol better than GPT-5 Nano?
GPT-5.6 Sol is the stronger model overall, scoring 64.4 to 33.4 on the Noometry Index. GPT-5 Nano costs 58× 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-5.6 Sol or GPT-5 Nano?
GPT-5 Nano is cheaper. It lists at $0.05 per million input tokens and $0.40 per million output tokens; GPT-5.6 Sol lists at $4 and $20.
Is GPT-5.6 Sol or GPT-5 Nano better for coding?
GPT-5.6 Sol scores higher on coding benchmarks: 61.1 versus 33.3 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-5.6 Sol and GPT-5 Nano share?
34 benchmarks have published results for both models. GPT-5.6 Sol has 64 scored results on Noometry and GPT-5 Nano has 48.