Compare Models
Select models (max 7)
DeepSeek V4 Flash 0731Mistral Large 4 OSS
 |  |  |
|---|---|---|
| Vals IndexGDP-weighted benchmark | N/A | 56.42%±1.26 |
| Legal Research BenchAgentic US legal research | 30.29%±3.19 | 35.58%±3.33 |
| Finance Agent v2.1Core financial analyst tasks | N/A | 61.72%±2.05 |
| Tax Agent BenchAgentic US corporate tax research | 28.07%±3.16 | 27.33%±2.95 |
| MedCodeMedical billing code support | 41.41%±2.15 | N/A |
| Terminal-Bench-ScienceExpert-authored scientific research workflows | 4.29%±2.44 | N/A |
| Terminal-Bench 4.0Frontier-difficulty terminal tasks | 18.69%±3.54 | 26.26%±5.13 |
| Vibe Code Bench v1.1Building web apps from scratch | 74.74%±3.44 | 81.56%±3.29 |
Benchmarks
Vals Index *
DeepSeek V4 Flash 0731
N/AMistral Large 4 OSS
0.00%± 1.26
(32/32)Legal Research Bench *
DeepSeek V4 Flash 0731
0.00%± 3.19
(89/89)Mistral Large 4 OSS
0.00%± 3.33
(89/89)Finance Agent v2.1 *
DeepSeek V4 Flash 0731
N/AMistral Large 4 OSS
0.00%± 2.05
(35/35)Tax Agent Bench *
DeepSeek V4 Flash 0731
0.00%± 3.16
(80/80)Mistral Large 4 OSS
0.00%± 2.95
(80/80)MedCode *
DeepSeek V4 Flash 0731
0.00%± 2.15
(107/107)Mistral Large 4 OSS
N/ATerminal-Bench-Science
DeepSeek V4 Flash 0731
0.00%± 2.44
(43/43)Mistral Large 4 OSS
N/ATerminal-Bench 4.0
DeepSeek V4 Flash 0731
0.00%± 3.54
(59/59)Mistral Large 4 OSS
0.00%± 5.13
(59/59)Vibe Code Bench v1.1 *
DeepSeek V4 Flash 0731
0.00%± 3.44
(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
Comparison by Industry
Model performance on different sections of the economy.
Legal
54.00%
vs.25.70%
Finance
49.38%
vs.52.58%
Healthcare
60.89%
vs.N/A
Math
56.00%
vs.N/A
Science
34.37%
vs.N/A
Academic
88.05%
vs.N/A
Coding
50.41%
vs.53.91%
Cyber
72.08%
vs.N/A
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
$0.30
vs.$0.70
Input Cache Read/ 1M Tokens
$0.006
vs.$0.07
Output Cost/ 1M Tokens
$1.20
vs.$2.10
Model Metadata
Basic information about each model.
| | |
|---|---|---|
| Model provider | DeepSeek | Mistral AI |
| Latency | N/A | 2868.04s |
| Cost (In/Out) | $0.3 / $1.2 | $0.7 / $2.1 |
| Context Window | 1M | 1M |
| Max Output Token | 384k | 256k |
| Input Modality |