reasoning benchmark
CRUXEval-Output-CoT
CRUXEval-O (output prediction) with Chain-of-Thought prompting. Part of the CRUXEval benchmark consisting of 800 Python functions (3-13 lines) designed to evaluate code reasoning, understanding, and execution capabilities. The output prediction task requires models to predict the output of a given Python function with specific inputs, evaluated using chain-of-thought reasoning methodology.
Updated Aug 7, 2026
Published models1
Registry coverage1
MetricScore
EvidenceB
CRUXEval-Output-CoT leaderboard
Sorted by the source-provided rank. Higher score is better according to the registry.
| 1 | AC | 56.0% | 100.0% | 1 | C |
CRUXEval-Output-CoT highlights
The top published results on this benchmark's own scale.
What is CRUXEval-Output-CoT?
Definition and scoring fields from the benchmark registry.
CRUXEval-O (output prediction) with Chain-of-Thought prompting. Part of the CRUXEval benchmark consisting of 800 Python functions (3-13 lines) designed to evaluate code reasoning, understanding, and execution capabilities. The output prediction task requires models to predict the output of a given Python function with specific inputs, evaluated using chain-of-thought reasoning methodology.
Scores are shown in ratio. The current registry marks this benchmark as not independently verified with evidence level B.
- Family
- CRUXEval-Output-CoT
- Modality
- text
- Primary category
- reasoning
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- cruxeval-output-cot|llm-stats-current
Source-native results are preserved. Eligibility for the overall LLMBoard score is a separate policy decision.
FAQ
Common questions about CRUXEval-Output-CoT.
Which model scores highest on CRUXEval-Output-CoT?
Qwen2.5-Coder 7B Instruct is currently ranked first with 56.0%.
What does CRUXEval-Output-CoT measure?
CRUXEval-O (output prediction) with Chain-of-Thought prompting. Part of the CRUXEval benchmark consisting of 800 Python functions (3-13 lines) designed to evaluate code reasoning, understanding, and execution capabilities. The output prediction task requires models to predict the output of a given Python function with specific inputs, evaluated using chain-of-thought reasoning methodology.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
1 unique published model results are currently shown.
Does this benchmark affect the overall score?
This benchmark is preserved as source-native evidence but is not eligible for the current overall score.