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 32 · SOTA2 Research

Code Generation

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

LiveCodeBench HumanEval, HumanEval+, MBPP, MBPP+ (queries from Eurus-RL-Code) v6 (test)

43.2LCB v6 Accuracy

5

May 14, 2026

LiveCodeBench 50/50 calibration (test)

Diagnostic learned router

64.9CR (%)

5

May 8, 2026

HumanEval Random Span (prefix only)

82.4Pass@1

5

May 8, 2026

LCB monolingual

96.44RPR

5

Apr 30, 2026

LCB cross-lingual

58.28RPR

5

Apr 30, 2026

34.02Average Score

5

Apr 30, 2026

LiveCodeBench v6

37.14Accuracy

5

Apr 21, 2026

LiveCodeBench (OOD)

19.2Accuracy

5

Apr 16, 2026

27.8Accuracy

5

Apr 16, 2026

5.86TPF

5

Apr 10, 2026

42.18Accuracy

5

Mar 20, 2026

LCB v5 (evaluation)

GASP + Real-data RL

19.93Pass@1

5

Mar 18, 2026

34.2Pass@1

5

Feb 27, 2026

CodeAlpaca code-generation (test)

Full FT Sequential

4.12Perplexity (PPL)

5

Feb 26, 2026

HumanEval-Instruct 0-shot (test)

79.9TPS

5

Feb 26, 2026

97.78Base Pass Rate

5

Feb 26, 2026

MiMo-VL RL-2508

82.54Accuracy

5

Feb 26, 2026

133 PowerShell CodeGen prompts

46FRate (%)

5

Feb 26, 2026

Bolmo Evaluation Suite Code 7B

0.407Average Code Score

5

Feb 26, 2026

85Performance

5

Feb 26, 2026

314.99TPS

5

Feb 26, 2026

LiveCodeBench Hard v5

NSED (High-Perf open-weight)

64.5Pass@1

5

Feb 26, 2026

15.04Score

5

Feb 26, 2026

Coding Gender (test)

40Cor (%)

5

Feb 26, 2026

Coding Race (test)

57Correctness Rate

5

Feb 26, 2026

Page 32 of 40

Popular datasets

HumanEval MBPP LiveCodeBench BigCodeBench LCB

Follow for updates

Join SOTA2 Contact