Leaderboard bars
1 ranked models · higher is better
View accessible chart data
| Model | Rank | Provider | Score |
|---|---|---|---|
| Kimi K3 | #1 | Moonshot AI | 42% |
Loading benchmark header
Loading benchmark registry
Coding · Benchmark profile
Multi-hour whole-project software engineering tasks with hidden checks and exploit scanning.
Data verified 15 July 2026 · Methodology 1.2.0
Visual analysis
Three views of the same sourced leaderboard: model placement, the score curve, and descriptive provider averages. These visuals never alter ranking calculations.
1 ranked models · higher is better
| Model | Rank | Provider | Score |
|---|---|---|---|
| Kimi K3 | #1 | Moonshot AI | 42% |
Shows how quickly scores separate down the field
| Model | Rank | Provider | Score |
|---|---|---|---|
| Kimi K3 | #1 | Moonshot AI | 42% |
Average within the visible cohort · descriptive only
| Provider | Models | Average score |
|---|---|---|
| Moonshot AI | 1 | 42% |
One best score per model · higher is better
| Rank | Model | Provider | License | Score |
|---|---|---|---|---|
| #1 | Kimi K3 kimi-k3 | Moonshot AI | closed | 42% |
About SWE Marathon
Multi-hour whole-project software engineering tasks with hidden checks and exploit scanning. Results stay tied to the exact model variant and evaluation system. Multiple systems for the same model use the best published score on this page; overall Lumina scoring uses the median of ranking-eligible rows.
Open benchmark source ↗FAQ
Multi-hour whole-project software engineering tasks with hidden checks and exploit scanning.
Kimi K3 by Moonshot AI currently leads with 42%.
1 model in the LuminaBench cohort have a qualifying score on this benchmark.
No. This benchmark is display-only and does not enter the overall Lumina composite.
Related