DeepSeek R1

DeepSeek R1 is a model from DeepSeek, run through Amazon Bedrock. It places 3= of 14 on the Hurdle Index, and falls below the 90% bar on pay-gap reasoning.

Lab: DeepSeek
Called as: us.deepseek.r1-v1:0
Price, per million tokens: $1.35 in, $5.4 out
Tokens per task: 1,479 read, 12,266 written
Output limit: 32,000 tokens
Run: 23 October 2026, 120 attempts

Hurdle Index

82.8%76.4% to 88.2%. Place 3= of 14.

Cost per task

$0.06812th cheapest of 14. List price of the tokens used.

Time per task

77 s10th fastest of 14. Wall-clock time of each call.

On each benchmark

Benchmark	Mean, 95% interval	Place	Every run	Best of 3	Cost per task	Cut off	Bar
Pay-gap reasoning	82.8% 76.4% to 88.2%	3= of 14	68.8%	94.3%	$0.068	none	Below

Every attempt

Pay-gap reasoning: 40 tasks, three attempts each, one cell per attempt. White is a perfect answer, black is none of it right.

Attempt 1

Attempt 2

Attempt 3

Where it misses

The share of each kind of rubric line it got wrong, across every attempt.

Who is in scope22.5%

Mean hourly gap18.3%

Median hourly gap13.3%

Variable pay11.4%

Quartile pay bands33.3%

Gaps by category20.3%

Joint assessment trigger7.5%

Next to it on the index

Is it right for your job?

A public benchmark says how it does on someone else’s work. Hurdle builds one from yours.

Book a walkthrough