code benchmark
CFEval Leaderboard
CFEval is a code benchmark for evaluating code generation and problem-solving capabilities.
Updated Sep 5, 2026
Models2
Model coverage2
MetricScore
EvidenceB
CFEval Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelAC | Score2,134.00 points | Percentile100.00% | Participants2 | EvidenceC | Evaluated |
| Rank02 | ModelAC | Score2,071.00 points | Percentile0.00% | Participants2 | EvidenceC | Evaluated |
CFEval Highlights
The leading models and scores on this benchmark.
CFEval Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for CFEval
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
What is CFEval?
What CFEval measures and how its scores work.
CFEval is a benchmark for evaluating code generation and problem-solving capabilities.
CFEval measures code generation and problem-solving capabilities, reported as a Score in points.
Scores are shown in points. This benchmark is not independently verified and has an evidence level of B.
- Family
- CFEval
- Modality
- text
- Primary category
- code
- 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 CFEval.
Which model scores highest on CFEval?
Qwen3-235B-A22B-Thinking-2507 is currently ranked first with 2,134.00 points.
What are the top three models on CFEval?
The current leaders are Qwen3-235B-A22B-Thinking-2507 (2,134.00 points) and Qwen3-Next-80B-A3B-Thinking (2,071.00 points).
Which CFEval model has the lowest official input price?
Qwen3-Next-80B-A3B-Thinking has the lowest matched official input price at $0.50 input / $6.0 output per 1M tokens.
Which models are fastest among CFEval results?
No matched runtime record is currently available.
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.