Compare Models
Select models (max 5)
GPT 5.1 Codex MaxGemini 4 Argon
 |  |  |
|---|---|---|
| Vals IndexGDP-weighted benchmark | N/A | 68.90%±0.97 |
| Legal Research BenchAgentic US legal research | N/A | 54.81%±3.46 |
| Finance Agent (v2)Core financial analyst tasks | N/A | 65.40%±0.32 |
| Tax Agent BenchAgentic US corporate tax research | N/A | 76.23%±2.87 |
| MedCodeMedical billing code support | N/A | 58.80%±2.10 |
| Terminal-Bench ScienceExpert-authored scientific research workflows | N/A | 44.29%±5.98 |
| Code MigrationRewriting programs in new languages | N/A | 68.17%±4.35 |
| Terminal-Bench 4.0Frontier-difficulty terminal tasks | N/A | 57.58%±2.31 |
| Vibe Code Bench v1.1Building web apps from scratch | 22.17%±3.84 | 91.91%±1.90 |
Benchmarks
Vals Index *
GPT 5.1 Codex Max
N/AGemini 4 Argon
0.00%± 0.97
(41/41)Legal Research Bench *
GPT 5.1 Codex Max
N/AGemini 4 Argon
0.00%± 3.46
(72/72)Finance Agent (v2) *
GPT 5.1 Codex Max
N/AGemini 4 Argon
0.00%± 0.32
(73/73)Tax Agent Bench *
GPT 5.1 Codex Max
N/AGemini 4 Argon
0.00%± 2.87
(64/64)MedCode *
GPT 5.1 Codex Max
N/AGemini 4 Argon
0.00%± 2.10
(104/104)Terminal-Bench Science
GPT 5.1 Codex Max
N/AGemini 4 Argon
0.00%± 5.98
(34/34)Code Migration *
GPT 5.1 Codex Max
N/AGemini 4 Argon
0.00%± 4.35
(71/71)Terminal-Bench 4.0
GPT 5.1 Codex Max
N/AGemini 4 Argon
0.00%± 2.31
(42/42)Vibe Code Bench v1.1 *
GPT 5.1 Codex Max
0.00%± 3.84
(106/106)Gemini 4 Argon
0.00%± 1.90
(106/106)Overall performance
Performance on the Vals Index, a GDP-weighted aggregation of tasks across finance, coding, and law
•2026-09-30
Comparison by Industry
Model performance on different sections of the economy.
Legal
N/A
vs.54.23%
Finance
N/A
vs.72.29%
Healthcare
N/A
vs.73.11%
Math
N/A
vs.99.00%
Science
N/A
vs.55.36%
Education
N/A
vs.53.65%
Coding
52.86%
vs.64.03%
Cyber
N/A
vs.61.07%
Social Mobility
N/A
vs.69.76%
Cost Analysis
Per task and per token model pricing.
Vals Index · USD
N/A
$15.68
Cost / TestVals Index
N/A
vs.$15.68
Input Cost/ 1M Tokens
$1.25
vs.$4.00
Input Cache Read/ 1M Tokens
$0.125
vs.$0.20
Output Cost/ 1M Tokens
$10.00
vs.$20.00
Model Metadata
Basic information about each model.
| | |
|---|---|---|
| Model provider | OpenAI | Google |
| Latency | N/A | 2792.77s |
| Cost (In/Out) | $1.25 / $10 | $4 / $20 |
| Context Window | 400k | 1M |
| Max Output Token | 128k | 262k |
| Input Modality |