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