Compare Models

Select models (max 7)

Gemini 3 Flash (12/25)Mistral Large 4 OSS


Vals IndexGDP-weighted benchmark	N/A	56.42%±1.26
Legal Research BenchAgentic US legal research	18.27%±2.69	35.58%±3.33
Finance Agent v2.1Core financial analyst tasks	N/A	61.72%±2.05
Tax Agent BenchAgentic US corporate tax research	11.84%±2.32	27.33%±2.95
MedCodeMedical billing code support	55.92%±2.11	N/A
Terminal-Bench 4.0Frontier-difficulty terminal tasks	N/A	26.26%±5.13
Vibe Code Bench v1.1Building web apps from scratch	20.20%±3.95	81.56%±3.29

Benchmarks

Vals Index *

Gemini 3 Flash (12/25)

N/A

Mistral Large 4 OSS

0.00%± 1.26

(32/32)

Legal Research Bench *

Gemini 3 Flash (12/25)

0.00%± 2.69

(89/89)

Mistral Large 4 OSS

0.00%± 3.33

(89/89)

Finance Agent v2.1 *

Gemini 3 Flash (12/25)

N/A

Mistral Large 4 OSS

0.00%± 2.05

(35/35)

Tax Agent Bench *

Gemini 3 Flash (12/25)

0.00%± 2.32

(80/80)

Mistral Large 4 OSS

0.00%± 2.95

(80/80)

MedCode *

Gemini 3 Flash (12/25)

0.00%± 2.11

(107/107)

Mistral Large 4 OSS

N/A

Terminal-Bench 4.0

Gemini 3 Flash (12/25)

N/A

Mistral Large 4 OSS

0.00%± 5.13

(59/59)

Vibe Code Bench v1.1 *

Gemini 3 Flash (12/25)

0.00%± 3.95

(123/123)

Mistral Large 4 OSS

0.00%± 3.29

(123/123)

Overall performance

Performance on the Vals Index, a GDP-weighted aggregation of tasks across finance, coding, and law

•2026-10-29

Gemini 3 Flash (12/25)Mistral Large 4 OSS

Comparison by Industry

Model performance on different sections of the economy.

Legal

52.56%

vs.

25.70%

Finance

51.48%

vs.

52.58%

Healthcare

62.92%

vs.

N/A

Academic

88.03%

vs.

N/A

Coding

45.20%

vs.

53.91%

Cost Analysis

Per task and per token model pricing.

Vals Index · USD

N/A

$3.717

Cost / TestVals Index

N/A

vs.

$3.717

Input Cost/ 1M Tokens

$0.50

vs.

$0.70

Input Cache Read/ 1M Tokens

$0.05

vs.

$0.07

Output Cost/ 1M Tokens

$3.00

vs.

$2.10

Model Metadata

Basic information about each model.


Model provider	Google	Mistral AI
Latency	N/A	2868.04s
Cost (In/Out)	$0.5 / $3	$0.7 / $2.1
Context Window	1M	1M
Max Output Token	66k	256k
Input Modality