Compare Models
Select models (max 7)
Gemini 3.1 Pro Preview (02/26)GPT 5.4 Mini
| Legal Research BenchAgentic US legal research | 20.67%±2.81 | 12.50%±2.30 |
| Tax Agent BenchAgentic US corporate tax research | 9.29%±2.09 | 8.81%±2.04 |
| MedCodeMedical billing code support | 59.06%±2.00 | N/A |
| Terminal-Bench-ScienceExpert-authored scientific research workflows | 1.43%±1.43 | N/A |
| Terminal-Bench 4.0Frontier-difficulty terminal tasks | 2.52%±0.51 | 2.52%±1.01 |
| Vibe Code Bench v1.1Building web apps from scratch | 32.03%±4.34 | 47.97%±5.61 |
Benchmarks
Legal Research Bench *
Gemini 3.1 Pro Preview (02/26)
0.00%± 2.81
(98/98)GPT 5.4 Mini
0.00%± 2.30
(98/98)Tax Agent Bench *
Gemini 3.1 Pro Preview (02/26)
0.00%± 2.09
(89/89)GPT 5.4 Mini
0.00%± 2.04
(89/89)MedCode *
Gemini 3.1 Pro Preview (02/26)
0.00%± 2.00
(107/107)GPT 5.4 Mini
N/ATerminal-Bench-Science
Gemini 3.1 Pro Preview (02/26)
0.00%± 1.43
(47/47)GPT 5.4 Mini
N/ATerminal-Bench 4.0
Gemini 3.1 Pro Preview (02/26)
0.00%± 0.51
(68/68)GPT 5.4 Mini
0.00%± 1.01
(68/68)Vibe Code Bench v1.1 *
Gemini 3.1 Pro Preview (02/26)
0.00%± 4.34
(132/132)GPT 5.4 Mini
0.00%± 5.61
(132/132)Overall performance
Performance on the Vals Index, a GDP-weighted aggregation of tasks across finance, coding, legal, and tax
Comparison by Industry
Model performance on different sections of the economy.
Legal
54.04%
vs.12.50%
Finance
50.52%
vs.47.85%
Healthcare
67.59%
vs.N/A
Math
26.00%
vs.N/A
Science
27.38%
vs.N/A
Academic
91.55%
vs.82.29%
Education
83.18%
vs.N/A
Coding
42.28%
vs.40.99%
Cyber
0.00%
vs.N/A
Social Mobility
60.26%
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
$2.00
vs.$0.75
Input Cache Read/ 1M Tokens
$0.20
vs.$0.075
Output Cost/ 1M Tokens
$12.00
vs.$4.50
Model Metadata
Basic information about each model.
| Model provider | ||
| Latency | N/A | N/A |
| Cost (In/Out) | $2 / $12 | $0.75 / $4.5 |
| Context Window | 1M | 400k |
| Max Output Token | 66k | 128k |
| Input Modality |