Measured · release 2026-10-12
The best LLM for code review, measured
Muse Spark 1.3 found 79 of 158 known issues on 50 pull requests, with 42 findings that matched none: F1 56.6%, for $0.424 a review. DeepSeek V4.1 Flash, which IonWarp’s Code Review runs by default, scored 49.2% for $0.102. Claude Opus 4.5 graded every finding.
| Model / App | Reviewer Score | F1 | Latency | $/run |
|---|---|---|---|---|
| IonWarp · Muse Spark 1.3 | 71.2 | 56.6% | 3m 18s | $0.424 |
| Qodo v2 | 64.7 | 58.5% | 5m 40s | ~$1.67 |
| IonWarp · DeepSeek V4 Pro | 48.7 | 51.4% | 5m 59s | $0.165 |
| IonWarp · DeepSeek V4.1 FlashRuns on your PRs | 41.0 | 49.2% | 6m 56s | $0.102 |
| IonWarp · GLM 5.3 Flash | 40.8 | 42.8% | 2m 15s | $0.018 |
| Greptile v4.1 | 39.9 | 51.1% | 4m 58s | ~$1.75 |
| Cursor Bugbot | 36.2 | 51.4% | 7m 52s | ~$1.25 |
| IonWarp · GPT 5.6 Luna Pro | 31.8 | 41.6% | 1m 47s | $0.116 |
| CodeRabbit | 3.1 | 42.1% | 7m 34s | ~$1.50 |
Reviewer Score = (3 × F1 + time + $/run) ÷ 5, each part 0 to 100 within this table. IonWarp rows cost the model’s inference; ~$ is each app’s list price for 5 seats at 100 reviews a month. Pinned Martian Core reproduction. Release 2026-10-12, CC BY 4.0.
By kind of review
The best model for each review
The top F1 among models on each lane. What wins general code review is not what wins security or CI/CD.
Muse Spark 1.3
F1 56.6% · 3m 18s · $0.424
Security ReviewGLM 5.3 Flash
F1 66.7% · 1m 38s · $0.012
AI ArchitectureDeepSeek V4.1 Flash
F1 47.1% · 6m 14s · $0.050
Log & ErrorsGemini 3.8 Flash
F1 67.7% · 1m 29s · $0.100
Docs ReviewGemini 3.8 Flash
F1 68.6% · 59s · $0.084
API PerformanceMuse Spark 1.3
F1 56.0% · 42s · $0.063
SOC 2 ReviewGLM 5.3 Flash
F1 66.7% · 34s · $0.0095
CI/CD PerformanceDeepSeek V4 Pro
F1 72.7% · 1m 22s · $0.032
| Model | Code Review benchmark | Security Review benchmark | AI Architecture benchmark | Log & Errors benchmark | Docs Review benchmark | API Performance benchmark | SOC 2 Review benchmark | CI/CD Performance benchmark |
|---|---|---|---|---|---|---|---|---|
| DeepSeek V4 Pro | 51.4% | 34.8% | 44.4% | – | 65.2% | 52.2% | 56.3% | 72.7% |
| DeepSeek V4.1 Flash | 49.2% | 62.5% | 47.1% | 59.0% | – | 53.3% | 66.7% | 59.5% |
| GLM 5.3 | – | – | 47.1% | – | – | – | – | – |
| GLM 5.3 Flash | 42.8% | 66.7% | 15.4% | 36.1% | – | 48.3% | 66.7% | 55.0% |
| GPT 5.6 Luna Pro | 41.6% | 28.6% | 35.3% | 36.0% | – | 50.0% | 64.5% | 54.5% |
| Gemini 3.8 Flash | – | 51.6% | 33.3% | 67.7% | 68.6% | 41.7% | – | – |
| Grok 4.6 | – | 53.3% | 34.8% | – | – | – | – | – |
| Muse Spark 1.3 | 56.6% | 44.4% | 28.6% | 43.6% | 59.5% | 56.0% | 55.2% | 44.4% |
Models only, each run as IonWarp’s reviewer for that lane on every pull request of the lane. Only Code Review is ranked; the other lanes are provisional. On a phone this shows the first 3 of 8 lanes; a wider screen shows them all.
Model by model
Where each model leads
Muse Spark
Best model on Code Review, API Performance. Best F1: 59.5% on Docs Review; lowest: 28.6% on AI Architecture.
Muse Spark, lane by laneDeepSeek
Best model on AI Architecture, CI/CD Performance. Best F1: 72.7% on CI/CD Performance; lowest: 34.8% on Security Review.
DeepSeek, lane by laneGLM
Best model on Security Review, SOC 2 Review. Best F1: 66.7% on Security Review; lowest: 15.4% on AI Architecture.
GLM, lane by laneGPT Luna
Not the best model on any lane. Best F1: 64.5% on SOC 2 Review; lowest: 28.6% on Security Review.
GPT Luna, lane by laneGrok
Not the best model on any lane. Best F1: 53.3% on Security Review; lowest: 34.8% on AI Architecture.
Gemini
Best model on Log & Errors, Docs Review. Best F1: 68.6% on Docs Review; lowest: 33.3% on AI Architecture.
Gemini, lane by laneFAQ
Picking a model
What is the best LLM for code review?
On 50 pull requests with 158 known issues, Muse Spark 1.3 had the best F1 of the 5 models we ran: 56.6%, at $0.424 a review. The Qodo v2 app scored 58.5%. DeepSeek V4.1 Flash, which IonWarp’s Code Review runs, scored 49.2% at $0.102.
Is the best model the same for every kind of review?
No. Code Review: Muse Spark 1.3; Security Review: GLM 5.3 Flash; AI Architecture: DeepSeek V4.1 Flash; Log & Errors: Gemini 3.8 Flash; Docs Review: Gemini 3.8 Flash; API Performance: Muse Spark 1.3; SOC 2 Review: GLM 5.3 Flash; CI/CD Performance: DeepSeek V4 Pro. Only the code review lane is ranked; the others are provisional.
Why doesn’t IonWarp run the top model everywhere?
Cost and speed count too. Every agent starts on DeepSeek V4.1 Flash, and IonWarpBench moves an agent to another model only when it clears the quality bar for less. The model is named on every review.
Is the best LLM for coding also the best for code review?
Not necessarily, and a coding ranking cannot tell you. Coding benchmarks grade code a model writes; this one grades whether a model finds known issues in a pull request someone else wrote.

Every agent names its model.
Try for free14 days free, no card. Then Pro is $49 a month per workspace with 5 seats, or Max $149 with 10.