Capability breakdown
Intelligence over time
Provider & region options
Fastest loop: Overshoot · US East (Virginia) · 2.6 s end to end.
| Overshoot | US East (Virginia) | 248 tok/s | 46 ms | 2.6 s | $5.00 | – |
| Overshoot | US West (Oregon) | 248 tok/s | 54 ms | 2.6 s | $5.00 | – |
| Overshoot | EU West (Ireland) | 248 tok/s | 55 ms | 2.6 s | $5.00 | – |
| Overshoot | EU Central (Frankfurt) | 248 tok/s | 64 ms | 2.7 s | $5.00 | – |
| Overshoot | Asia Pacific (Tokyo) | 248 tok/s | 81 ms | 2.7 s | $5.00 | – |
| Overshoot | Asia Pacific (Mumbai) | 248 tok/s | 97 ms | 2.7 s | $5.00 | – |
| Overshoot | Middle East (Dubai) | 248 tok/s | 98 ms | 2.7 s | $5.00 | – |
| Overshoot | South America (São Paulo) | 248 tok/s | 107 ms | 2.7 s | $5.00 | – |
| OpenAI API | US East (Virginia) | 245 tok/s | 60 ms | 3.0 s | $4.78 | – |
| OpenAI API | US West (Oregon) | 245 tok/s | 72 ms | 3.0 s | $4.78 | – |
| OpenAI API | EU West (Ireland) | 245 tok/s | 72 ms | 3.0 s | $4.78 | – |
| OpenAI API | Asia Pacific (Tokyo) | 245 tok/s | 95 ms | 3.0 s | $4.78 | – |
Sample outputs
Illustrative samples shared across models, not verbatim output from GPT-5.4 mini.
Scene description
“Describe what's happening in this camera frame.”
A forklift is reversing toward loading bay 3 while a worker in a hi-vis vest signals from the left. Two pallets remain unwrapped near the dock edge.
OCR + extraction
“Read the shipping label and return structured JSON.”
{ "tracking": "1Z A24 9W7 03 8421 990 4", "carrier": "UPS", "weight_kg": 12.4, "dest": "Portland, OR 97204" }
Grounding
“Point to every person not wearing a hard hat.”
2 detections, [x:0.41, y:0.62, w:0.08, h:0.19] conf 0.94 · [x:0.77, y:0.55, w:0.07, h:0.21] conf 0.88.
Related models
Where it ranks
- #5Qwen3.6 35B A3B80.9
- #6Qwen3.6 27B77.0
- #7GPT-5.4 mini75.5
- #8Gemini 3 Flash75.3
- #9Claude Haiku 4.574.2
- #10Holo3 35B A3B74.0