Benchmark Results

Martian Benchmark Testing

Last updated July 6, 2026 · re-measured periodically

RMCode Max scored F1 = 74.7%, Pro scored F1 = 58.9%, and Free scored F1 = 53.0% on the Martian-50 code-review benchmark — measured end-to-end on the deployed production service and judged with the canonical Martian methodology.

These numbers come from a typical run: each finding was posted by the RMCode GitHub App on a public forked PR (see the 50 PRs below). Because language-model output is not deterministic, results can vary between runs. We re-measure periodically — after model refreshes and product updates — so the figures here may change over time. Official Martian leaderboard submission is pending.

Benchmark

Code Review F1 Score

RMCode Max
#1
74.7%
Cubic
61.8%
RMCode Pro
58.9%
Qodo Extended
57.9%
Augment
53.5%
RMCode Free
53%
Qodo
48.4%
Cursor Bugbot
45.5%
GitHub Copilot
37%
CodeRabbit
35.2%

Martian Code Review Benchmarkcurated hard PRs from large production repositories, with human-reviewed gold findings

RMCode results are self-evaluated; official submission is not yet submitted.

What is the Martian Benchmark?

The Martian Code Review Benchmark is an independent, open-source evaluation for AI code review tools.

It uses curated hard pull requests from large, mature open-source projects, with human-reviewed code review findings as the gold set. An independent LLM judge scores each tool on precision (are the flagged issues real?), recall (did it catch the known issues?), and F1 (the harmonic mean of both).

This is not our benchmark — it's the same evaluation used by Cubic, Qodo, Cursor Bugbot, CodeRabbit, and other tools. We use the same methodology, data, and scoring.

Results by Tier

RMCode offers three quality levels. All three have been measured end-to-end on the deployed service; Max runs our deepest, most thorough review pipeline:

TierF1CreditsCompetitive Position
Max74.7%20 crOur highest-scoring tier — the deepest Max review pipeline, measured end-to-end on the deployed production service
Pro58.9%5 crMultiple scout passes with a precision filter — measured end-to-end on the deployed service
Free53.0%1 crAbove most tools on the leaderboard — at no cost

Full Comparison

The deployed RMCode results shown beside the official April 9, 2026 Martian offline leaderboard, ranked by F1 score:

#ToolF1
RMCode Max74.7%
1Cubic Dev61.8%
RMCode Pro58.9%
2Qodo Extended57.9%
3Augment53.5%
RMCode Free53.0%
4Qodo48.4%
5Propel46.9%
7Cursor Bugbot45.5%
8Devin44.2%
9Greptile44.0%
13Claude Code37.6%
14GitHub Copilot37.0%
15CodeRabbit35.2%
16Gemini33.9%

Leaderboard scores from the official April 9, 2026 Martian offline benchmark. The RMCode Free, Pro, and Max scores were measured end-to-end on the deployed service using the same data, methodology, and judge model. Official RMCode submission pending.

Benchmark results are one input when evaluating a code review tool. Real-world performance can vary by language, repository structure, pull request size, and the types of issues present.

Why isn't RMCode on the official leaderboard yet?

We're still launching, and we're deliberately not tuning to a single benchmark snapshot. Our focus is long-term, real-world effectiveness — better review results with fewer tokens through better system design, and the freedom to run on the most cost-effective model, including open-source options and your own keys (BYOK on Enterprise).

Our principle is simple: results per token, not tokens burned — the most effective model for the job, the fewest tokens to get there, better results at lower cost, and no vendor lock-in. We are building a broader benchmark to measure that sustained effectiveness over time, and we'll submit to Martian once that groundwork is in place. Until then, every number here is measured on the live product and reproducible below.

The 50 PRs — Live Proof

Every score below was produced by the deployed production RMCode service reviewing a real pull request. Each PR was reconstructed as a public repository, opened as a PR, and reviewed automatically by the rmcode-ai GitHub App — the same app anyone can install. Open any “view review” link to see the bot's inline comments on the actual diff.

Scoring is the canonical Martian pairwise judge (Claude Opus 4.5). Per PR: TP = real issues caught, FP = false alarms, FN = known issues missed.

#Repo · PRRMCode ReviewFindingsTP / FP / FN
1keycloak#37429view review →53 / 2 / 1
2keycloak#37634view review →33 / 0 / 1
3keycloak#38446view review →32 / 0 / 0
4keycloak#36882view review →20 / 2 / 1
5keycloak#36880view review →32 / 1 / 1
6keycloak#37038view review →22 / 0 / 0
7keycloak#33832view review →22 / 0 / 0
8keycloak#40940view review →22 / 0 / 0
9keycloak-greptile#1view review →22 / 0 / 0
10sentry#93824view review →55 / 0 / 0
11sentry-greptile#5view review →11 / 0 / 2
12sentry-greptile#1view review →43 / 0 / 1
13grafana#97529view review →31 / 1 / 1
14sentry#80168view review →11 / 0 / 1
15sentry#80528view review →11 / 0 / 1
16sentry#77754view review →53 / 0 / 1
17sentry#95633view review →33 / 0 / 0
18sentry-greptile#2view review →33 / 1 / 0
19sentry-greptile#3view review →22 / 0 / 1
20grafana#103633view review →20 / 2 / 2
21sentry#67876view review →33 / 0 / 0
22keycloak#32918view review →32 / 1 / 0
23grafana#94942view review →11 / 0 / 1
24grafana#90939view review →00 / 0 / 2
25grafana#80329view review →21 / 1 / 0
26grafana#90045view review →33 / 0 / 0
27grafana#106778view review →31 / 2 / 1
28grafana#107534view review →10 / 1 / 1
29grafana#79265view review →44 / 0 / 1
30discourse-graphite#9view review →00 / 0 / 2
31grafana#76186view review →21 / 1 / 1
32discourse-graphite#10view review →34 / 0 / 0
33discourse-graphite#7view review →42 / 2 / 1
34discourse-graphite#8view review →42 / 1 / 1
35discourse-graphite#3view review →52 / 1 / 0
36discourse-graphite#5view review →22 / 0 / 0
37discourse-graphite#6view review →21 / 1 / 0
38discourse-graphite#4view review →74 / 3 / 2
39discourse-graphite#1view review →22 / 0 / 1
40discourse-graphite#2view review →32 / 1 / 0
41cal.com#22532view review →32 / 0 / 0
42cal.com#8330view review →11 / 0 / 1
43cal.com#14943view review →11 / 0 / 1
44cal.com#22345view review →21 / 1 / 1
45cal.com#11059view review →55 / 1 / 0
46cal.com#7232view review →22 / 0 / 0
47cal.com#14740view review →31 / 2 / 4
48cal.com#10600view review →32 / 1 / 2
49cal.com#10967view review →44 / 0 / 1
50cal.com#8087view review →32 / 0 / 0
Aggregate — 50 PRs13599 / 29 / 38

Aggregate: 99 TP, 29 FP, 38 FN → precision 77.3%, recall 72.3%, F1 = 74.7%.

Measured on the deployed production service (Max tier) with the canonical Martian methodology and judge. Repositories are hosted under the public rmcode-benchmark organization. Official Martian leaderboard submission is pending.

Methodology

Our internal evaluation follows the Martian benchmark methodology exactly: same curated hard PRs, same golden findings, same judge prompt, same scoring. Key details:

  • Context-aware analysis — understands code beyond just the diff, including related files and dependencies
  • Progressive quality levels — each tier uses a more thorough review process, trading speed and cost for accuracy
  • No benchmark-specific tuning — all bug patterns are generic, not tailored to specific test cases

What This Means For You

Higher F1 means your reviews catch more real bugs with fewer false alarms. You spend less time dismissing noise and more time shipping.

RMCode Free scores above most tools on the leaderboard — at no cost. Choose the quality level that fits your needs:

  • Free — 30 credits/month, enough for up to 30 Standard reviews, no credit card required
  • Pro — 200 credits/month, F1 = 58.9% on the deployed Martian-50 run, runs multiple scout passes with a precision filter
  • Max — 600 credits/month, F1 = 74.7% on the deployed Martian-50 run, our deepest, most thorough review pipeline
Try it free — Install GitHub App

30 credits/month free. No credit card required.