Compare Models

Select models (max 7)
GPT 5.1 Codex MaxQwen 4 Max
Benchmarks

Vals Index *

GPT 5.1 Codex Max
N/A
Qwen 4 Max
0.00%± 1.01
(38/38)

Legal Research Bench *

GPT 5.1 Codex Max
N/A
Qwen 4 Max
0.00%± 3.42
(95/95)

Finance Agent v2.1 *

GPT 5.1 Codex Max
N/A
Qwen 4 Max
0.00%± 2.02
(41/41)

Tax Agent Bench *

GPT 5.1 Codex Max
N/A
Qwen 4 Max
0.00%± 3.54
(86/86)

Terminal-Bench 4.0

GPT 5.1 Codex Max
N/A
Qwen 4 Max
0.00%± 0.88
(65/65)

Vibe Code Bench v1.1 *

GPT 5.1 Codex Max
0.00%± 3.84
(129/129)
Qwen 4 Max
0.00%± 2.27
(129/129)

Overall performance

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

2026-11-15

Comparison by Industry

Model performance on different sections of the economy.

Legal
N/A
31.30%
Finance
N/A
59.29%
Coding
52.86%
67.57%

Cost Analysis

Per task and per token model pricing.

Vals Index · USD
N/A
$9.33
Cost / TestVals Index
N/A
$9.33
Input Cost/ 1M Tokens
$1.25
$1.50
Input Cache Read/ 1M Tokens
$0.125
$0.075
Output Cost/ 1M Tokens
$10.00
$4.50

Model Metadata

Basic information about each model.

Model provider
OpenAIOpenAI
AlibabaAlibaba
LatencyN/A3879.45s
Cost (In/Out)$1.25 / $10$1.5 / $4.5
Context Window400k1M
Max Output Token128k262k
Input Modality