Model Comparator
Compare up to four models using the same criteria.
2 models compared
- GPT-6 Astra (Medium)
OpenAI
- Claude Opus 5 (Max)
Anthropic
✓ Best published value among measured models. — Data unavailable. These metrics do not establish an overall ranking.
| Metrics | GPT-6 Astra (Medium) OpenAI | Claude Opus 5 (Max) Anthropic | Add a model · 2/4 |
|---|---|---|---|
| Intelligence | 49.6 | Best: 50.8 | |
| Coding | 76.7 | Best: 78 | |
| Agentic | 46 | Best: 56.5 | |
| Speed | 43.8 t/s | Best: 54.7 t/s | |
| TTFT | Best: 6.3 s | 83.4 s | |
| Input · $ / 1M tokens | $10×2 relative to the lowest price among the compared models | Best: $5 | |
| Output · $ / 1M tokens | $50×2 relative to the lowest price among the compared models | Best: $25 | |
| Context window | 1M | 1M | |
| Reasoning | Yes | Yes | |
| Open weights | No | No | |
| Cost / task | Best: $1.54 | $5.86×3.8 relative to the lowest price among the compared models |
Intelligence
- GPT-6 Astra (Medium)
- 49.6
- Claude Opus 5 (Max)
- Best: 50.8
Coding
- GPT-6 Astra (Medium)
- 76.7
- Claude Opus 5 (Max)
- Best: 78
Agentic
- GPT-6 Astra (Medium)
- 46
- Claude Opus 5 (Max)
- Best: 56.5
Speed
- GPT-6 Astra (Medium)
- 43.8 t/s
- Claude Opus 5 (Max)
- Best: 54.7 t/s
TTFT
- GPT-6 Astra (Medium)
- Best: 6.3 s
- Claude Opus 5 (Max)
- 83.4 s
Input · $ / 1M tokens
- GPT-6 Astra (Medium)
- $10×2 relative to the lowest price among the compared models
- Claude Opus 5 (Max)
- Best: $5
Output · $ / 1M tokens
- GPT-6 Astra (Medium)
- $50×2 relative to the lowest price among the compared models
- Claude Opus 5 (Max)
- Best: $25
Context window
- GPT-6 Astra (Medium)
- 1M
- Claude Opus 5 (Max)
- 1M
Reasoning
- GPT-6 Astra (Medium)
- Yes
- Claude Opus 5 (Max)
- Yes
Open weights
- GPT-6 Astra (Medium)
- No
- Claude Opus 5 (Max)
- No
Cost / task
- GPT-6 Astra (Medium)
- Best: $1.54
- Claude Opus 5 (Max)
- $5.86×3.8 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 (Medium)49.6 · $1.54
- Claude Opus 5 (Max)50.8 · $5.86