Compare Models

Select models (max 5)

o3Mistral Large 4


Vals IndexGDP-weighted benchmark	N/A	48.05%±1.11
Legal Research BenchAgentic US legal research	N/A	31.73%±3.23
Finance Agent (v2)Core financial analyst tasks	N/A	54.68%±0.58
Tax Agent BenchAgentic US corporate tax research	N/A	63.29%±3.23
MedCodeMedical billing code support	47.29%±2.16	40.69%±2.17
Code MigrationRewriting programs in new languages	N/A	30.56%±4.22
Terminal-Bench 4.0Frontier-difficulty terminal tasks	N/A	22.73%±0.88
Vibe Code Bench v1.1Building web apps from scratch	N/A	78.40%±3.55

Benchmarks

Vals Index *

N/A

Mistral Large 4

0.00%± 1.11

(44/44)

Legal Research Bench *

N/A

Mistral Large 4

0.00%± 3.23

(74/74)

Finance Agent (v2) *

N/A

Mistral Large 4

0.00%± 0.58

(75/75)

Tax Agent Bench *

N/A

Mistral Large 4

0.00%± 3.23

(66/66)

MedCode *

0.00%± 2.16

(105/105)

Mistral Large 4

0.00%± 2.17

(105/105)

Code Migration *

N/A

Mistral Large 4

0.00%± 4.22

(74/74)

Terminal-Bench 4.0

N/A

Mistral Large 4

0.00%± 0.88

(44/44)

Vibe Code Bench v1.1 *

N/A

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

o3 Mistral Large 4

Comparison by Industry

Model performance on different sections of the economy.

Legal

83.76%

vs.

23.78%

Finance

70.14%

vs.

58.06%

Healthcare

61.97%

vs.

60.56%

Math

N/A

vs.

10.00%

Science

N/A

vs.

39.60%

Academic

83.37%

vs.

N/A

Education

41.77%

vs.

N/A

Coding

83.91%

vs.

38.25%

Cost Analysis

Per task and per token model pricing.

Vals Index · USD

N/A

$13.78

Cost / TestVals Index

N/A

vs.

$13.78

Input Cost/ 1M Tokens

$2.00

vs.

$1.36

Input Cache Read/ 1M Tokens

$0.50

vs.

$0.14

Output Cost/ 1M Tokens

$8.00

vs.

$4.18

Model Metadata

Basic information about each model.


Model provider	OpenAI	Mistral AI
Latency	N/A	6350.41s
Cost (In/Out)	$2 / $8	$1.36 / $4.18
Context Window	200k	512k
Max Output Token	100k	256k
Input Modality