Skip to content
Preprint

Execution-grounded evaluation reveals hidden failures in language-model calculations for environmental science

Aug 2026 · 0 citations
Computer Science

TL;DR

AtmosCoder-Bench is introduced, an execution-grounded benchmark that makes the calculation process visible, and finds that multiple-choice formats inflate measured accuracy by at least 12 percentage points.

Abstract

Large language models are increasingly used for quantitative work in the environmental sciences, yet existing evaluations score only final answers, leaving calculation process unobserved. Here we introduce AtmosCoder-Bench, an execution-grounded benchmark that makes the calculation process visible. Built through a transferable semi-automated pipeline (436 problems, 3,910 variants, 7,029 graded quantities), every problem is validated to be unambiguous and human-solvable, with uniquely verifiable answers. We find that (i) multiple-choice formats inflate measured accuracy by at least 12 percentage points; (ii) many failures arise not from missing knowledge but from models failing to apply known formulas and constraints consistently throughout multi-step computation; and (iii) even frontier models remain weak when task-specific conditions invalidate familiar methods, often reverting to canonical solution patterns rather than adapting methods to the relevant physical regime, leaving expert oversight essential.

View source

Similar papers

Preprint Aug 2026

TRACES: A Benchmark for Epistemic Reliability in Scientific Reasoning by LLMs

A probe corpus of 42 retracted, fraudulent, and pseudoscientific papers is paired with a methodology for eliciting and scoring single-shot model engagement with each paper's framing, indicating an urgent need for guardrail infrastructure for scientific deployment of language models.

V. Rodionov, Shamil Assylbekov · 0 citations
Preprint Aug 2026

What Proves You Wrong: Benchmarking Language Models on Falsifiable Research Ideation

The Lit2Test benchmark centers on a six-field contract organized around a falsifying outcome, so that every proposal precommits the observation that would prove it wrong, making its quality decidable in the first place rather than merely arguable.

Ziyue Wang, Aomufei Yuan, Yiran Yao et al. · 0 citations
Preprint Jul 2026

SPARK: Susceptibility-Guided Profiling and Steering of Latent Reasoning States in Large Language Models

SPARK is introduced, which uses hidden-state response to diagnose whether a model internally enters an effective reasoning state and to guide lightweight test-time steering, and suggests that susceptibility can serve not only as a diagnostic signal for reasoning failures, but also as a practical guide for targeted test-time intervention.

Dongxu Zhang, Yiding Sun, Zihao Guo et al. · 0 citations
Preprint Aug 2026

Measuring Stability and Failure Behavior in Language Models Under Structured Perturbations

Language models are usually judged by a single accuracy score, which does not reveal how their performance degrades as inputs are perturbed. We present a graded, multi-family, failure-aware framework for stress-testing reasoning models. It perturbs each problem along a multi-level severity ladder across seven families: six that preserve the answer, paraphrase, input noise, formatting, irrelevant context, context load, and conflicting instructions, and a Knowledge Boundary family that removes answerability so that refusal becomes the correct response. Every test is validity-gated and labeled by its measured severity, and each model is summarized by per-level Accuracy, a magnitude-weighted Stability, and a per-family Collapse Point defined relative to the model's own baseline. Instantiated on the same 100 seed problems used by GSM-Symbolic, expanded into 4,473 gated tests and run on four models spanning capability tiers, the framework exposes structure that an aggregate score hides: the level at which a model fails is family-specific rather than global, and two stressors expose consistent weaknesses across all models: conflicting instructions and questions built on an impossible premise. Recognition of unanswerability is otherwise uneven, reliable on missing information and fabricated evidence but weak on impossible premises. These failure points are invisible to standard accuracy reporting.

Samira Golsefid · 0 citations
Preprint Jul 2026

Are LLMs Ready for Scientific Discovery? A Capability-Oriented Benchmark for AI Scientists

Existing benchmarks for scientific data analysis evaluate LLMs primarily on code execution or workflow completion, overlooking that scientific analysis serves to support distinct types of scientific claims: hypothesis exploration, statistical inference, mechanistic explanation, each with different assumptions and validity criteria. We introduce SDABench, a benchmark that reorganizes evaluation around six capabilities (descriptive, exploratory, inferential, predictive, causal, and mechanistic) across five domains (Biology, Chemistry, Environment, Geography, Physics). SDABench comprises 527 real-data instances (SDA-Real) and 6000 synthetic instances (SDA-Synth), each in both multiple-choice and open-ended formats, constructed through an automated pipeline. Evaluating 15 representative LLMs, we find that models handle descriptive analysis well but degrade sharply on tasks requiring assumption selection, latent-process modeling, or mechanistic reasoning. SDABench further provides a five-stage error analysis framework that locates where LLMs fail: more advanced models more reliably identify the relevant scope and variables, but still struggle to select appropriate analytical procedures, model variable relationships, and draw valid conclusions.

Chuhan Shi, Xiaoquan Ren, Sicheng Song et al. · 1 citation