Leading score48.40 %
Verified AI benchmark
Martian Code Review Bench — Offline F1 Leaderboard
Controlled code-review benchmark across 50 hard-to-find bugs; F1 balances precision and recall.
Semantic classUnclassified
CategoryCode Review DirectionHigher is better
Version2026-06-24 Verified entities5
How to interpret this leaderboard
What this benchmark does—and does not—measure
This leaderboard preserves the benchmark's own metric, source and test date. Results are comparable only within the same benchmark definition and semantic class; missing data is never treated as a zero.
Method & source
- Unit
- %
- Results
- 5
- Latest test
- Jun 24, 2026
- Distinct source links
- 1
Entities at top score1
Evidence freshnessJun 24, 2026
Verified results
Martian Code Review Bench — Offline F1 rankings
Only the latest verified result for each listed entity is shown. Equal scores receive the same displayed rank.
| Rank | Model / Tool | Score | Tested | Evidence |
|---|---|---|---|---|
| #1 | Qodo | 48.40% | Jun 24, 2026 | Martian Code Review Bench |
| #2 | Cursor | 45.50% | Jun 24, 2026 | Martian Code Review Bench |
| #3 | Devin | 44.20% | Jun 24, 2026 | Martian Code Review Bench |
| #4 | GitHub Copilot | 43.50% | Jun 24, 2026 | Martian Code Review Bench |
| #5 | CodeRabbit | 35.20% | Jun 24, 2026 | Martian Code Review Bench |
What to keep in mind
A benchmark is one evidence signal, not a universal product verdict. Test conditions, benchmark versions, source methodology and date can all affect interpretation. Compare shared benchmarks and current product evidence before making a model or tool decision.
Why dates and sources are shown
AI Orbit retains the source and tested date for each verified result so readers can judge whether evidence is current enough for their use case. Older evidence is not silently presented as a new test.