Compare Models

Select models (max 7)
Qwen 3 MaxGPT-6.2 Astra
Benchmarks

Vals Index *

Qwen 3 Max
N/A
GPT-6.2 Astra
0.00%± 0.94
(41/41)

Legal Research Bench *

Qwen 3 Max
N/A
GPT-6.2 Astra
0.00%± 3.44
(98/98)

Finance Agent v2.1 *

Qwen 3 Max
N/A
GPT-6.2 Astra
0.00%± 2.12
(44/44)

Tax Agent Bench *

Qwen 3 Max
N/A
GPT-6.2 Astra
0.00%± 2.79
(89/89)

Terminal-Bench-Science

Qwen 3 Max
N/A
GPT-6.2 Astra
0.00%± 5.44
(47/47)

Terminal-Bench 4.0

Qwen 3 Max
N/A
GPT-6.2 Astra
0.00%± 1.34
(68/68)

Vibe Code Bench v1.1 *

Qwen 3 Max
0.00%± 1.29
(132/132)
GPT-6.2 Astra
0.00%± 2.04
(132/132)

Overall performance

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

2026-11-16

Comparison by Industry

Model performance on different sections of the economy.

Legal
81.86%
29.52%
Finance
73.51%
52.87%
Science
N/A
68.44%
Academic
81.95%
N/A
Coding
40.86%
69.39%

Cost Analysis

Per task and per token model pricing.

Vals Index · USD
N/A
$10.68
Cost / TestVals Index
N/A
$10.68
Input Cost/ 1M Tokens
$1.20
$8.00
Input Cache Write/ 1M Tokens
N/A
$10.00
Input Cache Read/ 1M Tokens
N/A
$0.40
Output Cost/ 1M Tokens
$6.00
$40.00

Model Metadata

Basic information about each model.

Model provider
AlibabaAlibaba
OpenAIOpenAI
LatencyN/A3136.31s
Cost (In/Out)$1.2 / $6$8 / $40
Context Window262k1M
Max Output Token66k128k
Input Modality