GPT-5.4 nano

OpenAI · elicited April 2026 · average interval-width rank #17.7 of 29 across the canonical panel · $0.12 total elicitation cost.

gpt-5.4-nano

Canonical panel profile

One row per canonical quantity, each on its own scale: this model's pooled center and 90 percent interval, with the 29-model panel median as a gray tick.

Employment participation elasticity of single mothers

0.213 · med 0.533

Frisch elasticity of labor supply

0.593 · med 0.413

Income elasticity of labor supply

-0.001 · med -0.062

Uncompensated wage elasticity of labor supply

0.148 · med 0.100

Capital gains realizations elasticity

-0.373 · med -0.647

Elasticity of taxable income

0.552 · med 0.430

Intertemporal elasticity of substitution

0.747 · med 0.527

Elasticity of substitution between capital and labor

0.787 · med 0.690

Armington elasticity

2.233 · med 2.067

Annual discount factor

0.963 · med 0.960

Coefficient of relative risk aversion

1.900 · med 2.000

TFP persistence

0.823 · med 0.950

Capital share in production

0.314 · med 0.334

Generation harness

From the paper's per-model disclosure (Appendix A16). The prompt and repeated-run design are identical across models; the output mechanism follows each provider's API surface.

Provider path: OpenAI Chat Completions
Output mechanism: strict JSON schema
Completion budget: 1200
Sampling: temperature 1.0, batched n <= 8
Reasoning: provider default effort
API identifier: gpt-5.4-nano (alias)

195 successful runs · elicited April and July 2026 · v4 prompts · 15 runs per model-quantity cell. Code · Raw responses · Paper (PDF)

Code and dataElicited April and July 2026 · 29 models · v4 prompts