Compare Models
Select models (max 7)
WonderGPT-6 Sol
 |  |  |
|---|---|---|
| Vals IndexGDP-weighted benchmark | 64.88%±1.07 | N/A |
| Legal Research BenchAgentic US legal research | 50.48%±3.48 | 28.85%±3.15 |
| Finance Agent v2.1Core financial analyst tasks | 65.55%±2.03 | N/A |
| Tax Agent BenchAgentic US corporate tax research | 36.27%±3.47 | 15.00%±2.58 |
| MedCodeMedical billing code support | N/A | 47.07%±2.12 |
| Terminal-Bench-ScienceExpert-authored scientific research workflows | 22.86%±5.05 | 30.00%±5.52 |
| Code Migration v1.1Rewriting programs in new languages | 72.36%±3.19 | N/A |
| Terminal-Bench 4.0Frontier-difficulty terminal tasks | 49.49%±2.20 | 44.44%±3.54 |
| Vibe Code Bench v1.1Building web apps from scratch | 83.09%±2.49 | 87.82%±2.53 |
Benchmarks
Vals Index *
Wonder
0.00%± 1.07
(26/26)GPT-6 Sol
N/ALegal Research Bench *
Wonder
0.00%± 3.48
(84/84)GPT-6 Sol
0.00%± 3.15
(84/84)Finance Agent v2.1 *
Wonder
0.00%± 2.03
(30/30)GPT-6 Sol
N/ATax Agent Bench *
Wonder
0.00%± 3.47
(75/75)GPT-6 Sol
0.00%± 2.58
(75/75)MedCode *
Wonder
N/AGPT-6 Sol
0.00%± 2.12
(107/107)Terminal-Bench-Science
Wonder
0.00%± 5.05
(42/42)GPT-6 Sol
0.00%± 5.52
(42/42)Code Migration v1.1 *
Wonder
0.00%± 3.19
(28/28)GPT-6 Sol
N/ATerminal-Bench 4.0
Wonder
0.00%± 2.20
(54/54)GPT-6 Sol
0.00%± 3.54
(54/54)Vibe Code Bench v1.1 *
Wonder
0.00%± 2.49
(118/118)GPT-6 Sol
0.00%± 2.53
(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
37.12%
vs.28.85%
Finance
58.11%
vs.15.00%
Healthcare
N/A
vs.64.55%
Math
84.00%
vs.83.00%
Science
39.12%
vs.45.00%
Education
N/A
vs.44.79%
Coding
57.34%
vs.54.22%
Cyber
80.36%
vs.54.25%
Social Mobility
70.23%
vs.56.63%
Cost Analysis
Per task and per token model pricing.
Vals Index · USD
$10.65
N/A
Cost / TestVals Index
$10.65
vs.N/A
Input Cost/ 1M Tokens
$4.00
vs.$2.00
Input Cache Write/ 1M Tokens
N/A
vs.$2.50
Input Cache Read/ 1M Tokens
$0.20
vs.$0.20
Output Cost/ 1M Tokens
$20.00
vs.$10.00
Model Metadata
Basic information about each model.
| | |
|---|---|---|
| Model provider | Meta | OpenAI |
| Latency | 2123.57s | N/A |
| Cost (In/Out) | $4 / $20 | $2 / $10 |
| Context Window | 1M | 1M |
| Max Output Token | 131k | 128k |
| Input Modality |