Compare Models
Select models (max 7)
GPT-6.1 TerraKimi K3.1 Pro
 |  |  |
|---|---|---|
| Vals IndexGDP-weighted benchmark | 60.17%±1.03 | 62.52%±1.14 |
| Legal Research BenchAgentic US legal research | 25.96%±3.05 | 37.50%±3.37 |
| Finance Agent v2.1Core financial analyst tasks | 55.96%±2.09 | 61.49%±2.10 |
| Tax Agent BenchAgentic US corporate tax research | 15.17%±2.43 | 24.87%±3.12 |
| Terminal-Bench-ScienceExpert-authored scientific research workflows | N/A | 31.43%±5.59 |
| Terminal-Bench 4.0Frontier-difficulty terminal tasks | 49.49%±1.82 | 63.64%±1.75 |
| Vibe Code Bench v1.1Building web apps from scratch | 84.00%±2.87 | 84.89%±2.95 |
Benchmarks
Vals Index *
GPT-6.1 Terra
0.00%± 1.03
(28/28)Kimi K3.1 Pro
0.00%± 1.14
(28/28)Legal Research Bench *
GPT-6.1 Terra
0.00%± 3.05
(86/86)Kimi K3.1 Pro
0.00%± 3.37
(86/86)Finance Agent v2.1 *
GPT-6.1 Terra
0.00%± 2.09
(32/32)Kimi K3.1 Pro
0.00%± 2.10
(32/32)Tax Agent Bench *
GPT-6.1 Terra
0.00%± 2.43
(77/77)Kimi K3.1 Pro
0.00%± 3.12
(77/77)Terminal-Bench-Science
GPT-6.1 Terra
N/AKimi K3.1 Pro
0.00%± 5.59
(43/43)Terminal-Bench 4.0
GPT-6.1 Terra
0.00%± 1.82
(56/56)Kimi K3.1 Pro
0.00%± 1.75
(56/56)Vibe Code Bench v1.1 *
GPT-6.1 Terra
0.00%± 2.87
(120/120)Kimi K3.1 Pro
0.00%± 2.95
(120/120)Overall performance
Performance on the Vals Index, a GDP-weighted aggregation of tasks across finance, coding, and law
•2026-10-26
Comparison by Industry
Model performance on different sections of the economy.
Legal
13.81%
vs.24.58%
Finance
48.15%
vs.52.12%
Math
N/A
vs.91.00%
Science
N/A
vs.44.37%
Coding
66.75%
vs.76.81%
Cost Analysis
Per task and per token model pricing.
Vals Index · USD
$2.925
$6.44
Cost / TestVals Index
$2.925
vs.$6.44
Input Cost/ 1M Tokens
$1.00
vs.$2.00
Input Cache Write/ 1M Tokens
$1.25
vs.N/A
Input Cache Read/ 1M Tokens
$0.05
vs.$0.20
Output Cost/ 1M Tokens
$5.00
vs.$10.00
Model Metadata
Basic information about each model.
| | |
|---|---|---|
| Model provider | OpenAI | Kimi |
| Latency | 2381.41s | 3816.45s |
| Cost (In/Out) | $1 / $5 | $2 / $10 |
| Context Window | 1M | 1M |
| Max Output Token | 128k | 1M |
| Input Modality |