An Execution-Verified Multi-Language Benchmark for Code Semantic Reasoning

• URL: http://arxiv.org/abs/2605.11006v1
• Date: Sun, 10 May 2026 07:17:00 GMT
• Title: An Execution-Verified Multi-Language Benchmark for Code Semantic Reasoning
• Abstract summary: TraceEval is the first execution-verified, multi-language benchmark for code semantic reasoning.<n>TraceEval consists of 10,583 real-world programs extracted from 1,600+ open-source repositories across Python, JavaScript, and Java.<n>The strongest model, Claude-Opus-4.6, reaches an average F1 of 72.9% across the three languages.
• Score: 10.815335026032377
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Evaluating whether large language models (LLMs) can recover execution-relevant program structure, rather than only produce code that passes tests, remains an open problem. Existing code benchmarks emphasize test-passing outputs, from standalone programming tasks (HumanEval, MBPP, LiveCodeBench) to repository repair (SWE-Bench); this is useful, but offers limited diagnostic signal about which program semantics a model can recover from source. We introduce TraceEval, to our knowledge the first execution-verified, multi-language benchmark for code semantic reasoning: recovering a program's runtime call structure from source code. Unlike prior call-graph benchmarks that rely on static-tool output or hand-annotated ground truth, every positive edge in TraceEval is mechanically witnessed by validation execution, eliminating annotator disagreement and label noise for observed behavior. TraceEval consists of (i) 10,583 real-world programs (2,129 test, 8,454 train) extracted from 1,600+ open-source repositories across Python, JavaScript, and Java via an LLM-assisted harness-generation pipeline with tracer validation; and (ii) a reproducible pipeline that converts any open-source repository into new verified benchmark instances. We evaluate 10 LLMs at zero-shot on the held-out test split. The strongest model, Claude-Opus-4.6, reaches an average F1 of 72.9% across the three languages. To demonstrate the train split's utility as a supervision substrate, we fine-tune the Qwen2.5-Coder family on it: lifts of up to +55.6 F1 bring tuned Qwen2.5-Coder-32B to 71.2%, within 1.7 F1 of zero-shot Claude-Opus-4.6. We release the benchmark, pipeline, baselines, and a datasheet at https://github.com/yikun-li/TraceEva

Related papers

• LoopsBench: From Harness Engineering to Loop Engineering in Benchmarking Coding Agent [60.27239351179265]
  LOOPSBENCH is a benchmark for loop engineering in coding agent evaluation.<n>It comprises 112 tasks from authentic sources spanning 8 programming languages and 9 domains.<n>Its flow-aware runtime releases tests along the ready frontier and retains completed nodes as regression obligations.
  arXiv  Detail & Related papers  (2026-07-31T20:18:25Z)
• RepoReasoner: Evaluating Repository-Level Code Reasoning Ability of Long-Context Language Models [54.53236295237077]
  We introduce RepoReasoner, a benchmark for evaluating repository-level code reasoning.<n> Output Prediction measures fine-grained, stateful execution reasoning across files.<n>Call Chain Prediction evaluates high-level architectural dependency understanding under noisy context.
  arXiv  Detail & Related papers  (2026-07-28T17:12:41Z)
• Benchmarking LLMs for Verilog Design Flows [6.24010225101442]
  Large language models (LLMs) show promise in code generation, but their capabilities to produce correct, synthesizable hardware description language (HDL) code still remain to be properly benchmarked.<n>This paper presents a reproducible benchmarking platform that evaluates open-source LLMs on Verilog RTL generation.<n>The pipeline improved syntax validity from 0% to a 70.43% average and simulation pass rate to 51.8% across three open-source models.
  arXiv  Detail & Related papers  (2026-07-23T21:00:38Z)
• PairCoder++: Pair Programming as a Universal Paradigm for Verified Code-Driven Multimodal and Structured-Artifact Generation [51.92442051257354]
  PairCoder improves essentially every benchmark whose artifact is verifiable, on full official metric suites rather than execution alone.<n>TikZ compile rate up 10 to 30 points on every model, at 2.9 to 9.2 times single model cost.
  arXiv  Detail & Related papers  (2026-07-02T08:36:02Z)
• CrackMeBench: Binary Reverse Engineering for Agents [3.93181912653522]
  CrackMeBench is a benchmark for evaluating language-model agents on educational reverse-engineering tasks.<n>The v0 benchmark combines eight public calibration CrackMes with twelve generated main-score tasks built from seeded C, Rust, and Go templates.<n>CrackMeBench records pass@1 and pass@3, scored submissions, wall-clock time, command traces, tool categories, provider-reported token usage, estimated cost, and qualitative failure labels.
  arXiv  Detail & Related papers  (2026-05-11T14:01:36Z)
• AlgoVeri: An Aligned Benchmark for Verified Code Generation on Classical Algorithms [54.99368693313797]
  Existing benchmarks test only individual languages/tools, so the performance numbers are not directly comparable.<n>We address this gap with AlgoVeri, a benchmark that evaluates vericoding of $77$ classical algorithms in Dafny, Verus, and Lean.
  arXiv  Detail & Related papers  (2026-02-10T06:58:26Z)
• SemGuard: Real-Time Semantic Evaluator for Correcting LLM-Generated Code [46.20378145112059]
  Post-hoc repair pipelines detect such faults only after execution.<n>We present SemGuard, a semantic-evaluator-driven framework that performs real-time, line-level semantic supervision.
  arXiv  Detail & Related papers  (2025-09-29T09:21:32Z)
• ThrowBench: Benchmarking LLMs by Predicting Runtime Exceptions [4.852619858744873]
  Large Language Models (LLMs) have shown astounding capabilities of code understanding and synthesis.<n>We introduce ThrowBench, a benchmark consisting of over 2,400 short user-written programs written in four different programming languages.<n>We evaluate our benchmark on six state-of-the-art code LLMs and see modest performance ranging from 19 to 38% (F1 score)
  arXiv  Detail & Related papers  (2025-03-06T09:22:23Z)
• EquiBench: Benchmarking Large Language Models' Reasoning about Program Semantics via Equivalence Checking [58.15568681219339]
  We introduce EquiBench, a new benchmark for evaluating large language models (LLMs)<n>This task directly tests a model's ability to reason about program semantics.<n>We evaluate 19 state-of-the-art LLMs and find that in the most challenging categories, the best accuracies are 63.8% and 76.2%, only modestly above the 50% random baseline.
  arXiv  Detail & Related papers  (2025-02-18T02:54:25Z)
• ExecRepoBench: Multi-level Executable Code Completion Evaluation [45.963424627710765]
  We introduce a novel framework for enhancing code completion in software development through the creation of a repository-level benchmark ExecRepoBench.<n>We present a multi-level grammar-based completion methodology conditioned on the abstract syntax tree to mask code fragments at various logical units.<n>Then, we fine-tune the open-source LLM with 7B parameters on Repo-Instruct to produce a strong code completion baseline model Qwen2.5-Coder-Instruct-C.
  arXiv  Detail & Related papers  (2024-12-16T17:14:35Z)
• RustRepoTrans: Repository-level Code Translation Benchmark Targeting Rust [50.65321080814249]
  RustRepoTrans is the first repository-level context code translation benchmark targeting incremental translation.<n>We evaluate seven representative LLMs, analyzing their errors to assess limitations in complex translation scenarios.
  arXiv  Detail & Related papers  (2024-11-21T10:00:52Z)
• LEVER: Learning to Verify Language-to-Code Generation with Execution [64.36459105535]
  We propose LEVER, a simple approach to improve language-to-code generation by learning to verify the generated programs with their execution results. Specifically, we train verifiers to determine whether a program sampled from the LLMs is correct or not based on the natural language input, the program itself and its execution results. LEVER consistently improves over the base code LLMs(4.6% to 10.9% with code-davinci) and achieves new state-of-the-art results on all of them.
  arXiv  Detail & Related papers  (2023-02-16T18:23:22Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.