Model Comparator
Compare up to four models using the same criteria.
2 models compared
✓ Best published value among measured models. — Data unavailable. These metrics do not establish an overall ranking.
| Metrics | Add a model · 2/4 | ||
|---|---|---|---|
| Intelligence | Best: 61.8 | 56.9 | |
| Coding | — | 76.9 | |
| Agentic | — | 51 | |
| Cyber Index | — | 33.4% | |
| Speed | Best: 98.1 t/s | 35.6 t/s | |
| TTFT | Best: 26.7 s | 235 s | |
| Input · $ / 1M tokens | Best: $8 | $10×1.3 relative to the lowest price among the compared models | |
| Output · $ / 1M tokens | Best: $40 | $50×1.3 relative to the lowest price among the compared models | |
| Context window | 1M | 1M | |
| Reasoning | Yes | Yes | |
| Open weights | No | No | |
| Cost / task | $9.08×1.5 relative to the lowest price among the compared models | Best: $6.24 |
Intelligence
- Claude Fable 5.2 (High, Default Fallback)
- Best: 61.8
- GPT-6 Astra (Max)
- 56.9
Coding
- Claude Fable 5.2 (High, Default Fallback)
- —
- GPT-6 Astra (Max)
- 76.9
Agentic
- Claude Fable 5.2 (High, Default Fallback)
- —
- GPT-6 Astra (Max)
- 51
Cyber Index
- Claude Fable 5.2 (High, Default Fallback)
- —
- GPT-6 Astra (Max)
- 33.4%
Speed
- Claude Fable 5.2 (High, Default Fallback)
- Best: 98.1 t/s
- GPT-6 Astra (Max)
- 35.6 t/s
TTFT
- Claude Fable 5.2 (High, Default Fallback)
- Best: 26.7 s
- GPT-6 Astra (Max)
- 235 s
Input · $ / 1M tokens
- Claude Fable 5.2 (High, Default Fallback)
- Best: $8
- GPT-6 Astra (Max)
- $10×1.3 relative to the lowest price among the compared models
Output · $ / 1M tokens
- Claude Fable 5.2 (High, Default Fallback)
- Best: $40
- GPT-6 Astra (Max)
- $50×1.3 relative to the lowest price among the compared models
Context window
- Claude Fable 5.2 (High, Default Fallback)
- 1M
- GPT-6 Astra (Max)
- 1M
Reasoning
- Claude Fable 5.2 (High, Default Fallback)
- Yes
- GPT-6 Astra (Max)
- Yes
Open weights
- Claude Fable 5.2 (High, Default Fallback)
- No
- GPT-6 Astra (Max)
- No
Cost / task
- Claude Fable 5.2 (High, Default Fallback)
- $9.08×1.5 relative to the lowest price among the compared models
- GPT-6 Astra (Max)
- Best: $6.24
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.
- Claude Fable 5.2 (High, Default Fallback)61.8 · $9.08
- GPT-6 Astra (Max)56.9 · $6.24