reasoning benchmark
CRUX-O Leaderboard
CRUX-O is the output-prediction part of the CRUXEval benchmark, comprising 800 Python functions of 3–13 lines that evaluate AI models' code reasoning, understanding, and execution.
Updated Sep 5, 2026
Models1
Model coverage1
MetricScore
EvidenceB
CRUX-O Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelAC | Score0.79 points | Percentile100.00% | Participants1 | EvidenceC | Evaluated |
CRUX-O Highlights
The leading models and scores on this benchmark.
The Top AI Models for CRUX-O
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
Ranking basisThis crux-o AI model leaderboard uses descending score in the benchmark original unit. The leaderboard ranking keeps matched price and speed data separate from benchmark evidence.
- 01ACAlibaba Cloud / Qwen Team
- Score
- 0.79 points
- Price
- $0.70 input / $2.8 output per 1M tokens
- Speed
- Up to 21.74 tok/s via DeepInfra
Strengths
- Ranks #1 of 1 compared models
- 100th percentile on this benchmark
- C evidence result
Considerations
- This result measures CRUX-O, not total model capability
Selection summary
Best AI Models for CRUX-O
Qwen3 235B A22B currently leads CRUX-O with 0.79 points. It is the top model on this specific benchmark, while the best LLM for the broader task should also be checked against other benchmarks, price, and runtime.
Use this leaderboard with the supporting benchmark results and coverage details above. A leaderboard position summarizes the selected ranking signal; it does not replace workload-specific testing.
What is CRUX-O?
What CRUX-O measures and how its scores work.
CRUX-O (output prediction) is part of the CRUXEval benchmark and consists of 800 Python functions designed to assess AI models by asking them to predict function outputs from code and inputs.
It measures the ability to predict correct Python function outputs from function code and inputs, reported as Score in points.
Scores are shown in points. This benchmark is not independently verified and has an evidence level of B.
- Family
- CRUX-O
- Modality
- text
- Primary category
- reasoning
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- overall
LLM Stats. Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about CRUX-O.
Which model scores highest on CRUX-O?
Qwen3 235B A22B is currently ranked first with 0.79 points.
What are the top three models on CRUX-O?
The current leaders are Qwen3 235B A22B (0.79 points).
Which CRUX-O model has the lowest official input price?
Qwen3 235B A22B has the lowest matched official input price at $0.70 input / $2.8 output per 1M tokens.
Which models are fastest among CRUX-O results?
The fastest matched records are Qwen3 235B A22B (21.74 tok/s via DeepInfra).
Does the highest score result prove overall model quality?
No. This benchmark measures one defined capability or task. The overall LLMBoard score uses a separate aggregation across eligible benchmark evidence.