Compare Models
Select models (max 7)
DeepSeek V4.1 FlashGPT-5.6 Luna
 |  |  |
|---|---|---|
| Legal Research BenchAgentic US legal research | 41.35%±3.42 | 36.54%±3.35 |
| Finance Agent v2.1Core financial analyst tasks | 65.43%±2.02 | N/A |
| Tax Agent BenchAgentic US corporate tax research | 26.63%±3.14 | 24.82%±3.11 |
| MedCodeMedical billing code support | 41.17%±2.04 | 42.39%±2.27 |
| Terminal-Bench-ScienceExpert-authored scientific research workflows | 0.00%±0.00 | 0.00%±0.00 |
| Code Migration v1.1Rewriting programs in new languages | 58.94%±2.66 | N/A |
| Terminal-Bench 4.0Frontier-difficulty terminal tasks | 19.70%±1.75 | 11.62%±1.01 |
| Vibe Code Bench v1.1Building web apps from scratch | 84.74%±2.89 | 77.06%±3.07 |
Benchmarks
Legal Research Bench *
DeepSeek V4.1 Flash
0.00%± 3.42
(84/84)GPT-5.6 Luna
0.00%± 3.35
(84/84)Finance Agent v2.1 *
DeepSeek V4.1 Flash
0.00%± 2.02
(30/30)GPT-5.6 Luna
N/ATax Agent Bench *
DeepSeek V4.1 Flash
0.00%± 3.14
(75/75)GPT-5.6 Luna
0.00%± 3.11
(75/75)MedCode *
DeepSeek V4.1 Flash
0.00%± 2.04
(107/107)GPT-5.6 Luna
0.00%± 2.27
(107/107)Terminal-Bench-Science
DeepSeek V4.1 Flash
0.00%± 0.00
(42/42)GPT-5.6 Luna
0.00%± 0.00
(42/42)Code Migration v1.1 *
DeepSeek V4.1 Flash
0.00%± 2.66
(28/28)GPT-5.6 Luna
N/ATerminal-Bench 4.0
DeepSeek V4.1 Flash
0.00%± 1.75
(54/54)GPT-5.6 Luna
0.00%± 1.01
(54/54)Vibe Code Bench v1.1 *
DeepSeek V4.1 Flash
0.00%± 2.89
(118/118)GPT-5.6 Luna
0.00%± 3.07
(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
62.31%
vs.60.29%
Finance
53.27%
vs.56.09%
Healthcare
63.34%
vs.63.39%
Math
54.00%
vs.60.00%
Science
29.65%
vs.25.30%
Academic
N/A
vs.87.58%
Education
47.88%
vs.44.22%
Coding
42.10%
vs.46.64%
Cyber
37.23%
vs.37.58%
Social Mobility
64.28%
vs.61.16%
Cost Analysis
Per task and per token model pricing.
Vals Index · USD
N/A
N/A
Cost / TestVals Index
N/A
vs.N/A
Input Cost/ 1M Tokens
$0.30
vs.$0.20
Input Cache Write/ 1M Tokens
N/A
vs.$0.25
Input Cache Read/ 1M Tokens
$0.006
vs.$0.02
Output Cost/ 1M Tokens
$1.20
vs.$1.20
Model Metadata
Basic information about each model.
| | |
|---|---|---|
| Model provider | DeepSeek | OpenAI |
| Latency | N/A | N/A |
| Cost (In/Out) | $0.3 / $1.2 | $0.2 / $1.2 |
| Context Window | 1M | 1M |
| Max Output Token | 384k | 128k |
| Input Modality |