Pith Number

pith:KZDVXHMN

pith:2024:KZDVXHMN6OXBF3ESRTXYRQTNPG

not attested not anchored not stored refs resolved

CRUXEval: A Benchmark for Code Reasoning, Understanding and Execution

Alex Gu, Armando Solar-Lezama, Baptiste Rozi\`ere, Gabriel Synnaeve, Hugh Leather, Sida I. Wang

CRUXEval benchmark reveals GPT-4 with chain-of-thought reaches only 75% and 81% on input and output prediction for short Python functions.

arxiv:2401.03065 v1 · 2024-01-05 · cs.SE · cs.AI · cs.LG

Open paper page JSON Open Graph Bundle Merged state Verified badge What is a Pith Number?

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{KZDVXHMN6OXBF3ESRTXYRQTNPG}

Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge

Record completeness

1 Bitcoin timestamp

2 Internet Archive

3 Author claim open · sign in to claim

4 Citations open

5 Replications open

✓ Portable graph bundle live · download bundle · merged state

The bundle contains the canonical record plus signed events. A mirror can host it anywhere and recompute the same current state with the deterministic merge algorithm.

Claims

C1strongest claim

The best setup, GPT-4 with chain of thought (CoT), achieves a pass@1 of 75% and 81% on input and output prediction, respectively. In contrast, Code Llama 34B achieves a pass@1 of 50% and 46% on input and output prediction.

C2weakest assumption

That the 800 generated functions and their input-output pairs sufficiently represent the range of code reasoning and execution challenges encountered in practical programming.

C3one line summary

CRUXEval benchmark shows current code models including GPT-4 achieve at most 81% on input and output prediction for short Python functions, exposing gaps not captured by HumanEval.

References

26 extracted · 26 resolved · 2 Pith anchors

[1] A parallel corpus of Python functions and documentation strings for automated code documentation and code generation 2017 · arXiv:1707.02275

[2] Rishi Hazra, Gabriele Venturato, Pedro Zuidberg Dos Martires, and Luc De Raedt 2023

[3] CodeSearchNet Challenge: Evaluating the State of Semantic Code Search 1909 · arXiv:1909.09436

[4] arXiv preprint arXiv:2305.05383 , year= 2020

[5] arXiv preprint arXiv:2401.00595 , year = 2022

Formal links

1 machine-checked theorem link

Cited by

33 papers in Pith

CodeMind: Evaluating Large Language Models for Code Reasoning

CodeFlowBench: A Multi-turn, Iterative Benchmark for Complex Code Generation

STRIDE: Learnable Stepwise Language Feedback for LLM Reasoning

Enhancing the Code Reasoning Capabilities of LLMs via Consistency-based Reinforcement Learning

Code as Agent Harness

Receipt and verification

First computed	2026-05-17T23:39:21.763738Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

56475b9d8df3ae12ec928cef88c26d79b2c031c404fb081e55ef01c218e157f5

Aliases

arxiv: 2401.03065 · arxiv_version: 2401.03065v1 · doi: 10.48550/arxiv.2401.03065 · pith_short_12: KZDVXHMN6OXB · pith_short_16: KZDVXHMN6OXBF3ES · pith_short_8: KZDVXHMN

Agent API

Resolver JSON Graph JSON Events JSON Schema Signing key

Verify this Pith Number yourself

curl -sH 'Accept: application/ld+json' https://pith.science/pith/KZDVXHMN6OXBF3ESRTXYRQTNPG \
  | jq -c '.canonical_record' \
  | python3 -c "import sys,json,hashlib; b=json.dumps(json.loads(sys.stdin.read()), sort_keys=True, separators=(',',':'), ensure_ascii=False).encode(); print(hashlib.sha256(b).hexdigest())"
# expect: 56475b9d8df3ae12ec928cef88c26d79b2c031c404fb081e55ef01c218e157f5

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "4c190e234dc0fa17a55b121a20712b031c4c0e5b120b7649118471d954ff9ab4",
    "cross_cats_sorted": [
      "cs.AI",
      "cs.LG"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.SE",
    "submitted_at": "2024-01-05T20:53:51Z",
    "title_canon_sha256": "1700e7185c043a55a5a1a9139892df67d8d35d960960ccb5cd1594d2edcc500b"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2401.03065",
    "kind": "arxiv",
    "version": 1
  }
}