Grok 4.20

xAI · elicited April 2026 · average interval-width rank #22.3 of 29 across the canonical panel · $3.45 total elicitation cost.

grok-4.20

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

0.467 · med 0.533

Frisch elasticity of labor supply

0.467 · med 0.413

Income elasticity of labor supply

-0.107 · med -0.062

Uncompensated wage elasticity of labor supply

0.160 · med 0.100

Capital gains realizations elasticity

-0.473 · med -0.647

Elasticity of taxable income

0.500 · med 0.430

Intertemporal elasticity of substitution

0.967 · med 0.527

Elasticity of substitution between capital and labor

0.803 · med 0.690

Armington elasticity

2.000 · med 2.067

Annual discount factor

0.959 · med 0.960

Coefficient of relative risk aversion

2.000 · med 2.000

TFP persistence

0.937 · med 0.950

Capital share in production

0.330 · 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: LiteLLM
Output mechanism: forced function call
Completion budget: 1200
Sampling: temperature 1.0
Reasoning: reasoning variant
API identifier: xai/grok-4.20-reasoning (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