DeepSeekopen weightsReasoning
DeepSeek R1
The release that reset expectations for open reasoning models.
Jan 20, 2025
$0.55 / $2.19
$0.96
128K
Benchmark scores
| Benchmark | Score | Δ vs prior | Rank (current) | Configuration | Source |
|---|---|---|---|---|---|
SWE-bench Verified | 49.2% | #9 of 9 | leaderboard | benchlm.ai ↗ | |
τ²-bench (Telecom) | 36.5% | #10 of 10 | leaderboard | benchlm.ai ↗ | |
Artificial Analysis Intelligence Index | 20.1 | #10 of 11 | leaderboard | benchlm.ai ↗ |