Compare Models
Select models (max 7)
Mercury 2.5GPT 5.4 Mini
 |  |  |
|---|---|---|
| Legal Research BenchAgentic US legal research | 4.33%±1.41 | 12.50%±2.30 |
| Tax Agent BenchAgentic US corporate tax research | 2.49%±1.02 | 8.81%±2.04 |
| MedCodeMedical billing code support | 31.33%±1.95 | N/A |
| Terminal-Bench-ScienceExpert-authored scientific research workflows | 0.00%±0.00 | N/A |
| Terminal-Bench 4.0Frontier-difficulty terminal tasks | 0.00%±0.00 | 2.52%±1.01 |
| Vibe Code Bench v1.1Building web apps from scratch | 3.68%±1.41 | 47.97%±5.61 |
Benchmarks
Legal Research Bench *
Mercury 2.5
0.00%± 1.41
(84/84)GPT 5.4 Mini
0.00%± 2.30
(84/84)Tax Agent Bench *
Mercury 2.5
0.00%± 1.02
(75/75)GPT 5.4 Mini
0.00%± 2.04
(75/75)MedCode *
Mercury 2.5
0.00%± 1.95
(107/107)GPT 5.4 Mini
N/ATerminal-Bench-Science
Mercury 2.5
0.00%± 0.00
(42/42)GPT 5.4 Mini
N/ATerminal-Bench 4.0
Mercury 2.5
0.00%± 0.00
(54/54)GPT 5.4 Mini
0.00%± 1.01
(54/54)Vibe Code Bench v1.1 *
Mercury 2.5
0.00%± 1.41
(118/118)GPT 5.4 Mini
0.00%± 5.61
(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
43.69%
vs.12.50%
Finance
2.49%
vs.47.85%
Healthcare
43.21%
vs.N/A
Math
3.00%
vs.N/A
Science
0.00%
vs.N/A
Academic
N/A
vs.82.29%
Education
N/A
vs.50.81%
Coding
6.05%
vs.40.99%
Cyber
45.48%
vs.N/A
Social Mobility
45.26%
vs.N/A
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
$0.20
vs.$0.75
Input Cache Read/ 1M Tokens
$0.02
vs.$0.075
Output Cost/ 1M Tokens
$0.75
vs.$4.50
Model Metadata
Basic information about each model.
| | |
|---|---|---|
| Model provider | Inception | OpenAI |
| Latency | N/A | N/A |
| Cost (In/Out) | $0.2 / $0.75 | $0.75 / $4.5 |
| Context Window | 260k | 400k |
| Max Output Token | 66k | 128k |
| Input Modality |