{
 "body": "\nPart of the [MultiPL-E](multipl_e.md) family.\n\n## What it measures\n\nJavaScript is a dynamically typed, garbage-collected scripting language that runs in browsers and on Node.js. MultiPL-E translates the HumanEval and MBPP prompts into JavaScript by rewriting\nthe function signature, docstring and tests with JavaScript's own syntax and type system, then asks the\nmodel to complete the function body. The nuprl/MultiPL-E dataset card lists 161 HumanEval-derived items\nand 397 MBPP-derived items for JavaScript, both a little short of the original Python pools because a\nhandful of problems could not be ported faithfully. Completions run against a real JavaScript toolchain\ninside a container and are checked against the translated tests; there is no partial credit for a\ncompletion that fails to compile or fails any test.\n\n## Reading the numbers\n\nA high pass@1 here shows a model can produce working JavaScript for short, self-contained problems whose\nlogic it likely already knows from Python; it does not test JavaScript-specific idiom, library or ecosystem\nknowledge beyond what one function needs. Compare this score against `multipl_e_python` and other\nMultiPL-E language pages for the same model: a large gap usually reflects less JavaScript in the model's\ntraining data rather than a difference in reasoning ability. See the [MultiPL-E](multipl_e.md) family\npage for dataset licence, contamination and harness details shared by every language in the family.\n",
 "build": {
  "built_at": "2026-09-09T16:56:50+00:00",
  "commit": "0a599558854c0e238c03a0f0d725239cb28f9d11",
  "eligibility_as_of": "2026-09-09"
 },
 "disposition": {
  "canonical_id": "multipl_e_javascript",
  "reasons": [],
  "status": "unassessed",
  "verified_results": []
 },
 "models_covered": [
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "Claude Opus 4",
   "model_id": "anthropic/claude-opus-4-20250514",
   "provider": "anthropic",
   "provider_display": "Anthropic",
   "score": 91.5,
   "source": "lmarena.ai, provider-reports, multimodal-evals, safety-evals, preference-evals, domain-evals"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "Claude Opus 4.6",
   "model_id": "anthropic/claude-opus-4-6",
   "provider": "anthropic",
   "provider_display": "Anthropic",
   "score": 91.5,
   "source": "lmarena.ai, provider-reports, multimodal-evals, safety-evals, preference-evals, domain-evals, anthropic-system-card-mythos"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "Claude Sonnet 4",
   "model_id": "anthropic/claude-sonnet-4-20250514",
   "provider": "anthropic",
   "provider_display": "Anthropic",
   "score": 89.5,
   "source": "lmarena.ai, provider-reports, multimodal-evals, safety-evals, preference-evals"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "Claude Sonnet 4.5",
   "model_id": "anthropic/claude-sonnet-4-5-20250929",
   "provider": "anthropic",
   "provider_display": "Anthropic",
   "score": 89.5,
   "source": "lmarena.ai, provider-reports, multimodal-evals, safety-evals, preference-evals"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "Claude Sonnet 4.5 (latest)",
   "model_id": "anthropic/claude-sonnet-4-5",
   "provider": "anthropic",
   "provider_display": "Anthropic",
   "score": 89.5,
   "source": "lmarena.ai, provider-reports, multimodal-evals, safety-evals, preference-evals"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "GPT-4.1",
   "model_id": "openai/gpt-4-1",
   "provider": "openai",
   "provider_display": "OpenAI",
   "score": 88.2,
   "source": "lmarena.ai, provider-reports, multimodal-evals, safety-evals, domain-evals preference-evals, llm-stats, intlpull"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "Gemini 2.5 Pro",
   "model_id": "google/gemini-2-5-pro",
   "provider": "google",
   "provider_display": "Google DeepMind",
   "score": 87.5,
   "source": "lmarena.ai, provider-reports, multimodal-evals, safety-evals, preference-evals, domain-evals, llm-stats, intlpull"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "DeepSeek R1",
   "model_id": "deepseek/deepseek-r1",
   "provider": "deepseek",
   "provider_display": "DeepSeek",
   "score": 86.8,
   "source": "lmarena.ai, provider-reports, preference-evals, open-llm-leaderboard-v2, domain-evals"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "DeepSeek R1 0528",
   "model_id": "deepseek/deepseek-r1-0528",
   "provider": "deepseek",
   "provider_display": "DeepSeek",
   "score": 86.8,
   "source": "lmarena.ai, provider-reports, preference-evals, open-llm-leaderboard-v2, domain-evals"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "DeepSeek R1 0528 NVFP4 v2",
   "model_id": "nvidia/deepseek-r1-0528-nvfp4-v2",
   "provider": "nvidia",
   "provider_display": "NVIDIA",
   "score": 86.8,
   "source": "lmarena.ai, provider-reports, preference-evals, open-llm-leaderboard-v2"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "DeepSeek Reasoner",
   "model_id": "deepseek/deepseek-reasoner",
   "provider": "deepseek",
   "provider_display": "DeepSeek",
   "score": 86.8,
   "source": "lmarena.ai, provider-reports, preference-evals, open-llm-leaderboard-v2, llm-stats"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "GPT-4o",
   "model_id": "openai/gpt-4o",
   "provider": "openai",
   "provider_display": "OpenAI",
   "score": 85.8,
   "source": "lmarena.ai, provider-reports, multimodal-evals, safety-evals, preference-evals, domain-evals, llm-stats, intlpull"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "GPT-4o (2024-05-13)",
   "model_id": "openai/gpt-4o-2024-05-13",
   "provider": "openai",
   "provider_display": "OpenAI",
   "score": 85.8,
   "source": "lmarena.ai, provider-reports, multimodal-evals, safety-evals, preference-evals, domain-evals, llm-stats, intlpull"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "GPT-4o (2024-08-06)",
   "model_id": "openai/gpt-4o-2024-08-06",
   "provider": "openai",
   "provider_display": "OpenAI",
   "score": 85.8,
   "source": "lmarena.ai, provider-reports, multimodal-evals, safety-evals, preference-evals, domain-evals, llm-stats, intlpull"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "GPT-4o (2024-11-20)",
   "model_id": "openai/gpt-4o-2024-11-20",
   "provider": "openai",
   "provider_display": "OpenAI",
   "score": 85.8,
   "source": "lmarena.ai, provider-reports, multimodal-evals, safety-evals, preference-evals, domain-evals, llm-stats, intlpull"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "GPT-4o mini",
   "model_id": "openai/gpt-4o-mini",
   "provider": "openai",
   "provider_display": "OpenAI",
   "score": 85.8,
   "source": "lmarena.ai, provider-reports, multimodal-evals, safety-evals, preference-evals, domain-evals, llm-stats, intlpull"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "Qwen2.5 Coder 32B Instruct",
   "model_id": "qwen/qwen2-5-coder-32b-instruct",
   "provider": "qwen",
   "provider_display": "Alibaba / Qwen Team",
   "score": 82.1,
   "source": "provider-reports, open-llm-leaderboard-v2"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "Qwen2.5 Coder 32B Instruct AWQ",
   "model_id": "qwen/qwen2-5-coder-32b-instruct-awq",
   "provider": "qwen",
   "provider_display": "Alibaba / Qwen Team",
   "score": 82.1,
   "source": "provider-reports, open-llm-leaderboard-v2"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "Gemma 4 31B",
   "model_id": "google/gemma-4-31b",
   "provider": "google",
   "provider_display": "Google DeepMind",
   "score": 79.5,
   "source": "lmarena.ai, provider-reports, multimodal-evals, open-llm-leaderboard-v2"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "gemma 4 31B it",
   "model_id": "google/gemma-4-31b-it",
   "provider": "google",
   "provider_display": "Google DeepMind",
   "score": 79.5,
   "source": "lmarena.ai, provider-reports, multimodal-evals, open-llm-leaderboard-v2"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "gemma 4 31B it GGUF",
   "model_id": "unsloth/gemma-4-31b-it-gguf",
   "provider": "unsloth",
   "provider_display": "Unsloth",
   "score": 79.5,
   "source": "lmarena.ai, provider-reports, multimodal-evals, open-llm-leaderboard-v2"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "Gemma 4 31B IT NVFP4",
   "model_id": "nvidia/gemma-4-31b-it-nvfp4",
   "provider": "nvidia",
   "provider_display": "NVIDIA",
   "score": 79.5,
   "source": "lmarena.ai, provider-reports, multimodal-evals, open-llm-leaderboard-v2"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "Mistral Large (latest)",
   "model_id": "mistral/mistral-large-latest",
   "provider": "mistral",
   "provider_display": "Mistral AI",
   "score": 78.8,
   "source": "lmarena.ai, provider-reports, multimodal-evals, safety-evals, preference-evals, open-llm-leaderboard-v2, llm-stats"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "Mistral Large 2.1",
   "model_id": "mistral/mistral-large-2411",
   "provider": "mistral",
   "provider_display": "Mistral AI",
   "score": 78.8,
   "source": "lmarena.ai, provider-reports, safety-evals, preference-evals,, domain-evals open-llm-leaderboard-v2"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "Mistral Large 3",
   "model_id": "mistral/mistral-large-2512",
   "provider": "mistral",
   "provider_display": "Mistral AI",
   "score": 78.8,
   "source": "lmarena.ai, provider-reports, multimodal-evals, safety-evals, preference-evals, open-llm-leaderboard-v2"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "Codestral (latest)",
   "model_id": "mistral/codestral-latest",
   "provider": "mistral",
   "provider_display": "Mistral AI",
   "score": 78.2,
   "source": "lmarena.ai, provider-reports"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "Gemma 4 26B",
   "model_id": "google/gemma-4-26b",
   "provider": "google",
   "provider_display": "Google DeepMind",
   "score": 77.5,
   "source": "lmarena.ai, provider-reports, open-llm-leaderboard-v2"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "Qwen2.5 Coder 14B Instruct",
   "model_id": "qwen/qwen2-5-coder-14b-instruct",
   "provider": "qwen",
   "provider_display": "Alibaba / Qwen Team",
   "score": 76.5,
   "source": "bigcode-leaderboard, provider-reports, open-llm-leaderboard-v2"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "Llama 3.3 70B Instruct NVFP4",
   "model_id": "nvidia/llama-3-3-70b-instruct-nvfp4",
   "provider": "nvidia",
   "provider_display": "NVIDIA",
   "score": 75.8,
   "source": "lmarena.ai, provider-reports, safety-evals, preference-evals, open-llm-leaderboard-v2, llm-stats"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "Llama-3.3-70B-Instruct",
   "model_id": "meta/llama-3-3-70b-instruct",
   "provider": "meta",
   "provider_display": "Meta",
   "score": 75.8,
   "source": "lmarena.ai, provider-reports, safety-evals, preference-evals, open-llm-leaderboard-v2, llm-stats"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "phi 4",
   "model_id": "microsoft/phi-4",
   "provider": "microsoft",
   "provider_display": "Microsoft",
   "score": 74.2,
   "source": "lmarena.ai, provider-reports, preference-evals, open-llm-leaderboard-v2,, domain-evals llm-stats"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "Phi 4 mini instruct",
   "model_id": "microsoft/phi-4-mini-instruct",
   "provider": "microsoft",
   "provider_display": "Microsoft",
   "score": 74.2,
   "source": "lmarena.ai, provider-reports, preference-evals, llm-stats, open-llm-leaderboard-v2"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "Llama 3.1 70B",
   "model_id": "meta/llama-3-1-70b",
   "provider": "meta",
   "provider_display": "Meta",
   "score": 73.5,
   "source": "lmarena.ai, provider-reports, safety-evals, domain-evals, open-llm-leaderboard-v2"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "Llama 3.1 70B Instruct",
   "model_id": "meta/llama-3-1-70b-instruct",
   "provider": "meta",
   "provider_display": "Meta",
   "score": 73.5,
   "source": "lmarena.ai, provider-reports, safety-evals, domain-evals, open-llm-leaderboard-v2"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "Qwen2.5 Coder 7B Instruct",
   "model_id": "qwen/qwen2-5-coder-7b-instruct",
   "provider": "qwen",
   "provider_display": "Alibaba / Qwen Team",
   "score": 70.2,
   "source": "bigcode-leaderboard, provider-reports, open-llm-leaderboard-v2"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "Qwen2.5 Coder 7B Instruct GPTQ Int4",
   "model_id": "qwen/qwen2-5-coder-7b-instruct-gptq-int4",
   "provider": "qwen",
   "provider_display": "Alibaba / Qwen Team",
   "score": 70.2,
   "source": "bigcode-leaderboard, provider-reports, open-llm-leaderboard-v2"
  },
  {
   "as_of": "2026-04",
   "attribution": "unverified-legacy",
   "display_name": "CodeLlama 34B Instruct hf",
   "model_id": "meta/codellama-34b-instruct-hf",
   "provider": "meta",
   "provider_display": "Meta",
   "score": 62.1,
   "source": "bigcode-leaderboard, provider-reports, open-llm-leaderboard-v1"
  }
 ],
 "page": {
  "aliases": [],
  "category": "coding",
  "contamination": {
   "note": "Inherits the source HumanEval/MBPP contamination risk (public since 2021-2022); see the multipl_e family page for detail.",
   "risk": "high"
  },
  "dataset": {
   "languages": [
    "JavaScript"
   ],
   "license": "MIT",
   "modalities": [
    "code"
   ],
   "public_test_set": true,
   "size": null,
   "size_note": "Reading the nuprl/MultiPL-E dataset card on 2026-09-07: 161 HumanEval-derived items (of the original 164) and 397 MBPP-derived items, both a little short of the full Python originals because a handful of problems could not be ported to JavaScript faithfully.",
   "splits": "test (humaneval-js and mbpp-js configs)",
   "url": "https://huggingface.co/datasets/nuprl/MultiPL-E"
  },
  "freshness": {
   "researched": "2026-09-07",
   "researched_by": "sonnet-5 agent, batch 1, slice C",
   "reviewed": "",
   "reviewed_by": ""
  },
  "harness": {
   "bigbench": "",
   "helm": "",
   "inspect_evals": "",
   "lm_eval": "",
   "opencompass": "",
   "other": "bigcode-evaluation-harness task multiple-js"
  },
  "id": "multipl_e_javascript",
  "last_updated": "",
  "leaderboard_url": "",
  "lineage": {
   "family": "multipl_e",
   "predecessor": "",
   "successors": [],
   "variants": []
  },
  "measures": "This subset translates the HumanEval and MBPP prompts into JavaScript by rewriting each problem's function signature, docstring and tests with JavaScript syntax and typing, then asks the model to complete the function body in JavaScript. The underlying algorithmic problem is unchanged from the Python original; only the surface language differs.\n",
  "metric": {
   "baseline_note": "No published human baseline.",
   "direction": "higher_is_better",
   "human_baseline": null,
   "max_score": 100,
   "name": "pass@1",
   "random_baseline": 0,
   "unit": "%"
  },
  "name": "MultiPL-E: JavaScript",
  "page_kind": "subset",
  "paper": {
   "arxiv": "2208.08227",
   "title": "MultiPL-E: A Scalable and Extensible Approach to Benchmarking Neural Code Generation",
   "url": "https://arxiv.org/abs/2208.08227",
   "year": 2022
  },
  "publisher": {
   "authors": [
    "Federico Cassano",
    "John Gouwar",
    "Daniel Nguyen",
    "Sydney Nguyen",
    "Luna Phipps-Costin",
    "Donald Pinckney",
    "Ming-Ho Yee",
    "Yangtian Zi",
    "Carolyn Jane Anderson",
    "Molly Q Feldman",
    "Arjun Guha",
    "Michael Greenberg",
    "Abhinav Jangda"
   ],
   "org": "Northeastern University Programming Research Lab (nuprl)",
   "url": "https://github.com/nuprl/MultiPL-E"
  },
  "released": "2022-08",
  "repo_url": "https://github.com/nuprl/MultiPL-E",
  "saturation": {
   "as_of": "",
   "note": "Not established at the per-language level; see the multipl_e family page for the general pattern of high-resource versus low-resource language spread.",
   "status": "unknown",
   "top_score": null
  },
  "sources": [
   {
    "accessed": "2026-09-07",
    "title": "MultiPL-E: A Scalable and Extensible Approach to Benchmarking Neural Code Generation",
    "url": "https://arxiv.org/abs/2208.08227"
   },
   {
    "accessed": "2026-09-07",
    "title": "nuprl/MultiPL-E dataset card",
    "url": "https://huggingface.co/datasets/nuprl/MultiPL-E"
   },
   {
    "accessed": "2026-09-07",
    "title": "nuprl/MultiPL-E repository",
    "url": "https://github.com/nuprl/MultiPL-E"
   }
  ],
  "status": "active",
  "subcategory": "multilingual code generation",
  "summary": "The JavaScript subset of MultiPL-E: HumanEval and MBPP function-completion problems translated into JavaScript and scored with pass@1.",
  "tags": [
   "code-generation",
   "javascript",
   "pass-at-k",
   "humaneval",
   "mbpp"
  ],
  "task_format": "Function completion in JavaScript: given a translated signature, docstring and (for HumanEval-derived items) doctests, the model generates a function body, which is compiled or interpreted with a real JavaScript toolchain inside a container and checked against translated unit tests.\n"
 }
}