Compare Models
Select models (max 7)
Ember-1Grok 4.6
 |  |  |
|---|---|---|
| Legal Research BenchAgentic US legal research | 44.71%±3.46 | 48.08%±3.47 |
| Tax Agent BenchAgentic US corporate tax research | 31.08%±3.34 | 33.14%±3.40 |
| MedCodeMedical billing code support | N/A | 44.71%±2.26 |
| Terminal-Bench-ScienceExpert-authored scientific research workflows | 5.71%±2.79 | 11.43%±3.83 |
| Terminal-Bench 4.0Frontier-difficulty terminal tasks | 20.71%±3.64 | 17.17%±1.34 |
| Vibe Code Bench v1.1Building web apps from scratch | 83.87%±3.15 | 76.24%±3.82 |
Benchmarks
Legal Research Bench *
Ember-1
0.00%± 3.46
(84/84)Grok 4.6
0.00%± 3.47
(84/84)Tax Agent Bench *
Ember-1
0.00%± 3.34
(75/75)Grok 4.6
0.00%± 3.40
(75/75)MedCode *
Ember-1
N/AGrok 4.6
0.00%± 2.26
(107/107)Terminal-Bench-Science
Ember-1
0.00%± 2.79
(42/42)Grok 4.6
0.00%± 3.83
(42/42)Terminal-Bench 4.0
Ember-1
0.00%± 3.64
(54/54)Grok 4.6
0.00%± 1.34
(54/54)Vibe Code Bench v1.1 *
Ember-1
0.00%± 3.15
(118/118)Grok 4.6
0.00%± 3.82
(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.67.19%
Finance
31.08%
vs.56.14%
Healthcare
N/A
vs.65.62%
Math
61.00%
vs.51.00%
Science
31.76%
vs.38.09%
Academic
N/A
vs.92.05%
Education
N/A
vs.28.90%
Coding
50.30%
vs.49.55%
Cyber
69.52%
vs.67.68%
Social Mobility
66.17%
vs.66.85%
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.$2.00
Input Cache Read/ 1M Tokens
$0.30
vs.$0.50
Output Cost/ 1M Tokens
$15.00
vs.$6.00
Model Metadata
Basic information about each model.
| | |
|---|---|---|
| Model provider | Fireworks | SpaceXAI |
| Latency | N/A | N/A |
| Cost (In/Out) | $3 / $15 | $2 / $6 |
| Context Window | 1M | 500k |
| Max Output Token | 131k | 500k |
| Input Modality |