Model comparison
GPT-5.6 Sol vs o1-mini
GPT-5.6 Sol is the stronger model overall, scoring 64.4 to 33.7 on the Noometry Index.
Last verified . 24 shared benchmarks.
Summary
- They share 24 benchmarks with published results for both. GPT-5.6 Sol scores higher in 9 categories and o1-mini in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GPT-5.6 Sol leads 74.7 to 8.9.
- The biggest single-benchmark swing is ARC-AGI-2: 92.5% for GPT-5.6 Sol and 0.8% for o1-mini.
Side by side
| GPT-5.6 Sol | o1-mini | |
|---|---|---|
| Provider | OpenAI | OpenAI |
| Noometry Index | 64.4 | 33.7 |
| Released | 2026-07-09 | 2024-09-12 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | — |
| Max output | 128K | — |
| Input $ / M tokens | $4 | — |
| Output $ / M tokens | $20 | — |
| Results tracked | 64 | 39 |
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), o1-mini: 35.1 (#218)
| Benchmark | GPT-5.6 Sol | o1-mini |
|---|---|---|
| WeirdML | 89.4% | 36.3% |
| LMArena Coding | 1493 | 1362 |
| DeepSWE | 72.7% | — |
| FrontierCode | 47.5% | — |
| Aider Polyglot | — | 32.9% |
| CursorBench | 41.7% | — |
| LMArena WebDev | 1619 | — |
| FrontierSWE | 32.2% | — |
| SciCode | 57.1% | — |
| LiveBench Coding | — | 48% |
| MirrorCode | 20% | — |
| ALE-Bench | 2,177 | — |
| HumanEval+ | — | 89% |
| MBPP+ | — | 78.8% |
Agentic & Tool Use GPT-5.6 Sol leads
GPT-5.6 Sol: 50.2 (#7), o1-mini: 24.3 (#112)
| Benchmark | GPT-5.6 Sol | o1-mini |
|---|---|---|
| APEX-Agents | 51.4% | — |
| OSWorld 2.0 | 27.3% | — |
| τ²-bench Banking | 46.9% | — |
| Cybench | — | 10% |
| 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), o1-mini: 8.9 (#340)
| Benchmark | GPT-5.6 Sol | o1-mini |
|---|---|---|
| ARC-AGI-2 | 92.5% | 0.8% |
| SimpleBench | 71.7% | 18.1% |
| ARC-AGI-1 | 97.5% | 14% |
| LMArena Hard Prompts | 1481 | 1333 |
| Epoch Capabilities Index | 161.99 | 135.82 |
| Kagi LLM Benchmark | 67% | — |
| NYT Connections (extended) | 93.8% | — |
| CritPt | 32.3% | — |
| Chess Puzzles | 64% | — |
| EnigmaEval | 37.1% | — |
| EBR-Bench | 44.8% | — |
| LiveBench Reasoning | — | 72.3% |
| Mystery Game Puzzles | 58% | — |
| DTBench | 96% | — |
| LiveBench Data Analysis | — | 57.9% |
| LMCA | 59.2% | — |
| Surface Evolver Bench | 93.1% | — |
| Bench to the Future 3 | 0.14 | — |
| LiveBench | — | 57.8% |
Math GPT-5.6 Sol leads
GPT-5.6 Sol: 85.5 (#7), o1-mini: 33.7 (#168)
| Benchmark | GPT-5.6 Sol | o1-mini |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 100% | 46.9% |
| LMArena Math | 1472 | 1358 |
| FrontierMath (Tiers 1-3) | 89.1% | — |
| FrontierMath Tier 4 | 82.9% | — |
| ProofBench | 83% | — |
| LiveBench Math | — | 62% |
| MATH Level 5 | — | 89.2% |
| FrontierMath (Feb 2025 set) | — | 1.7% |
| FrontierMath Erdős | 0% | — |
Knowledge GPT-5.6 Sol leads
GPT-5.6 Sol: 64.3 (#16), o1-mini: 34.8 (#180)
| Benchmark | GPT-5.6 Sol | o1-mini |
|---|---|---|
| GPQA Diamond | 93.5% | 62.4% |
| LMArena Expert | 1517 | 1316 |
| SimpleQA Verified | 69.7% | — |
| Confabulations | — | 18.6% |
| Vectara Hallucination Rate | 12.4% | — |
Multimodal Not comparable
GPT-5.6 Sol: 48.9 (#8), o1-mini: —
| Benchmark | GPT-5.6 Sol | o1-mini |
|---|---|---|
| LMArena Vision | 1281 | — |
| 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), o1-mini: 43.8 (#177)
| Benchmark | GPT-5.6 Sol | o1-mini |
|---|---|---|
| LMArena Non-English | 1450 | 1289 |
| LMArena Chinese | 1523 | 1314 |
| LMArena French | 1475 | 1292 |
| LMArena German | 1476 | 1278 |
| LMArena Japanese | 1475 | 1245 |
| LMArena Korean | 1434 | 1223 |
| LMArena Russian | 1466 | 1283 |
| LMArena Spanish | 1449 | 1302 |
Instruction Following GPT-5.6 Sol leads
GPT-5.6 Sol: 77.8 (#16), o1-mini: 67.0 (#200)
| Benchmark | GPT-5.6 Sol | o1-mini |
|---|---|---|
| LMArena Instruction Following | 1480 | 1304 |
| LiveBench Instruction Following | — | 65.4% |
Long Context GPT-5.6 Sol leads
GPT-5.6 Sol: 45.3 (#42), o1-mini: 40.1 (#156)
| Benchmark | GPT-5.6 Sol | o1-mini |
|---|---|---|
| LMArena Longer Query | 1479 | 1321 |
Writing & Preference GPT-5.6 Sol leads
GPT-5.6 Sol: 73.5 (#12), o1-mini: 48.6 (#196)
| Benchmark | GPT-5.6 Sol | o1-mini |
|---|---|---|
| LMArena Text | 1456 | 1317 |
| LMArena Creative Writing | 1450 | 1244 |
| LMArena Multi-Turn | 1456 | 1314 |
| Short-Story Creative Writing | — | 64.9% |
| EQ-Bench Creative Writing | 1972 | — |
| EQ-Bench 4 | 1250 | — |
| LiveBench Language | — | 40.9% |
Frequently asked questions
Is GPT-5.6 Sol better than o1-mini?
GPT-5.6 Sol is the stronger model overall, scoring 64.4 to 33.7 on the Noometry Index.
Is GPT-5.6 Sol or o1-mini better for coding?
GPT-5.6 Sol scores higher on coding benchmarks: 61.1 versus 35.1 in the Noometry coding category.
How many benchmarks do GPT-5.6 Sol and o1-mini share?
24 benchmarks have published results for both models. GPT-5.6 Sol has 64 scored results on Noometry and o1-mini has 39.