code benchmark
SWE-Review
Software Engineering Review benchmark evaluating code review capabilities
Updated Aug 7, 2026
Published models1
Registry coverage1
MetricScore
EvidenceB
SWE-Review leaderboard
Sorted by the source-provided rank. Higher score is better according to the registry.
| 1 | MI | 8.9% | 100.0% | 1 | C |
SWE-Review highlights
The top published results on this benchmark's own scale.
What is SWE-Review?
Definition and scoring fields from the benchmark registry.
Software Engineering Review benchmark evaluating code review capabilities
Scores are shown in ratio. The current registry marks this benchmark as not independently verified with evidence level B.
- Family
- SWE-Review
- Modality
- text
- Primary category
- code
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- swe-review|llm-stats-current
Source-native results are preserved. Eligibility for the overall LLMBoard score is a separate policy decision.
FAQ
Common questions about SWE-Review.
Which model scores highest on SWE-Review?
MiniMax M2.1 is currently ranked first with 8.9%.
What does SWE-Review measure?
Software Engineering Review benchmark evaluating code review capabilities
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.