Model comparison
GPT-6 Sol vs o3-pro
GPT-6 Sol is the stronger model overall, scoring 61.8 to 42.9 on the Noometry Index.
Last verified . 6 shared benchmarks.
Summary
- They share 6 benchmarks with published results for both. GPT-6 Sol scores higher in 4 categories and o3-pro in 1 category; 5 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GPT-6 Sol leads 74.0 to 23.8.
- The biggest single-benchmark swing is ARC-AGI-2: 89.6% for GPT-6 Sol and 4.9% for o3-pro.
- GPT-6 Sol is cheaper at $2 / $10 per million input/output tokens, against $20 / $80 for o3-pro.
- GPT-6 Sol accepts more context: 1.05M tokens versus 200K.
Side by side
| GPT-6 Sol | o3-pro | |
|---|---|---|
| Provider | OpenAI | OpenAI |
| Noometry Index | 61.8 | 42.9 |
| Released | 2026-09-22 | 2025-06-10 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | 200K |
| Max output | 128K | 100K |
| Input $ / M tokens | $2 | $20 |
| Output $ / M tokens | $10 | $80 |
| Results tracked | 45 | 12 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-6 Sol leads
GPT-6 Sol: 60.1 (#11), o3-pro: 55.5 (#24)
| Benchmark | GPT-6 Sol | o3-pro |
|---|---|---|
| DeepSWE | 68.8% | — |
| FrontierCode | 49.3% | — |
| Aider Polyglot | — | 84.9% |
| LMArena WebDev | 1688 | — |
| SciCode | 57.6% | — |
| WeirdML | — | 58.2% |
| LMArena Coding | 1447 | — |
| ALE-Bench | 2,462 | — |
Agentic & Tool Use Not comparable
GPT-6 Sol: 37.2 (#36), o3-pro: —
| Benchmark | GPT-6 Sol | o3-pro |
|---|---|---|
| APEX-Agents | 54.3% | — |
| GDP.pdf | 26.4% | — |
| Vending-Bench 2 | 14,428 | — |
Reasoning GPT-6 Sol leads
GPT-6 Sol: 74.0 (#9), o3-pro: 23.8 (#171)
| Benchmark | GPT-6 Sol | o3-pro |
|---|---|---|
| ARC-AGI-2 | 89.6% | 4.9% |
| ARC-AGI-1 | 95.5% | 59.3% |
| DTBench | 97.3% | 86.9% |
| LMCA | 59.1% | 38.5% |
| Epoch Capabilities Index | 162.72 | 147.42 |
| Kagi LLM Benchmark | — | 72.1% |
| NYT Connections (extended) | 90.1% | — |
| CritPt | 30.9% | — |
| EBR-Bench | 53.3% | — |
| LMArena Hard Prompts | 1418 | — |
| Mystery Game Puzzles | 56% | — |
Math Not comparable
GPT-6 Sol: 87.2 (#7), o3-pro: —
| Benchmark | GPT-6 Sol | o3-pro |
|---|---|---|
| FrontierMath (Tiers 1-3) | 89.8% | — |
| FrontierMath Tier 4 | 90% | — |
| OTIS Mock AIME 2024-2025 | 100% | — |
| ProofBench | 83% | — |
| LMArena Math | 1402 | — |
Knowledge GPT-6 Sol leads
GPT-6 Sol: 64.8 (#15), o3-pro: 29.5 (#238)
| Benchmark | GPT-6 Sol | o3-pro |
|---|---|---|
| Vectara Hallucination Rate | 6.5% | 23.3% |
| GPQA Diamond | 94.3% | — |
| SimpleQA Verified | 60.7% | — |
| Confabulations | — | 14.2% |
| LMArena Expert | 1439 | — |
Multimodal Not comparable
GPT-6 Sol: 47.6 (#10), o3-pro: —
| Benchmark | GPT-6 Sol | o3-pro |
|---|---|---|
| LMArena Vision | 1245 | — |
| Blueprint-Bench 2 | 36.9% | — |
| Furniture Assembly | 58.3% | — |
Multilingual Not comparable
GPT-6 Sol: 50.5 (#118), o3-pro: —
| Benchmark | GPT-6 Sol | o3-pro |
|---|---|---|
| LMArena Non-English | 1385 | — |
| LMArena Chinese | 1405 | — |
| LMArena French | 1410 | — |
| LMArena German | 1390 | — |
| LMArena Japanese | 1385 | — |
| LMArena Korean | 1341 | — |
| LMArena Russian | 1401 | — |
| LMArena Spanish | 1384 | — |
Instruction Following Not comparable
GPT-6 Sol: 74.5 (#94), o3-pro: —
| Benchmark | GPT-6 Sol | o3-pro |
|---|---|---|
| LMArena Instruction Following | 1412 | — |
Long Context o3-pro leads
GPT-6 Sol: 43.1 (#108), o3-pro: 72.2 (#1)
| Benchmark | GPT-6 Sol | o3-pro |
|---|---|---|
| Fiction.LiveBench | — | 97.2% |
| LMArena Longer Query | 1411 | — |
Writing & Preference GPT-6 Sol leads
GPT-6 Sol: 71.9 (#18), o3-pro: 57.1 (#133)
| Benchmark | GPT-6 Sol | o3-pro |
|---|---|---|
| LMArena Text | 1395 | — |
| LMArena Creative Writing | 1378 | — |
| Short-Story Creative Writing | — | 84.4% |
| EQ-Bench Creative Writing | 2125 | — |
| LMArena Multi-Turn | 1412 | — |
Frequently asked questions
Is GPT-6 Sol better than o3-pro?
GPT-6 Sol is the stronger model overall, scoring 61.8 to 42.9 on the Noometry Index.
Which is cheaper, GPT-6 Sol or o3-pro?
GPT-6 Sol is cheaper. It lists at $2 per million input tokens and $10 per million output tokens; o3-pro lists at $20 and $80.
Is GPT-6 Sol or o3-pro better for coding?
GPT-6 Sol scores higher on coding benchmarks: 60.1 versus 55.5 in the Noometry coding category.
Which has the bigger context window?
GPT-6 Sol does, with 1.05M tokens against 200K.
How many benchmarks do GPT-6 Sol and o3-pro share?
6 benchmarks have published results for both models. GPT-6 Sol has 45 scored results on Noometry and o3-pro has 12.