Compare Models
Select models (max 7)
Kimi K3Mistral Large 4
 |  |  |
|---|---|---|
| Vals IndexGDP-weighted benchmark | 52.95%±1.00 | N/A |
| Legal Research BenchAgentic US legal research | 46.15%±3.46 | 31.73%±3.23 |
| Finance Agent v2.1Core financial analyst tasks | 60.01%±2.09 | 61.38%±2.02 |
| Tax Agent BenchAgentic US corporate tax research | 33.37%±3.39 | 30.39%±3.31 |
| MedCodeMedical billing code support | 49.36%±2.20 | 40.69%±2.17 |
| Terminal-Bench-ScienceExpert-authored scientific research workflows | 1.43%±1.43 | N/A |
| Code Migration v1.1Rewriting programs in new languages | 28.59%±3.78 | N/A |
| Terminal-Bench 4.0Frontier-difficulty terminal tasks | 17.17%±0.51 | 27.78%±1.82 |
| Vibe Code Bench v1.1Building web apps from scratch | 84.97%±2.75 | 78.40%±3.55 |
Benchmarks
Vals Index *
Kimi K3
0.00%± 1.00
(26/26)Mistral Large 4
N/ALegal Research Bench *
Kimi K3
0.00%± 3.46
(84/84)Mistral Large 4
0.00%± 3.23
(84/84)Finance Agent v2.1 *
Kimi K3
0.00%± 2.09
(30/30)Mistral Large 4
0.00%± 2.02
(30/30)Tax Agent Bench *
Kimi K3
0.00%± 3.39
(75/75)Mistral Large 4
0.00%± 3.31
(75/75)MedCode *
Kimi K3
0.00%± 2.20
(107/107)Mistral Large 4
0.00%± 2.17
(107/107)Terminal-Bench-Science
Kimi K3
0.00%± 1.43
(42/42)Mistral Large 4
N/ACode Migration v1.1 *
Kimi K3
0.00%± 3.78
(28/28)Mistral Large 4
N/ATerminal-Bench 4.0
Kimi K3
0.00%± 0.51
(54/54)Mistral Large 4
0.00%± 1.82
(54/54)Vibe Code Bench v1.1 *
Kimi K3
0.00%± 2.75
(118/118)Mistral Large 4
0.00%± 3.55
(118/118)Overall performance
Performance on the Vals Index, a GDP-weighted aggregation of tasks across finance, coding, and law
•2026-10-22
Comparison by Industry
Model performance on different sections of the economy.
Legal
48.43%
vs.24.62%
Finance
61.34%
vs.53.58%
Healthcare
68.70%
vs.60.56%
Math
87.00%
vs.10.00%
Science
37.01%
vs.39.60%
Academic
89.68%
vs.N/A
Education
52.78%
vs.N/A
Coding
47.19%
vs.39.77%
Cyber
75.24%
vs.N/A
Social Mobility
68.20%
vs.N/A
Cost Analysis
Per task and per token model pricing.
Vals Index · USD
$7.169
N/A
Cost / TestVals Index
$7.169
vs.N/A
Input Cost/ 1M Tokens
$3.00
vs.$1.36
Input Cache Read/ 1M Tokens
$0.30
vs.$0.14
Output Cost/ 1M Tokens
$15.00
vs.$4.18
Model Metadata
Basic information about each model.
| | |
|---|---|---|
| Model provider | Kimi | Mistral AI |
| Latency | 4496.01s | N/A |
| Cost (In/Out) | $3 / $15 | $1.36 / $4.18 |
| Context Window | 1M | 512k |
| Max Output Token | 1M | 256k |
| Input Modality |