Coding · Benchmark profile
Cognition's 150-task Extended subset of the FrontierCode 1.1 software-engineering benchmark.
Data verified 21 Jul 2026 · Methodology 1.6.0
Benchmark score on FrontierCode 1.1 Extended
GPT-5.6 Sol leads at 60.6%, followed by GPT-5.6 Terra (55.8%) and GPT-5.6 Luna (55.1%).
Visual analysis
Switch between model placement, score distribution and descriptive provider averages. Every view uses the same sourced leaderboard.
3 ranked models · higher is better
| Model | Rank | Provider | Score |
|---|---|---|---|
| GPT-5.6 Sol | #1 | OpenAI | 60.6% |
| GPT-5.6 Terra | #2 | OpenAI | 55.8% |
| GPT-5.6 Luna | #3 | OpenAI | 55.1% |
One best score per model · higher is better
| Rank | Model | Provider | License | Evidence use | Score |
|---|---|---|---|---|---|
| #1 | GPT-5.6 Sol gpt-5.6-sol | OpenAI | closed | Reference only | 60.6% |
| #2 | GPT-5.6 Terra gpt-5.6-terra | OpenAI | closed | Estimated reference | 55.8% |
| #3 | GPT-5.6 Luna gpt-5.6-luna | OpenAI | closed | Estimated reference | 55.1% |
The top of this snapshot is led by GPT-5.6 Sol at 60.6%; third place is 5.5 points behind. The top-3 spread is 5.5 points.
About FrontierCode 1.1 Extended
Cognition's 150-task Extended subset of the FrontierCode 1.1 software-engineering benchmark. Results stay tied to the exact model variant and evaluation system. Multiple systems for the same model use the best published score on this page; overall Lumina scoring uses the median of ranking-eligible rows.
Open benchmark source ↗FAQ
Cognition's 150-task Extended subset of the FrontierCode 1.1 software-engineering benchmark.
GPT-5.6 Sol by OpenAI currently leads with 60.6%.
3 models in the LuminaBench cohort have a qualifying score on this benchmark.
No. This benchmark is display-only and does not enter the overall Lumina composite.
Related
