CodingDeprecated
Trust Score:
10

MultiPL-E

Parallel HumanEval and MBPP translations for comparing code generation across many programming languages.

Launched: Refresh: static
Status Assessment (deprecated):

The original MultiPL-HumanEval axis is a static translation of 161 public HumanEval tasks and inherits HumanEval exposure and ceiling. The official repository now points readers to Ag-LiveCodeBench-X for a more challenging multilingual evaluation.

Performance Timeline

Longitudinal progression of model scores against human baselines.

Performance & Historical Trajectory

Empirical score progression across model release dates and evaluation rounds.

Independent Vendor-Reported Human Baseline (88.5%)
ModelScoreDateSource TypeProvenance
SantaCoder-1.1B (MultiPL-HumanEval Python, pass@1)18%2023-01-09vendor-reportedSource ↗
InCoder-6.7B (MultiPL-HumanEval Python, pass@1)15.2%2022-08-17independentSource ↗
code-davinci-002 (MultiPL-HumanEval Python, pass@1)47%2022-08-17independentSource ↗

Human Baseline & Difficulty Horizon

Calibrated human reference points, specialist benchmarks, and ceiling thresholds.
Measured Human Score88.5%Domain Expert Baseline
Baseline Protocol & Interpretation

Human programming accuracy across 18 programming languages derived from HumanEval.

Metric & Scoring Methodology

Verification protocols, aggregation formulas, and specialized metric variants.
Primary Metric:pass@1 by programming language (%)
Scoring Engine:unit-tests

Dataset & Compute Cost

Evaluation volume, public availability, API pricing, and local hardware requirements.
Total Dataset Size2,898Annotated evaluation items
Public Test SetPublicOpenly mirrored on repositories
Access GatingOpen AccessUnrestricted download
Evaluation LicenseOpen AccessDataset usage and redistribution terms
Frontier API Compute Cost:

$5 – $20 USD for full benchmark evaluation run on frontier APIs.

Recommended Local GPU Setup:

1x NVIDIA RTX 4090 (24GB) or A100 (40GB/80GB) via vLLM / SGLang

Official Dataset & Benchmark Files:Download / View Dataset Repository ↗

How to Run & Reproduce

Standardized evaluation protocols, CLI commands, and reproducible runner templates.
Prompt Regimezero-shot
Reasoning Modedirect
Sampling Temp0
Pass@k Budgetk = 1
Tools & SandboxPure Text
Scoring Verifierunit-tests
Option AEleutherAI LM-Evaluation-Harness (Open-Weight Models)
lm_eval --model hf --model_args pretrained=<model_path> --tasks multi-pl-e --batch_size auto
Option BOpenCompass Evaluation Framework
opencompass --datasets multi-pl-e --models <model_config>
Python APIDeterministic Inference Loop Snippet
# Standard API Evaluation Loop
from openai import OpenAI

client = OpenAI()
response = client.chat.completions.create(
    model="gpt-4o",
    messages=[{"role": "user", "content": prompt}],
    temperature=0.0,
)
Standardized Reporting Requirement:

When publishing results for MultiPL-E, always report the exact prompt template, few-shot exemplar ordering, sampling temperature (temperature=0), maximum reasoning budget tokens, and the precise timestamped model snapshot ID.

Contamination & Memorization Analysis

Audit of pretraining exposure risks, memorization vectors, and refresh policies.
Overall Contamination Risk:HIGH
Refresh Cadence:

Static fixed snapshot

Test Set Exposure:

Public on web / HuggingFace