GPT-6 Luna
No video
Key numbers
- Panel score
- –not scored
- Cost
- $0.010API list price
- Wall time
- 1.7 min
- Model time
- 1.7 min100% of wall time
- tok/s
- 49.4
- Tokens
- 555kOutput: 5.0k
- Cache hit
- 89%
- API calls
- 11
- Tool calls
- 10
- Renderer
- –
- H1–H6
- No video
How the run ended
Gave up. It built the project in the wrong directory, started the render in the background and ended its turn while the render was still “pending”. Not a single frame was rendered, so there is no video.
Time and speed
Wall time includes rendering and encoding. Model time is the sum of all model calls.
- Model generating
- Tools & waiting
| Wall time | 1.7 min |
|---|---|
| Model time | 1.7 min |
| Tools & waiting | 0.0 min |
| Model share of wall time | 100% |
| tok/s | 49.4 |
| Model calls | 11 |
Tokens and cost
Tokens summed over every model response. Tokens multiplied by the provider’s price.
| Uncached input | 59,140 |
|---|---|
| Cache read | 491,264 |
| Cache write | 0 |
| Output | 4,968of which 443 reasoning |
| Total | 555,372 |
| Cache-hit ratio | 89.3% |
| Cost | $0.010API list price |
Tools used
Tool calls by name, as the harness logged them. Names differ between harnesses.
Rendering
| Renderer | – |
|---|---|
| Final render | – |
| Per frame | – |
Hard requirements H1–H6
No video was delivered, so there was nothing to check.
From the agent’s report
Short, verbatim quotes from the REPORT.md the agent wrote itself.
Final ffprobe JSON: pending render and encode.