Compare Models
Select models (max 5)
Gemini 4 ArgonMistral Large 4
 |  |  |
|---|---|---|
| Vals IndexGDP-weighted benchmark | 68.90%±0.97 | 48.05%±1.11 |
| Legal Research BenchAgentic US legal research | 54.81%±3.46 | 31.73%±3.23 |
| Finance Agent (v2)Core financial analyst tasks | 65.40%±0.32 | 54.68%±0.58 |
| Tax Agent BenchAgentic US corporate tax research | 76.23%±2.87 | 63.29%±3.23 |
| MedCodeMedical billing code support | 58.80%±2.10 | 40.69%±2.17 |
| Terminal-Bench ScienceExpert-authored scientific research workflows | 44.29%±5.98 | N/A |
| Code MigrationRewriting programs in new languages | 68.17%±4.35 | 30.56%±4.22 |
| Terminal-Bench 4.0Frontier-difficulty terminal tasks | 57.58%±2.31 | 22.73%±0.88 |
| Vibe Code Bench v1.1Building web apps from scratch | 91.91%±1.90 | 78.40%±3.55 |
Benchmarks
Vals Index *
Gemini 4 Argon
0.00%± 0.97
(44/44)Mistral Large 4
0.00%± 1.11
(44/44)Legal Research Bench *
Gemini 4 Argon
0.00%± 3.46
(74/74)Mistral Large 4
0.00%± 3.23
(74/74)Finance Agent (v2) *
Gemini 4 Argon
0.00%± 0.32
(75/75)Mistral Large 4
0.00%± 0.58
(75/75)Tax Agent Bench *
Gemini 4 Argon
0.00%± 2.87
(66/66)Mistral Large 4
0.00%± 3.23
(66/66)MedCode *
Gemini 4 Argon
0.00%± 2.10
(105/105)Mistral Large 4
0.00%± 2.17
(105/105)Terminal-Bench Science
Gemini 4 Argon
0.00%± 5.98
(38/38)Mistral Large 4
N/ACode Migration *
Gemini 4 Argon
0.00%± 4.35
(74/74)Mistral Large 4
0.00%± 4.22
(74/74)Terminal-Bench 4.0
Gemini 4 Argon
0.00%± 2.31
(44/44)Mistral Large 4
0.00%± 0.88
(44/44)Vibe Code Bench v1.1 *
Gemini 4 Argon
0.00%± 1.90
(109/109)Mistral Large 4
0.00%± 3.55
(109/109)Overall performance
Performance on the Vals Index, a GDP-weighted aggregation of tasks across finance, coding, and law
•2026-10-06
Comparison by Industry
Model performance on different sections of the economy.
Legal
54.23%
vs.23.78%
Finance
72.29%
vs.58.06%
Healthcare
73.11%
vs.60.56%
Math
99.00%
vs.10.00%
Science
55.36%
vs.39.60%
Education
53.65%
vs.N/A
Coding
64.03%
vs.38.25%
Cyber
61.07%
vs.N/A
Social Mobility
69.76%
vs.N/A
Cost Analysis
Per task and per token model pricing.
Vals Index · USD
$15.68
$13.78
Cost / TestVals Index
$15.68
vs.$13.78
Input Cost/ 1M Tokens
$4.00
vs.$1.36
Input Cache Read/ 1M Tokens
$0.20
vs.$0.14
Output Cost/ 1M Tokens
$20.00
vs.$4.18
Model Metadata
Basic information about each model.
| | |
|---|---|---|
| Model provider | Google | Mistral AI |
| Latency | 2792.77s | 6350.41s |
| Cost (In/Out) | $4 / $20 | $1.36 / $4.18 |
| Context Window | 1M | 512k |
| Max Output Token | 262k | 256k |
| Input Modality |