Model Comparator
Compare up to four models using the same criteria.
2 models compared
- GPT-6 Astra (Xhigh)
OpenAI
✓ Best published value among measured models. — Data unavailable. These metrics do not establish an overall ranking.
| Metrics | GPT-6 Astra (Xhigh) OpenAI | Add a model · 2/4 | |
|---|---|---|---|
| Intelligence | 52.4 | Best: 53.4 | |
| Coding | 75.9 | Best: 81.6 | |
| Agentic | 50.2 | Best: 57.9 | |
| Cyber Index | — | 25.0% | |
| Speed | 43.3 t/s | Best: 71.1 t/s | |
| TTFT | Best: 174 s | 262 s | |
| Input · $ / 1M tokens | $10 | $10 | |
| Output · $ / 1M tokens | $50 | $50 | |
| Context window | 1M | 1M | |
| Reasoning | Yes | Yes | |
| Open weights | No | No | |
| Cost / task | Best: $2.31 | $7.63×3.3 relative to the lowest price among the compared models |
Intelligence
- GPT-6 Astra (Xhigh)
- 52.4
- Claude Fable 5.1 (Max, Default Fallback)
- Best: 53.4
Coding
- GPT-6 Astra (Xhigh)
- 75.9
- Claude Fable 5.1 (Max, Default Fallback)
- Best: 81.6
Agentic
- GPT-6 Astra (Xhigh)
- 50.2
- Claude Fable 5.1 (Max, Default Fallback)
- Best: 57.9
Cyber Index
- GPT-6 Astra (Xhigh)
- —
- Claude Fable 5.1 (Max, Default Fallback)
- 25.0%
Speed
- GPT-6 Astra (Xhigh)
- 43.3 t/s
- Claude Fable 5.1 (Max, Default Fallback)
- Best: 71.1 t/s
TTFT
- GPT-6 Astra (Xhigh)
- Best: 174 s
- Claude Fable 5.1 (Max, Default Fallback)
- 262 s
Input · $ / 1M tokens
- GPT-6 Astra (Xhigh)
- $10
- Claude Fable 5.1 (Max, Default Fallback)
- $10
Output · $ / 1M tokens
- GPT-6 Astra (Xhigh)
- $50
- Claude Fable 5.1 (Max, Default Fallback)
- $50
Context window
- GPT-6 Astra (Xhigh)
- 1M
- Claude Fable 5.1 (Max, Default Fallback)
- 1M
Reasoning
- GPT-6 Astra (Xhigh)
- Yes
- Claude Fable 5.1 (Max, Default Fallback)
- Yes
Open weights
- GPT-6 Astra (Xhigh)
- No
- Claude Fable 5.1 (Max, Default Fallback)
- No
Cost / task
- GPT-6 Astra (Xhigh)
- Best: $2.31
- Claude Fable 5.1 (Max, Default Fallback)
- $7.63×3.3 relative to the lowest price among the compared models
Each reasoning level remains a separate configuration.
Score and cost
Each line joins the reasoning levels of a compared model; the large point marks the configuration in the table. The top-right corner holds the best score for the lowest cost. Select another point to compare that level.
- GPT-6 Astra (Xhigh)52.4 · $2.31
- Claude Fable 5.1 (Max, Default Fallback)53.4 · $7.63