DeepSeek R1
163,840 token context with transparent <think> delimiters showing reasoning over retrieved documents. MIT license enables fine-tuning on domain-specific retrieval tasks and full model customization.
Model Information
- Provider
- DeepSeek
- License
- Open Source
- Input Price per 1M
- $0.30
- Output Price per 1M
- $1.20
- Context Window
- 164K
- Release Date
- 2025-01-20
- Model Name
- deepseek-r1
- Total Evaluations
- 900
Performance Record
Wins170 (18.9%)
Losses617 (68.6%)
Ties113 (12.6%)
Wins
Losses
Ties
Performance Overview
ELO ratings by dataset
DeepSeek R1's ELO performance varies across different benchmark datasets, showing its strengths in specific domains.
DeepSeek R1 - ELO by Dataset
Detailed Metrics
Dataset breakdown
Performance metrics across different benchmark datasets, including accuracy and latency percentiles.
SciFact
ELO 143424.0% WR72W-161L-67T
Quality Metrics
- Correctness
- 5.00
- Faithfulness
- 5.00
- Grounding
- 4.97
- Relevance
- 5.00
- Completeness
- 4.87
- Overall
- 4.97
Latency Distribution
- Mean
- 14826ms
- Min
- 7765ms
- Max
- 33129ms
PG
ELO 127817.3% WR52W-239L-9T
Quality Metrics
- Correctness
- 4.90
- Faithfulness
- 4.90
- Grounding
- 4.87
- Relevance
- 4.93
- Completeness
- 4.60
- Overall
- 4.84
Latency Distribution
- Mean
- 23334ms
- Min
- 12280ms
- Max
- 85633ms
MSMARCO
ELO 115315.3% WR46W-217L-37T
Quality Metrics
- Correctness
- 4.67
- Faithfulness
- 4.70
- Grounding
- 4.67
- Relevance
- 4.90
- Completeness
- 4.60
- Overall
- 4.71
Latency Distribution
- Mean
- 16654ms
- Min
- 9675ms
- Max
- 31255ms
Compare Models
See how it stacks up
Compare DeepSeek R1 with other top llms to understand the differences in performance, accuracy, and latency.