Rank #1 / 9
GPT-6 Astra
GPT-6 Astra is OpenAI's GPT-6 model (proprietary). It is ranked 1 of 9 models on the Visual Intelligence Index.
- OpenAI
- Proprietary
- GPT-6
- Audio
- Structured output
- Tool calling
- Streaming
- Batch API
Comparison Summary
GPT-6 Astra ranks 1 of 9 on the perception index. Immediately behind is Gemini 3.8 Flash. List price is $10.00 per million input tokens and $50.00 per million output. 3 of 5 priced models cost less to prompt. The context window is 1.05M. Every score is from our own evaluation runs; list prices are as published by the provider. Strongest capability in this set is Spatial Reasoning (85%). Weakest is Action / Event Understanding (79%).
- Visual Intelligence
- 82.2%
- Availability
- Proprietary
- Input / 1M tokens
- $10.00
- Output / 1M tokens
- $50.00
- Long context input / 1M
- $20.00
- Long context output / 1M
- $75.00
- Context Window
- 1.05M
- Parameters
- —
All benchmark scores
| Benchmark | Metric | Score | Coverage | Setting |
|---|---|---|---|---|
| Video-MME v2 | Accuracy, no subtitles | 73.4% | Full | 1 fps, 1500-frame cap (2 videos thinned) |
| LVBench | Test accuracy | 81.6% | Full | 1 fps, 1500-frame cap (103 videos thinned) |
| Perception Test | Overall accuracy | 92.5% | Full | 1 fps |
| NExT-QA | Accuracy (hard split) | 90.7% | Full | 1 fps |
| Q-Bench Video | Overall accuracy | 68.3% | Full | 1 fps |
| EgoSchema | Accuracy (fullset) | 83.4% | Full | 1 fps |
| UCF101-AD | Accuracy | 61.4% | Full | 1 fps |
Benchmark Scores
Compare reported model scores across each available benchmark or capability index.
9 of 9 models
Display
Capabilities Index Scores
Compare reported model scores across each available benchmark or capability index.
9 of 9 models
Display
Usability
3.5/ 5
What it's like to build against this model, scored out of five from the developer-facing capabilities in the dataset.
- Reachable1.0
There is an endpoint you can call without hosting anything.
- First-party API — supported
- Third-party API — supported
- Portable0.0
You can run it yourself, and are not tied to one vendor.
- Open weights — not supported
- Self-hostable — not supported
- Multimodal input0.5
It takes the footage directly, rather than frames you extracted.
- Video ingestion — not supported
- Audio — supported
- Programmable1.0
Output you can parse, and tools it can call on its own.
- Structured output — supported
- Tool calling — supported
- Operable1.0
Usable interactively and in bulk, not only one call at a time.
- Streaming — supported
- Batch API — supported
Other OpenAI models
Other models from the OpenAI family.
| Date | Model | Visual Intelligence |
|---|---|---|
| Sep 3, 2026 | GPT-6 Astra | 82.2% |