Compare Models

Select models (max 7)

Mercury 3Drex Max


Vals IndexGDP-weighted benchmark	43.66%±1.23	N/A
Legal Research BenchAgentic US legal research	28.85%±3.15	N/A
Finance Agent v2.1Core financial analyst tasks	54.71%±1.99	N/A
Tax Agent BenchAgentic US corporate tax research	18.17%±2.54	N/A
Code Migration v1.1Rewriting programs in new languages	39.26%±3.17	N/A
Terminal-Bench 4.0Frontier-difficulty terminal tasks	3.03%±0.00	N/A
Vibe Code Bench v1.1Building web apps from scratch	60.93%±5.38	N/A

Benchmarks

Vals Index *

Mercury 3

0.00%± 1.23

(26/26)

Drex Max

N/A

Legal Research Bench *

Mercury 3

0.00%± 3.15

(84/84)

Drex Max

N/A

Finance Agent v2.1 *

Mercury 3

0.00%± 1.99

(30/30)

Drex Max

N/A

Tax Agent Bench *

Mercury 3

0.00%± 2.54

(75/75)

Drex Max

N/A

Code Migration v1.1 *

Mercury 3

0.00%± 3.17

(28/28)

Drex Max

N/A

Terminal-Bench 4.0

Mercury 3

0.00%± 0.00

(54/54)

Drex Max

N/A

Vibe Code Bench v1.1 *

Mercury 3

0.00%± 5.38

(118/118)

Drex Max

N/A

Overall performance

Performance on the Vals Index, a GDP-weighted aggregation of tasks across finance, coding, and law

•2026-10-22

Mercury 3 Drex Max

Comparison by Industry

Model performance on different sections of the economy.

Legal

16.92%

vs.

N/A

Finance

43.59%

vs.

99.18%

Coding

34.41%

vs.

N/A

Cost Analysis

Per task and per token model pricing.

Vals Index · USD

$0.478

N/A

Cost / TestVals Index

$0.478

vs.

N/A

Input Cost/ 1M Tokens

$0.10

vs.

$0.06

Input Cache Read/ 1M Tokens

$0.01

vs.

N/A

Output Cost/ 1M Tokens

$0.35

vs.

$0.00

Model Metadata

Basic information about each model.


Model provider	Inception	Decision
Latency	1325.89s	N/A
Cost (In/Out)	$0.1 / $0.35	$0.06 / $0
Context Window	1M	262k
Max Output Token	131k	0
Input Modality