reasoning benchmark
EvalPlus Leaderboard
EvalPlus is a code synthesis evaluation framework that augments existing datasets with test cases generated by LLM and mutation-based strategies, including HumanEval+ with 80x more test cases.
Updated Sep 5, 2026
Models4
Model coverage4
MetricScore
EvidenceB
EvalPlus Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelMA | Score0.80 points | Percentile100.00% | Participants4 | EvidenceC | Evaluated |
| Rank02 | ModelAC | Score0.79 points | Percentile66.67% | Participants4 | EvidenceC | Evaluated |
| Rank03 | ModelAC | Score0.78 points | Percentile33.33% | Participants4 | EvidenceC | Evaluated |
| Rank04 | ModelAC | Score0.70 points | Percentile0.00% | Participants4 | EvidenceC | Evaluated |
EvalPlus Highlights
The leading models and scores on this benchmark.
EvalPlus Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for EvalPlus
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
What is EvalPlus?
What EvalPlus measures and how its scores work.
EvalPlus is a code synthesis evaluation framework that extends existing datasets with additional test cases.
It measures the functional correctness of generated code using Score, reported in points.
Scores are shown in points. This benchmark is not independently verified and has an evidence level of B.
- Family
- EvalPlus
- 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 EvalPlus.
Which model scores highest on EvalPlus?
Kimi K2 Base is currently ranked first with 0.80 points.
What are the top three models on EvalPlus?
The current leaders are Kimi K2 Base (0.80 points), Qwen2 72B Instruct (0.79 points), and Qwen3 235B A22B (0.78 points).
Which EvalPlus 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 EvalPlus 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.