Compare Models
Select models (max 5)
WonderWonder Full
 |  | |
|---|---|---|
| Vals IndexGDP-weighted benchmark | 61.06%±1.07 | 64.57%±1.07 |
| Legal Research BenchAgentic US legal research | 50.48%±3.48 | 53.37%±3.47 |
| Finance Agent (v2)Core financial analyst tasks | 56.64%±0.38 | 59.06%±0.21 |
| Tax Agent BenchAgentic US corporate tax research | 36.27%±3.47 | 43.00%±3.57 |
| Terminal-Bench ScienceExpert-authored scientific research workflows | 22.86%±5.05 | N/A |
| Code MigrationRewriting programs in new languages | 62.55%±4.35 | 61.03%±4.42 |
| Terminal-Bench 4.0Frontier-difficulty terminal tasks | 49.49%±2.20 | 58.08%±3.31 |
| Vibe Code Bench v1.1Building web apps from scratch | 83.09%±2.49 | 86.00%±1.93 |
Benchmarks
Vals Index *
Wonder
0.00%± 1.07
(47/47)Wonder Full
0.00%± 1.07
(47/47)Legal Research Bench *
Wonder
0.00%± 3.48
(78/78)Wonder Full
0.00%± 3.47
(78/78)Finance Agent (v2) *
Wonder
0.00%± 0.38
(78/78)Wonder Full
0.00%± 0.21
(78/78)Tax Agent Bench *
Wonder
0.00%± 3.47
(69/69)Wonder Full
0.00%± 3.57
(69/69)Terminal-Bench Science
Wonder
0.00%± 5.05
(40/40)Wonder Full
N/ACode Migration *
Wonder
0.00%± 4.35
(77/77)Wonder Full
0.00%± 4.42
(77/77)Terminal-Bench 4.0
Wonder
0.00%± 2.20
(47/47)Wonder Full
0.00%± 3.31
(47/47)Vibe Code Bench v1.1 *
Wonder
0.00%± 2.49
(112/112)Wonder Full
0.00%± 1.93
(112/112)Overall performance
Performance on the Vals Index, a GDP-weighted aggregation of tasks across finance, coding, and law
•2026-10-12
Comparison by Industry
Model performance on different sections of the economy.
Legal
33.78%
vs.37.52%
Finance
53.33%
vs.57.99%
Math
84.00%
vs.94.00%
Science
39.12%
vs.54.23%
Coding
65.52%
vs.57.09%
Cyber
80.36%
vs.73.63%
Social Mobility
70.23%
vs.73.75%
Cost Analysis
Per task and per token model pricing.
Vals Index · USD
$11.43
$8.559
Cost / TestVals Index
$11.43
vs.$8.559
Input Cost/ 1M Tokens
$4.00
vs.$4.00
Input Cache Read/ 1M Tokens
$0.20
vs.$0.20
Output Cost/ 1M Tokens
$20.00
vs.$20.00
Model Metadata
Basic information about each model.
| | |
|---|---|---|
| Model provider | Meta | Meta |
| Latency | 2227.95s | 3395.76s |
| Cost (In/Out) | $4 / $20 | $4 / $20 |
| Context Window | 1M | 1M |
| Max Output Token | 131k | 131k |
| Input Modality |