Compare Models

Select models (max 7)

GPT OSS 120BGPT-6.1 Terra


Vals IndexGDP-weighted benchmark	N/A	60.17%±1.03
Legal Research BenchAgentic US legal research	N/A	25.96%±3.05
Finance Agent v2.1Core financial analyst tasks	N/A	55.96%±2.09
Tax Agent BenchAgentic US corporate tax research	N/A	15.17%±2.43
Terminal-Bench 4.0Frontier-difficulty terminal tasks	N/A	49.49%±1.82
Vibe Code Bench v1.1Building web apps from scratch	N/A	84.00%±2.87

Benchmarks

Vals Index *

GPT OSS 120B

N/A

GPT-6.1 Terra

0.00%± 1.03

(28/28)

Legal Research Bench *

GPT OSS 120B

N/A

GPT-6.1 Terra

0.00%± 3.05

(86/86)

Finance Agent v2.1 *

GPT OSS 120B

N/A

GPT-6.1 Terra

0.00%± 2.09

(32/32)

Tax Agent Bench *

GPT OSS 120B

N/A

GPT-6.1 Terra

0.00%± 2.43

(77/77)

Terminal-Bench 4.0

GPT OSS 120B

N/A

GPT-6.1 Terra

0.00%± 1.82

(56/56)

Vibe Code Bench v1.1 *

GPT OSS 120B

N/A

GPT-6.1 Terra

0.00%± 2.87

(120/120)

Overall performance

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

•2026-10-27

GPT OSS 120B GPT-6.1 Terra

Comparison by Industry

Model performance on different sections of the economy.

Legal

75.94%

vs.

13.81%

Finance

71.59%

vs.

48.15%

Academic

78.85%

vs.

N/A

Coding

58.42%

vs.

66.75%

Cost Analysis

Per task and per token model pricing.

Vals Index · USD

N/A

$2.925

Cost / TestVals Index

N/A

vs.

$2.925

Input Cost/ 1M Tokens

$0.15

vs.

$1.00

Input Cache Write/ 1M Tokens

N/A

vs.

$1.25

Input Cache Read/ 1M Tokens

$0.015

vs.

$0.05

Output Cost/ 1M Tokens

$0.60

vs.

$5.00

Model Metadata

Basic information about each model.


Model provider	Fireworks	OpenAI
Latency	N/A	2381.41s
Cost (In/Out)	$0.15 / $0.6	$1 / $5
Context Window	128k	1M
Max Output Token	33k	128k
Input Modality