codex-gpt-5.6-luna
Blind track
2.45/4
Overall
13
Families scored
13
Seeds
0
Infra errors
±0.42
Std error
Per-task family scores
Failure-level histogram
L0 (failed L1)1
L1 structural5
L2 geometric0
L3 physical constraints1
L4 dfm6
infra error0
Efficiency & cost
| Metric | Value | Source |
|---|---|---|
| Agent calls | 1.00 | runtime.agent_call_count |
| Wall time (s) | 90.54 | runtime.wall_time_s |
| Cost (USD) | not available | opaque / not reported |
| Total tokens | 32848.38 (est.) | local_log_tokens |
Perception track
2.45/4
Overall
13
Families scored
13
Seeds
0
Infra errors
±0.42
Std error
Per-task family scores
Failure-level histogram
L0 (failed L1)1
L1 structural5
L2 geometric0
L3 physical constraints1
L4 dfm6
infra error0
Efficiency & cost
| Metric | Value | Source |
|---|---|---|
| Agent calls | 2.46 | runtime.agent_call_count |
| Wall time (s) | 148.97 | runtime.wall_time_s |
| Cost (USD) | not available | opaque / not reported |
| Total tokens | 79326.08 (est.) | local_log_tokens |
Perception summary
| Observations | 19 |
| Compiled | 16 |
| Render artifacts | 48 |
| Section artifacts | 96 |
| Warnings | 14 |
| Mean iterations | 2.46 |