Compare Models

Select models (max 7)
Ember-1Gemini 4 Neon
Benchmarks

Vals Index *

Ember-1
N/A
Gemini 4 Neon
0.00%± 0.94
(42/42)

Legal Research Bench *

Ember-1
0.00%± 3.46
(99/99)
Gemini 4 Neon
0.00%± 3.45
(99/99)

Finance Agent v2.1 *

Ember-1
N/A
Gemini 4 Neon
0.00%± 1.94
(45/45)

Tax Agent Bench *

Ember-1
0.00%± 3.34
(90/90)
Gemini 4 Neon
0.00%± 3.59
(90/90)

Terminal-Bench-Science

Ember-1
0.00%± 2.79
(48/48)
Gemini 4 Neon
0.00%± 5.82
(48/48)

Terminal-Bench 4.0

Ember-1
0.00%± 3.64
(69/69)
Gemini 4 Neon
0.00%± 2.02
(69/69)

Vibe Code Bench v1.1 *

Ember-1
0.00%± 3.15
(133/133)
Gemini 4 Neon
0.00%± 1.17
(133/133)

Overall performance

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

2026-11-18

Comparison by Industry

Model performance on different sections of the economy.

Legal
44.71%
37.92%
Finance
31.08%
66.64%
Math
61.00%
N/A
Science
31.76%
62.63%
Education
86.38%
N/A
Coding
50.30%
77.66%
Cyber
69.52%
N/A
Social Mobility
66.17%
N/A

Cost Analysis

Per task and per token model pricing.

Vals Index · USD
N/A
$7.405
Cost / TestVals Index
N/A
$7.405
Input Cost/ 1M Tokens
$3.00
$3.00
Input Cache Read/ 1M Tokens
$0.30
$0.15
Output Cost/ 1M Tokens
$15.00
$15.00

Model Metadata

Basic information about each model.

Model provider
FireworksFireworks
GoogleGoogle
LatencyN/A1884.68s
Cost (In/Out)$3 / $15$3 / $15
Context Window1M1M
Max Output Token131k1M
Input Modality