Llama 4 Maverick
Llama 4 Maverick is a model from Meta, run through Amazon Bedrock. It places 9 of 14 on the Hurdle Index, and falls below the 90% bar on pay-gap reasoning.
- Lab
- Meta
- Called as
us.meta.llama4-maverick-17b-instruct-v1:0- Price, per million tokens
- $0.24 in, $0.97 out
- Tokens per task
- 1,475 read, 2,983 written
- Output limit
- 32,000 tokens
- Run
- 23 October 2026, 120 attempts
Hurdle Index
10.5%7.2% to 14.4%. Place 9 of 14.Cost per task
$0.00326th cheapest of 14. List price of the tokens used.Time per task
13 s5th 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 | 10.5% 7.2% to 14.4% | 9 of 14 | 3.9% | 18.6% | $0.0032 | 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.
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