The R subset of MultiPL-E: HumanEval and MBPP function-completion problems translated into R and scored with pass@1.
unassessed
| Category | coding |
|---|---|
| Subcategory | multilingual code generation |
| Page status | active |
| Metric | pass@1 |
| Direction | higher_is_better |
| Unit | % |
| Dataset licence | MIT |
| Publisher | Northeastern University Programming Research Lab (nuprl) |
This subset translates the HumanEval and MBPP prompts into R by rewriting each problem's function signature, docstring and tests with R syntax and typing, then asks the model to complete the function body in R. The underlying algorithmic problem is unchanged from the Python original; only the surface language differs.
Function completion in R: 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 R toolchain inside a container and checked against translated unit tests.
| Model | Provider | Score | Card as of |
|---|---|---|---|
| GPT-5.1 | OpenAI | 69.5 | 2026-04 |
| GPT-5.1 Chat | OpenAI | 69.5 | 2026-04 |
| GPT-5.1 Codex | OpenAI | 69.5 | 2026-04 |
| GPT-5.1 Codex Max | OpenAI | 69.5 | 2026-04 |
| GPT-5.1 Codex mini | OpenAI | 69.5 | 2026-04 |
| Claude Opus 4 | Anthropic | 68.5 | 2026-04 |
| Claude Opus 4.6 | Anthropic | 68.5 | 2026-04 |
| GPT-5 | OpenAI | 68.2 | 2026-04 |
| GPT-5 Chat (latest) | OpenAI | 68.2 | 2026-04 |
| GPT-5 Mini | OpenAI | 68.2 | 2026-04 |
| GPT-5 Nano | OpenAI | 68.2 | 2026-04 |
| GPT-5 Pro | OpenAI | 68.2 | 2026-04 |
| GPT-5-Codex | OpenAI | 68.2 | 2026-04 |
| GPT-5.2 | OpenAI | 68.2 | 2026-04 |
| GPT-5.2 Chat | OpenAI | 68.2 | 2026-04 |
| GPT-5.2 Codex | OpenAI | 68.2 | 2026-04 |
| GPT-5.2 Pro | OpenAI | 68.2 | 2026-04 |
| GPT-5.3 Chat (latest) | OpenAI | 68.2 | 2026-04 |
| GPT-5.3 Codex | OpenAI | 68.2 | 2026-04 |
| GPT-5.3 Codex Spark | OpenAI | 68.2 | 2026-04 |
| GPT-5.4 | OpenAI | 68.2 | 2026-04 |
| GPT-5.4 mini | OpenAI | 68.2 | 2026-04 |
| GPT-5.4 nano | OpenAI | 68.2 | 2026-04 |
| GPT-5.4 Pro | OpenAI | 68.2 | 2026-04 |
| Claude Opus 4.5 | Anthropic | 67.8 | 2026-04 |
| Claude Opus 4.5 (latest) | Anthropic | 67.8 | 2026-04 |
| o3 | OpenAI | 67.5 | 2026-04 |
| Claude Sonnet 4.6 | Anthropic | 66.8 | 2026-04 |
| Claude Opus 4.1 | Anthropic | 66.5 | 2026-04 |
| Claude Opus 4.1 (latest) | Anthropic | 66.5 | 2026-04 |
| Qwen3-Coder 480B-A35B Instruct | Alibaba / Qwen Team | 66.5 | 2026-04 |
| Claude Sonnet 4 | Anthropic | 65.2 | 2026-04 |
| Claude Sonnet 4.5 | Anthropic | 65.2 | 2026-04 |
| Claude Sonnet 4.5 (latest) | Anthropic | 65.2 | 2026-04 |
| Gemini 2.5 Pro | Google DeepMind | 64.8 | 2026-04 |
| Grok 4 | xAI | 64.5 | 2026-04 |
| Grok 4 Fast | xAI | 64.5 | 2026-04 |
| Grok 4 Fast (Non-Reasoning) | xAI | 64.5 | 2026-04 |
| Grok 4.1 Fast | xAI | 64.5 | 2026-04 |
| Grok 4.1 Fast (Non-Reasoning) | xAI | 64.5 | 2026-04 |
| Grok 4.20 (Non-Reasoning) | xAI | 64.5 | 2026-04 |
| Grok 4.20 (Reasoning) | xAI | 64.5 | 2026-04 |
| Grok 4.20 Multi-Agent | xAI | 64.5 | 2026-04 |
| Claude Opus 4 (latest) | Anthropic | 64.2 | 2026-04 |
| o4-mini | OpenAI | 63.8 | 2026-04 |
| o4-mini-deep-research | OpenAI | 63.8 | 2026-04 |
| GPT-4.1 | OpenAI | 63.5 | 2026-04 |
| Qwen3 235B-A22B | Alibaba / Qwen Team | 62.5 | 2026-04 |
| Claude Sonnet 4 (latest) | Anthropic | 62.1 | 2026-04 |
| DeepSeek V3.2 Exp | DeepSeek | 61.5 | 2026-04 |
| Claude Sonnet 3.7 | Anthropic | 60.5 | 2026-04 |
| GPT-4o | OpenAI | 60.5 | 2026-04 |
| GPT-4o (2024-05-13) | OpenAI | 60.5 | 2026-04 |
| GPT-4o (2024-08-06) | OpenAI | 60.5 | 2026-04 |
| GPT-4o (2024-11-20) | OpenAI | 60.5 | 2026-04 |
| o3-mini | OpenAI | 60.5 | 2026-04 |
| DeepSeek R1 0528 | DeepSeek | 60.2 | 2026-04 |
| DeepSeek R1 0528 NVFP4 v2 | NVIDIA | 60.2 | 2026-04 |
| DeepSeek V3.2 | DeepSeek | 60.2 | 2026-04 |
| DeepSeek R1 | DeepSeek | 58.5 | 2026-04 |
| DeepSeek Reasoner | DeepSeek | 58.5 | 2026-04 |
| Claude Sonnet 3.5 | Anthropic | 58.2 | 2026-04 |
| Claude Sonnet 3.5 v2 | Anthropic | 58.2 | 2026-04 |
| GPT-4 Turbo | OpenAI | 58.2 | 2026-04 |
| Claude Haiku 4.5 | Anthropic | 56.8 | 2026-04 |
| Claude Haiku 4.5 (latest) | Anthropic | 56.8 | 2026-04 |
| Grok 3 | xAI | 56.8 | 2026-04 |
| Grok 3 Fast | xAI | 56.8 | 2026-04 |
| Grok 3 Fast Latest | xAI | 56.8 | 2026-04 |
| Grok 3 Latest | xAI | 56.8 | 2026-04 |
| Grok 3 Mini | xAI | 56.8 | 2026-04 |
| Grok 3 Mini Fast | xAI | 56.8 | 2026-04 |
| Grok 3 Mini Fast Latest | xAI | 56.8 | 2026-04 |
| Grok 3 Mini Latest | xAI | 56.8 | 2026-04 |
| DeepSeek V3.1 | DeepSeek | 56.5 | 2026-04 |
| Gemini 2.5 Flash | Google DeepMind | 56.2 | 2026-04 |
| Gemini 2.5 Flash Image | Google DeepMind | 56.2 | 2026-04 |
| Gemini 2.5 Flash Image (Preview) | Google DeepMind | 56.2 | 2026-04 |
| Gemini 2.5 Flash Lite | Google DeepMind | 56.2 | 2026-04 |
| Gemini 2.5 Flash Lite Preview 06-17 | Google DeepMind | 56.2 | 2026-04 |
| Gemini 2.5 Flash Lite Preview 09-25 | Google DeepMind | 56.2 | 2026-04 |
| Gemini 2.5 Flash Preview 04-17 | Google DeepMind | 56.2 | 2026-04 |
| Gemini 2.5 Flash Preview 05-20 | Google DeepMind | 56.2 | 2026-04 |
| Gemini 2.5 Flash Preview 09-25 | Google DeepMind | 56.2 | 2026-04 |
| Gemini 2.5 Flash Preview TTS | Google DeepMind | 56.2 | 2026-04 |
| Qwen3 32B | Alibaba / Qwen Team | 55.5 | 2026-04 |
| Qwen3 32B AWQ | Alibaba / Qwen Team | 55.5 | 2026-04 |
| Qwen3 32B NVFP4 | NVIDIA | 55.5 | 2026-04 |
| Mistral Large (latest) | Mistral AI | 55.2 | 2026-04 |
| Mistral Large 2.1 | Mistral AI | 55.2 | 2026-04 |
| Mistral Large 3 | Mistral AI | 55.2 | 2026-04 |
| DeepSeek V3 0324 | DeepSeek | 54.2 | 2026-04 |
| GPT-4 | OpenAI | 52.8 | 2026-04 |
| GPT-4.1 mini | OpenAI | 52.8 | 2026-04 |
| GPT-4.1 nano | OpenAI | 52.8 | 2026-04 |
| Claude Opus 3 | Anthropic | 52.5 | 2026-04 |
| DeepSeek Chat | DeepSeek | 52.5 | 2026-04 |
| DeepSeek V3 | DeepSeek | 52.5 | 2026-04 |
| Llama 4 Maverick 17B 128E Instruct | Meta | 52.2 | 2026-04 |
| Llama-4-Maverick-17B-128E-Instruct-FP8 | Meta | 52.2 | 2026-04 |
| Gemma 4 31B | Google DeepMind | 50.5 | 2026-04 |
| gemma 4 31B it | Google DeepMind | 50.5 | 2026-04 |
| gemma 4 31B it GGUF | Unsloth | 50.5 | 2026-04 |
| Gemma 4 31B IT NVFP4 | NVIDIA | 50.5 | 2026-04 |
| Qwen2.5 72B Instruct | Alibaba / Qwen Team | 50.5 | 2026-04 |
| GPT-4o mini | OpenAI | 50.2 | 2026-04 |
| Llama 4 Scout 17B 16E | Meta | 48.8 | 2026-04 |
| Llama 4 Scout 17B 16E Instruct | Meta | 48.8 | 2026-04 |
| Llama-4-Scout-17B-16E-Instruct-FP8 | Meta | 48.8 | 2026-04 |
| Claude Haiku 3.5 | Anthropic | 48.5 | 2026-04 |
| Claude Haiku 3.5 (latest) | Anthropic | 48.5 | 2026-04 |
| Llama 3.3 70B Instruct NVFP4 | NVIDIA | 48.5 | 2026-04 |
| Llama-3.3-70B-Instruct | Meta | 48.5 | 2026-04 |
| Mistral Medium (latest) | Mistral AI | 48.5 | 2026-04 |
| Mistral Medium 3 | Mistral AI | 48.5 | 2026-04 |
| Mistral Medium 3.1 | Mistral AI | 48.5 | 2026-04 |
| Gemma 4 26B | Google DeepMind | 48.2 | 2026-04 |
| phi 4 | Microsoft | 48.2 | 2026-04 |
| Llama 3.1 70B | Meta | 46.5 | 2026-04 |
| Llama 3.1 70B Instruct | Meta | 46.5 | 2026-04 |
| Mistral Small (latest) | Mistral AI | 40.5 | 2026-04 |
| Mistral Small 24B Instruct 2501 | Mistral AI | 40.5 | 2026-04 |
| Mistral Small 3.1 24B Instruct 2503 | Mistral AI | 40.5 | 2026-04 |
| Mistral Small 3.2 | Mistral AI | 40.5 | 2026-04 |
| Mistral Small 3.2 24B Instruct 2506 | Mistral AI | 40.5 | 2026-04 |
| Mistral Small 4 | Mistral AI | 40.5 | 2026-04 |
| Mistral Small 4 119B 2603 | Mistral AI | 40.5 | 2026-04 |
| Phi 4 mini instruct | Microsoft | 36.5 | 2026-04 |
| CodeLlama 34B Instruct hf | Meta | 28.5 | 2026-04 |