Model results

EvalPlus

Choose a shared evaluation protocol to compare model scores. Versions, sources and configurations stay separate.

Atlas snapshot captured 10/19/2026, 10:20:28 AM UTC. This is an import timestamp, not the evaluation date. Coverage may be incomplete.

Official source

← All evaluation groups

EvalPlus

Source: EvalPlus (reviewed publisher results)
Version: mbpp-evalplus-v0.2.0-399
Measurement date: Not reported
Metric: % · Higher is better
Evaluation scope: EvalPlus harness; mbpp; MBPP original tests in the MBPP+ v0.2.0 dataset; 399 hand-verified tasks from MBPP-sanitized 427; greedy decoding; pass@1; prompted=True; result date not supplied; source identity GPT 4o (Aug 2024); source supplies only a model month; exact dated backend unverified; historical model mapping retained pending execution evidence

Fewer than two comparable models. No ranking is assigned. Missing metadata is shown as unreported; matching imported metadata is not independent verification of the protocol.

GPT-4o (2024-08-06)
openai/gpt-4o-2024-08-06
87.6%
View modelEvidence independent