Try for free

The model the fleet runs

DeepSeek code review, measured

All 8 of IonWarp’s agents start on DeepSeek V4.1 Flash. Below is how it and DeepSeek V4 Pro review, lane by lane. A DeepSeek model is the best model we ran on AI Architecture and CI/CD Performance; on general code review, DeepSeek V4.1 Flash scores F1 49.2% at $0.102 a review.

DeepSeek on every lane
DeepSeek on every lane
LaneModelF1Rank among modelsTime (p50)$ / review
Code Review benchmarkDeepSeek V4 Pro51.4%2 of 55m 59s$0.165
Code Review benchmarkDeepSeek V4.1 Flash49.2%3 of 56m 56s$0.102
Security Review benchmarkDeepSeek V4.1 Flash62.5%2 of 75m 56s$0.063
Security Review benchmarkDeepSeek V4 Pro34.8%6 of 72m 40s$0.131
AI Architecture benchmarkDeepSeek V4 Pro44.4%3 of 81m 52s$0.102
AI Architecture benchmarkDeepSeek V4.1 Flash47.1%1 of 86m 14s$0.050
Log & Errors benchmarkDeepSeek V4.1 Flash59.0%2 of 54m 08s$0.039
Docs Review benchmarkDeepSeek V4 Pro65.2%2 of 33m 00s$0.064
API Performance benchmarkDeepSeek V4 Pro52.2%3 of 61m 21s$0.042
API Performance benchmarkDeepSeek V4.1 Flash53.3%2 of 66m 27s$0.043
SOC 2 Review benchmarkDeepSeek V4.1 Flash66.7%1 of 55m 56s$0.038
SOC 2 Review benchmarkDeepSeek V4 Pro56.3%4 of 52m 21s$0.068
CI/CD Performance benchmarkDeepSeek V4 Pro72.7%1 of 51m 22s$0.032
CI/CD Performance benchmarkDeepSeek V4.1 Flash59.5%2 of 554s$0.0095

Highlighted rows are what the agent runs today. Green: the best model on that lane.

Code review

DeepSeek against every model and app

Code Review: how each reviewer scoresRanked
Code Review: how each reviewer scores
Model / AppReviewer ScoreF1Latency$/run
IonWarp · Muse Spark 1.371.256.6%3m 18s$0.424
Qodo v264.758.5%5m 40s~$1.67
IonWarp · DeepSeek V4 Pro48.751.4%5m 59s$0.165
IonWarp · DeepSeek V4.1 FlashRuns on your PRs41.049.2%6m 56s$0.102
IonWarp · GLM 5.3 Flash40.842.8%2m 15s$0.018
Greptile v4.139.951.1%4m 58s~$1.75
Cursor Bugbot36.251.4%7m 52s~$1.25
IonWarp · GPT 5.6 Luna Pro31.841.6%1m 47s$0.116
CodeRabbit3.142.1%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.

FAQ

DeepSeek for review

Is DeepSeek good for code review?

For some reviews. A DeepSeek model is the best model we ran on AI Architecture (DeepSeek V4.1 Flash, F1 47.1%), CI/CD Performance (DeepSeek V4 Pro, F1 72.7%). On general code review, DeepSeek V4.1 Flash scored F1 49.2% and V4 Pro 51.4%; Muse Spark 1.3 scored 56.6%.

Which DeepSeek model does IonWarp use?

DeepSeek V4.1 Flash, at reasoning effort medium and temperature 0. All 8 of IonWarp’s agents start on DeepSeek V4.1 Flash. An agent moves to another model when IonWarpBench finds one that clears its quality bar for less.

Does my code go to DeepSeek?

No. IonWarp excludes DeepSeek’s own API: the open DeepSeek models run on other hosts through OpenRouter, and only on providers that do not keep or train on what they receive.

How much does a DeepSeek review cost?

DeepSeek V4.1 Flash costs $0.102 in model charges per code review on the benchmark (median 6m 56s). On IonWarp that comes out of the review spend your plan includes.

Did you measure the code DeepSeek writes?

No. We measured DeepSeek as a reviewer of other people’s pull requests. For the code it writes, read a coding benchmark.

DeepSeek on every PR, measured every release.

Try for free

14 days free, no card. Then Pro is $49 a month per workspace with 5 seats, or Max $149 with 10.