Skip to content
IonWarpTry for free
Muse Spark code review

Muse Spark code review: Muse Spark 1.3 benchmarks on real pull requests

Muse Spark 1.3 is the best model we have run on general code review. On 50 open-source pull requests with 158 known issues, it found 79; 42 of its findings matched none: an F1 of 56.6%, at 42 cents.[1] Only the Qodo app scored higher, 58.5%. We ran it on eight of IonWarp's nine review types (how the benchmarks work).

Example pull request#310

What lands on your pull request · Code Review

P1Retry charges the same order twice
billing/checkout.ts:42 · A timed-out response can charge the order twice
- await payments.charge(order);+ await payments.charge(order, {+   idempotencyKey: order.id,+ });
When payment succeeds but the response times out, the caller retries the same order. Both calls charge it. Pass the stable order ID as the payment idempotency key.

IonWarp's Code Review still runs DeepSeek V4.1 Flash by default: it scored 49.2% and costs 10 cents a review, about a quarter of Muse Spark's price.[1] Muse Spark is what a failed Code Review or API Performance review retries on. On most specialist reviews, cheaper models scored higher.

Where Muse Spark 1.3 leads, and where it does not

  • Code review: the best model, second to one app

    Ahead of DeepSeek V4 Pro (51.4%) and every other model we ran.[1] Best LLM for code review has the full table. In Discourse #8, findMembers() became async and nothing waited for it, so the members list could render empty. Of nine reviewers, only Muse Spark flagged it.[2]

    Code ReviewOn Starter, Pro and Max

  • API performance: the best model, behind three apps

    56.0% on 18 pull requests, in 42 seconds for about 6 cents. Greptile (76.9%), Bugbot (71.4%) and Qodo (66.7%) scored higher.[3]

    API PerformanceOn Max

  • Docs: third of three models

    59.5% on 19 pull requests, behind Gemini 3.8 Flash (68.6%) and DeepSeek V4 Pro (65.2%).[4]

    Docs ReviewOn Pro and Max

  • Security, SOC 2, CI/CD and logs: behind cheaper models

    Security 44.4% at 26 cents a review, against 66.7% for GLM 5.3 Flash at about a cent.[5] SOC 2 55.2% and CI/CD 44.4%, last of five models on both;[6][7] logs 43.6%, third of five.[8]

How Muse Spark scored on each review type

ReviewModelF1PrecisionRecall$ per reviewMedian timeRank
Code Review50 of 50 PRsMuse Spark 1.356.6%65.3%50.0%$0.423m 18s1 of 5
Security Review13 of 13 PRsMuse Spark 1.344.4%66.7%33.3%$0.262m 30s5 of 7
AI Architecture Review11 of 11 PRsMuse Spark 1.328.6%20.0%50.0%$0.192m 4s7 of 8
Log & Errors Review17 of 17 PRsMuse Spark 1.343.6%50.0%38.7%$0.0856 sec3 of 5
Docs Review19 of 19 PRsMuse Spark 1.359.5%55.0%64.7%$0.0948 sec3 of 3
API Performance Review18 of 18 PRsMuse Spark 1.356.0%58.3%53.8%$0.0642 sec1 of 6
SOC 2 Review20 of 20 PRsMuse Spark 1.355.2%57.1%53.3%$0.1148 sec5 of 5
CI/CD Performance18 of 18 PRsMuse Spark 1.344.4%42.9%46.2%$0.0349 sec5 of 5

Rank is among the models we ran on that review, by F1; a tie goes to the cheaper one. See the benchmark

Pricing

Simple pricing for your whole team.

One workspace price with seats included. Credits pool across your team. Unlimited repos on every plan.

Starter

$0 /mo

Try AI PR review.

  • 2 reviewers
    • Code Review
    • Security Review
  • 3 seats included
  • 15,000 credits to start, then 5,000/mo
  • About 70 reviews to start, then about 25 a month
  • Unlimited repos
Get Started

Max

$149 /mo

Scale AI PR review.

  • +9 reviewers
    • UX Review
    • API Performance
    • Analytics Review
    • SEO Review
    • Changelog
    • CI/CD Performance
    • Plan Review
    • Repeat-Failure Learnings
    • SOC 2 Review
  • 10 seats included
  • +75,000 credits/mo
  • About 360 reviews a month
  • +$29/mo per added seat
  • Unlimited repos
  • Priority support
Choose Max
Enterprise

Custom reviewers + credits · GitHub Enterprise · SSO/SAML + audit logs · Custom security review + SLA

Contact us
FAQ

Frequently asked questions

Is Muse Spark good for code review?

On general code review, yes: it was the best model we ran, with an F1 of 56.6% on 50 pull requests, behind only the Qodo app. On security, SOC 2, CI/CD and logs, cheaper models scored higher.

Why doesn't IonWarp run Muse Spark by default?

Price. On the code benchmark it costs 42 cents a review against 10 for DeepSeek V4.1 Flash, which IonWarp runs for Code Review. A failed Code Review review retries on Muse Spark.

Muse Spark or DeepSeek V4 Pro for code review?

Muse Spark found more known issues, 79 to 64, at 42 cents a review against 16. DeepSeek V4 Pro was more precise: 70% of its findings matched a known issue, against 65% for Muse Spark.

How fast is Muse Spark?

On code review its median was 3 minutes 18 seconds a review. On API performance and docs it took under a minute.

Sources

  1. The code review benchmark: 50 pull requests, 158 known issues (release of 2026-10-06)IonWarp benchmark · read
  2. discourse #8 (group members), graded code review findingsIonWarp benchmark · read
  3. The API performance review benchmark: 18 pull requests, 13 known issues (release of 2026-09-24)IonWarp benchmark · read
  4. The docs review benchmark: 19 pull requests, 17 known issues (release of 2026-09-22)IonWarp benchmark · read
  5. The security review benchmark: 13 pull requests, 18 known issues (release of 2026-09-24)IonWarp benchmark · read
  6. The SOC 2 review benchmark: 20 pull requests, 15 known control gaps (release of 2026-09-24)IonWarp benchmark · read
  7. The CI/CD benchmark: 18 pull requests, 13 known pipeline defects (release of 2026-09-20)IonWarp benchmark · read
  8. The log and error review benchmark: 17 pull requests, 31 known issues (release of 2026-09-24)IonWarp benchmark · read