Compare Models
Select models (max 5)
Gemma 4 31B ITWonder Full
 |  |  |
|---|---|---|
| Vals IndexGDP-weighted benchmark | N/A | 64.57%±1.07 |
| Legal Research BenchAgentic US legal research | N/A | 53.37%±3.47 |
| Finance Agent (v2)Core financial analyst tasks | N/A | 59.06%±0.21 |
| Tax Agent BenchAgentic US corporate tax research | N/A | 43.00%±3.57 |
| Code MigrationRewriting programs in new languages | N/A | 61.03%±4.42 |
| Terminal-Bench 4.0Frontier-difficulty terminal tasks | N/A | 58.08%±3.31 |
| Vibe Code Bench v1.1Building web apps from scratch | N/A | 86.00%±1.93 |
Benchmarks
Vals Index *
Gemma 4 31B IT
N/AWonder Full
0.00%± 1.07
(47/47)Legal Research Bench *
Gemma 4 31B IT
N/AWonder Full
0.00%± 3.47
(78/78)Finance Agent (v2) *
Gemma 4 31B IT
N/AWonder Full
0.00%± 0.21
(78/78)Tax Agent Bench *
Gemma 4 31B IT
N/AWonder Full
0.00%± 3.57
(69/69)Code Migration *
Gemma 4 31B IT
N/AWonder Full
0.00%± 4.42
(77/77)Terminal-Bench 4.0
Gemma 4 31B IT
N/AWonder Full
0.00%± 3.31
(47/47)Vibe Code Bench v1.1 *
Gemma 4 31B IT
N/AWonder 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
N/A
vs.37.52%
Finance
61.37%
vs.57.99%
Math
N/A
vs.94.00%
Science
N/A
vs.54.23%
Education
55.03%
vs.N/A
Coding
N/A
vs.55.46%
Cyber
N/A
vs.73.63%
Social Mobility
N/A
vs.73.75%
Cost Analysis
Per task and per token model pricing.
Vals Index · USD
N/A
$8.559
Cost / TestVals Index
N/A
vs.$8.559
Input Cost/ 1M Tokens
$0.00
vs.$4.00
Input Cache Write/ 1M Tokens
$0.00
vs.N/A
Input Cache Read/ 1M Tokens
$0.00
vs.$0.20
Output Cost/ 1M Tokens
$0.00
vs.$20.00
Model Metadata
Basic information about each model.
| | |
|---|---|---|
| Model provider | Google | Meta |
| Latency | N/A | 3395.76s |
| Cost (In/Out) | $0 / $0 | $4 / $20 |
| Context Window | 262k | 1M |
| Max Output Token | 33k | 131k |
| Input Modality |