Compare Models
Select models (max 7)
Mistral Large 4 OSSGemini 4 Carbon
 |  |  |
|---|---|---|
| Vals IndexGDP-weighted benchmark | 56.42%±1.26 | 70.36%±0.97 |
| Legal Research BenchAgentic US legal research | 35.58%±3.33 | 55.77%±3.45 |
| Finance Agent v2.1Core financial analyst tasks | 61.72%±2.05 | 67.16%±2.02 |
| Tax Agent BenchAgentic US corporate tax research | 27.33%±2.95 | 48.86%±3.42 |
| Terminal-Bench 4.0Frontier-difficulty terminal tasks | 26.26%±5.13 | 63.13%±2.20 |
| Vibe Code Bench v1.1Building web apps from scratch | 81.56%±3.29 | 89.06%±2.29 |
Benchmarks
Vals Index *
Mistral Large 4 OSS
0.00%± 1.26
(30/30)Gemini 4 Carbon
0.00%± 0.97
(30/30)Legal Research Bench *
Mistral Large 4 OSS
0.00%± 3.33
(88/88)Gemini 4 Carbon
0.00%± 3.45
(88/88)Finance Agent v2.1 *
Mistral Large 4 OSS
0.00%± 2.05
(34/34)Gemini 4 Carbon
0.00%± 2.02
(34/34)Tax Agent Bench *
Mistral Large 4 OSS
0.00%± 2.95
(79/79)Gemini 4 Carbon
0.00%± 3.42
(79/79)Terminal-Bench 4.0
Mistral Large 4 OSS
0.00%± 5.13
(58/58)Gemini 4 Carbon
0.00%± 2.20
(58/58)Vibe Code Bench v1.1 *
Mistral Large 4 OSS
0.00%± 3.29
(122/122)Gemini 4 Carbon
0.00%± 2.29
(122/122)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
25.70%
vs.36.63%
Finance
52.58%
vs.64.16%
Coding
53.91%
vs.76.10%
Cost Analysis
Per task and per token model pricing.
Vals Index · USD
$3.717
$10.51
Cost / TestVals Index
$3.717
vs.$10.51
Input Cost/ 1M Tokens
$0.70
vs.$4.00
Input Cache Read/ 1M Tokens
$0.07
vs.$0.20
Output Cost/ 1M Tokens
$2.10
vs.$20.00
Model Metadata
Basic information about each model.
| | |
|---|---|---|
| Model provider | Mistral AI | Google |
| Latency | 2868.04s | 2864.86s |
| Cost (In/Out) | $0.7 / $2.1 | $4 / $20 |
| Context Window | 1M | 1M |
| Max Output Token | 256k | 1M |
| Input Modality |