hurdleBook a walkthrough

Nova 2 Lite

Nova 2 Lite is a model from Amazon, run through Amazon Bedrock. It places 10= of 14 on the Hurdle Index, and falls below the 90% bar on pay-gap reasoning.

Lab
Amazon
Called as
global.amazon.nova-2-lite-v1:0
Price, per million tokens
$0.3 in, $1.25 out
Tokens per task
1,486 read, 187 written
Output limit
32,000 tokens
Run
23 October 2026, 120 attempts

Hurdle Index

2.2%1.4% to 3.2%. Place 10= of 14.

Cost per task

$0.00073rd cheapest of 14. List price of the tokens used.

Time per task

2 sThe fastest of 14. Wall-clock time of each call.

On each benchmark

BenchmarkMean, 95% intervalPlaceEvery runBest of 3Cost per taskCut offBar
Pay-gap reasoning2.2% 1.4% to 3.2%10= of 140.0%5.9%$0.0007noneBelow

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 scope94.2%
Mean hourly gap99.2%
Median hourly gap99.2%
Variable pay100.0%
Quartile pay bands100.0%
Gaps by category98.6%
Joint assessment trigger93.3%

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