Categories Companies Research

Loading the SOTA2 catalog…

Explore

Categories Companies Research

Contribute

Join SOTA2 Contact

SOTA2

© 2026 SOTA2

Build in Bellevue, USA

WizWand is now SOTA2 Research

Papers Benchmarks Datasets Tasks

Code Generation research benchmarks – Page 40 · SOTA2 Research

Code Generation

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

Mistral 2501 Base

66Accuracy

2

Feb 26, 2026

Code Generation (CG)

26.7BLEU

2

Feb 26, 2026

Leetcode Hard Python released after Oct 8, 2022 (test)

15Pass@1

2

Feb 26, 2026

MBPP Rust MultiPL-E translation (test)

75.4Pass@1

2

Feb 26, 2026

HumanEval MultiPL-E translation Rust (test)

0.68Pass@1

2

Feb 26, 2026

16.2Pass@1

2

Feb 26, 2026

Java Code Corpus modified type (test)

2.58Perplexity

2

Feb 26, 2026

Empirical Routing

48Winrate

1

Jun 23, 2026

Empirical Routing

60Winrate

1

Jun 23, 2026

HumanEval Binary Search

50Completion Rate

1

Jun 4, 2026

HumanEval Fibonacci

55Completion Rate (CR)

1

Jun 4, 2026

—

—Primary metric

0

May 29, 2026

—

—Primary metric

0

Apr 23, 2026

—

—Primary metric

0

Mar 4, 2026

Zero-D Reactor Combustion v1 (test)

—

—Primary metric

0

Feb 26, 2026

LiveCodeBench until train step 80 v6

—

—Primary metric

0

Feb 26, 2026

—

—Pass@1

0

Feb 26, 2026

Page 40 of 40

Popular datasets

HumanEval MBPP LiveCodeBench BigCodeBench LCB

Follow for updates

Join SOTA2 Contact