Compare Models
Select models (max 7)
Ember-1Gemini 3.7 Flash
 |  |  |
|---|---|---|
| Legal Research BenchAgentic US legal research | 44.71%±3.46 | 34.62%±3.31 |
| Tax Agent BenchAgentic US corporate tax research | 31.08%±3.34 | 22.80%±3.03 |
| MedCodeMedical billing code support | N/A | 53.39%±2.12 |
| Terminal-Bench-ScienceExpert-authored scientific research workflows | 5.71%±2.79 | 7.14%±3.10 |
| Terminal-Bench 4.0Frontier-difficulty terminal tasks | 20.71%±3.64 | 12.12%±3.03 |
| Vibe Code Bench v1.1Building web apps from scratch | 83.87%±3.15 | 70.39%±4.84 |
Benchmarks
Legal Research Bench *
Ember-1
0.00%± 3.46
(84/84)Gemini 3.7 Flash
0.00%± 3.31
(84/84)Tax Agent Bench *
Ember-1
0.00%± 3.34
(75/75)Gemini 3.7 Flash
0.00%± 3.03
(75/75)MedCode *
Ember-1
N/AGemini 3.7 Flash
0.00%± 2.12
(107/107)Terminal-Bench-Science
Ember-1
0.00%± 2.79
(42/42)Gemini 3.7 Flash
0.00%± 3.10
(42/42)Terminal-Bench 4.0
Ember-1
0.00%± 3.64
(54/54)Gemini 3.7 Flash
0.00%± 3.03
(54/54)Vibe Code Bench v1.1 *
Ember-1
0.00%± 3.15
(118/118)Gemini 3.7 Flash
0.00%± 4.84
(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%
vs.60.94%
Finance
31.08%
vs.54.73%
Healthcare
N/A
vs.68.67%
Math
61.00%
vs.58.00%
Science
31.76%
vs.7.14%
Academic
N/A
vs.91.01%
Education
N/A
vs.49.23%
Coding
50.30%
vs.55.10%
Cyber
69.52%
vs.24.16%
Social Mobility
66.17%
vs.N/A
Cost Analysis
Per task and per token model pricing.
Vals Index · USD
N/A
N/A
Cost / TestVals Index
N/A
vs.N/A
Input Cost/ 1M Tokens
$3.00
vs.$1.50
Input Cache Read/ 1M Tokens
$0.30
vs.$0.15
Output Cost/ 1M Tokens
$15.00
vs.$7.50
Model Metadata
Basic information about each model.
| | |
|---|---|---|
| Model provider | Fireworks | Google |
| Latency | N/A | N/A |
| Cost (In/Out) | $3 / $15 | $1.5 / $7.5 |
| Context Window | 1M | 1M |
| Max Output Token | 131k | 66k |
| Input Modality |