HumanEval Infilling

Mercury Coder Small 84.8% Only in system cards

Models fill in a masked middle span of HumanEval solutions given the code before and after it. Unit tests check the completed function.

The harness offers single-line, multi-line, random-span and random-span-light settings. Labs often report single-line and random-span-light separately.

Made by OpenAI (Bavarian et al.) Released Jul 2022 Function-level problems All tasks public Last in a system card Jun 2025 Last model added Jun 2025

Level: School Students, from grade school to high school
Scored: Checked automatically A program checks the result against an answer key, unit tests or the expected final state.
Answers: Code A program or patch run against tests.

openai/human-eval-infilling 210 stars Paper

Model scored in lab cards

System card reports it, from 1 lab

Mercury Coder Small leads with 84.8%

Best score per model as labs report them in their own cards. Labs pick their own settings, so these compare less cleanly than independent runs.

Bars Table

84.8 Mercury Coder Small

1 Mercury Coder Small 84.8%

#	Model	Score	Setting	Date	Source
1	Mercury Coder Small	84.8%		Jun 2025	Model card

Scores over time

All the scores we have, one dot each, so a model tested at several settings appears more than once.

Reported by the lab in its model card

Labs report it only in system cards

We read the headline results of 479 launch posts from 51 labs, and none of them list this benchmark. Some system cards do, below.

One system card reports it

Besides launch posts, we read the system cards, model cards and technical reports labs publish with a release. They report far more, including safety and frontier-risk tests.

Date	Document	Score	As the document writes it	Section
17 Jun 2025	Mercury Coder Small technical report	84.8	FIM Average of Single-Line 93.1 and Random-Span-Light 76.5 (Table 3)	Capabilities

Mercury Coder Small leads with 84.8%

Scores over time

Labs report it only in system cards

One system card reports it

More in Coding