Chess with an engine
loads medium
Tech. quality98
UX66
Time2 min 34 s
Cost$0.31
Compare →
GPT-5.6 Sol
Loads without errors5/5#1 of 26
Tech. quality98/100#3 of 26
UX78/100#23 of 26
Total cost$1.69
Average time2 min 30 s#11 of 26
Total tokens1,134,216
API price: $4 / $20 per 1M input / output tokens · as of 15/10/2026 source ↗
What is GPT-5.6 Sol good for?
The flagship of the GPT-5.6 generation, for complex professional work.
Description based on the maker · source ↗
- Maker
- OpenAI
- Released
- 09/07/2026
- Model weights
- closed, the model is available through the API only
- Reasoning levels
- low medium high
How did GPT-5.6 Sol do in the AI Lab tests?
- 5 of 5 outputs load without errors.
- Its best technical result was on the “New York & Central Park map” prompt (99/100).
- It implemented the chess rules flawlessly – passing the objective perft test on all 6 positions.
- Average time per prompt 2 min 30 s#11 of 26
- Average cost per prompt $0.34#20 of 26
- Technical quality 98/100#3 of 26
- Automatic UX rating 78/100#23 of 26
Outputs
All outputs of GPT-5.6 Sol on the 5 prompts every other model got as well.
Solar System
loads medium
Tech. quality97
UX80
Time2 min 05 s
Cost$0.33
Compare →
GTA-style game
loads medium
Tech. quality98
UX100
Time2 min 29 s
Cost$0.34
Compare →
Monitor test
loads medium
Tech. quality98
UX81
Time2 min 35 s
Cost$0.36
Compare →
New York & Central Park map
loads medium
Tech. quality99
UX62
Time2 min 46 s
Cost$0.34
Compare →
Cost = tokens priced with the API price list valid on the date shown next to the cost (prices change). ≈ = estimate (only the total token count is known), no ≈ = exact from input / output tokens. “Loads” = the page opens without errors; technical quality also checks behaviour during use – judge the quality in the viewer.