AA-Briefcase
1.1 / combined Elo ↗- DeepSeek R1 (Jan 2025):
- GPT-6 Astra:
Compare models
Find the right model, side by side.
Updated: Data as of:
First model
Second model
Model specifications
| Specifications |  DeepSeek R1 (Jan 2025)DeepSeek |  GPT-6 AstraOpenAI |
|---|---|---|
| Provider | Not reported | |
| Context sizetokens | 128,000 | 1,000,000 |
| Cutoff date | Not reported | 2026-04-30 |
| Input costUSD / 1M tokens | Not reported | $10.00 |
| Output costUSD / 1M tokens | Not reported | $50.00 |
| Max outputtokens | Not reported | 128,000 |
| LatencyTTFT · seconds | Not reported | 365.127 |
| Speedtokens / sec | Not reported | 70.564 |
Benchmark performance
6 shared benchmark comparisons. Versions and setups matched.
DeepSeek R1 (Jan 2025)GPT-6 Astra
AutomationBench-AA
1.0.6 / AA private 657 ↗Tools enabled- DeepSeek R1 (Jan 2025):
- GPT-6 Astra:
- DeepSeek R1 (Jan 2025):
- GPT-6 Astra:
GDPval-AA
2.1 ↗- DeepSeek R1 (Jan 2025):
- GPT-6 Astra:
GPQA Diamond
Diamond / Independent evaluation ↗- DeepSeek R1 (Jan 2025):
- GPT-6 Astra:
Terminal-Bench
4.0 / mini-swe-agent ↗mini-swe-agent- DeepSeek R1 (Jan 2025):
- GPT-6 Astra:
