Compare Models

Select models (max 7)
Ember-1Step 5 Preview
Benchmarks

Legal Research Bench *

Ember-1
0.00%± 3.46
(84/84)
Step 5 Preview
0.00%± 3.41
(84/84)

Finance Agent v2.1 *

Ember-1
N/A
Step 5 Preview
0.00%± 2.05
(30/30)

Tax Agent Bench *

Ember-1
0.00%± 3.34
(75/75)
Step 5 Preview
0.00%± 3.11
(75/75)

Terminal-Bench-Science

Ember-1
0.00%± 2.79
(42/42)
Step 5 Preview
0.00%± 2.01
(42/42)

Code Migration v1.1 *

Ember-1
N/A
Step 5 Preview
0.00%± 3.43
(28/28)

Terminal-Bench 4.0

Ember-1
0.00%± 3.64
(54/54)
Step 5 Preview
0.00%± 2.62
(54/54)

Vibe Code Bench v1.1 *

Ember-1
0.00%± 3.15
(118/118)
Step 5 Preview
0.00%± 4.27
(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
44.71%
40.38%
Finance
31.08%
51.91%
Math
61.00%
42.00%
Science
31.76%
29.58%
Coding
50.30%
45.62%
Cyber
69.52%
0.38%
Social Mobility
66.17%
58.12%

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
$3.00
$1.00
Input Cache Read/ 1M Tokens
$0.30
$0.05
Output Cost/ 1M Tokens
$15.00
$2.70

Model Metadata

Basic information about each model.

Model provider
FireworksFireworks
StepFunStepfun
LatencyN/AN/A
Cost (In/Out)$3 / $15$1 / $2.7
Context Window1M1M
Max Output Token131k1M
Input Modality