Compare Models

Select models (max 7)
Gemini 3.5 FlashMercury 2.5
Benchmarks

Legal Research Bench *

Gemini 3.5 Flash
0.00%± 3.21
(84/84)
Mercury 2.5
0.00%± 1.41
(84/84)

Tax Agent Bench *

Gemini 3.5 Flash
0.00%± 2.96
(75/75)
Mercury 2.5
0.00%± 1.02
(75/75)

MedCode *

Gemini 3.5 Flash
0.00%± 2.11
(107/107)
Mercury 2.5
0.00%± 1.95
(107/107)

Terminal-Bench-Science

Gemini 3.5 Flash
0.00%± 2.79
(42/42)
Mercury 2.5
0.00%± 0.00
(42/42)

Terminal-Bench 4.0

Gemini 3.5 Flash
0.00%± 1.51
(54/54)
Mercury 2.5
0.00%± 0.00
(54/54)

Vibe Code Bench v1.1 *

Gemini 3.5 Flash
0.00%± 4.73
(118/118)
Mercury 2.5
0.00%± 1.41
(118/118)

Overall performance

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

2026-10-22

Comparison by Industry

Model performance on different sections of the economy.

Legal
57.19%
43.69%
Finance
54.71%
2.49%
Healthcare
66.20%
43.21%
Math
31.00%
3.00%
Science
5.71%
0.00%
Academic
90.15%
N/A
Education
49.88%
N/A
Coding
45.65%
6.05%
Cyber
N/A
45.48%
Social Mobility
59.47%
45.26%

Cost Analysis

Per task and per token model pricing.

Vals Index · USD
N/A
N/A
Cost / TestVals Index
N/A
N/A
Input Cost/ 1M Tokens
$1.50
$0.20
Input Cache Read/ 1M Tokens
$0.15
$0.02
Output Cost/ 1M Tokens
$9.00
$0.75

Model Metadata

Basic information about each model.

Model provider
GoogleGoogle
InceptionInception
LatencyN/AN/A
Cost (In/Out)$1.5 / $9$0.2 / $0.75
Context Window1M260k
Max Output Token66k66k
Input Modality