DeepSeek R1
Performance overview across all HAL benchmarks
9
Benchmarks
10
Agents
2
Pareto Optimal Benchmarks
Token Pricing
$0.2
Input Tokens
per 1M tokens
$0.8
Output Tokens
per 1M tokens
Benchmark Performance
On the Pareto Frontier? indicates whether this model achieved a Pareto-optimal trade-off between accuracy and cost on that benchmark. Models on the Pareto frontier represent the current state-of-the-art efficiency for their performance level.
| Benchmark | Agent | Accuracy | Cost | On the Pareto Frontier? |
|---|---|---|---|---|
|
Assistantbench
|
Browser-Use | 8.75% | $6.62 | No |
|
Corebench Hard
|
CORE-Agent | 8.89% | $9.05 | No |
|
Corebench Hard
|
HAL Generalist Agent | 8.89% | $2.83 | No |
|
Gaia
|
HAL Generalist Agent | 30.30% | $5.47 | No |
|
Gaia
|
HF Open Deep Research | 24.85% | $11.10 | No |
|
Online Mind2Web
|
Browser-Use | 25.33% | $21.26 | No |
|
Scicode
|
Scicode Tool Calling Agent | 0.00% | $20.98 | No |
|
Scicode
|
Scicode Zero Shot Agent | 0.00% | $0.80 | No |
|
Scienceagentbench
|
SAB Self-Debug | 23.53% | $1.87 | Yes |
|
Swebench Verified Mini
|
HAL Generalist Agent | 6.00% | $10.32 | No |
|
Swebench Verified Mini
|
SWE-Agent | 0.00% | $0.41 | Yes |
|
Taubench Airline
|
TAU-bench Few Shot | 36.00% | $5.66 | No |
|
Taubench Airline
|
HAL Generalist Agent | 10.00% | $2.91 | No |
|
Usaco
|
USACO Episodic + Semantic | 38.11% | $8.18 | No |