FrontierSWE
AI benchmark results and model performance
Type: percentageCode
Recorded results
3
Average score
65.80%
Score range
55% - 81.20%
Leading model
81.20% - Kimi K3
Scores over time
Individual benchmark scores plotted by date.
Model results
| Organisation | Models | Reported | Top score | Info | Self reported | Source |
|---|---|---|---|---|---|---|
| Kimi K3 | 16 Jul 2026 | 81.20% | KimiCode harness; dominance score recomputed from raw scores with the official evaluation script, current July 16, 2026. | Yes | Source | |
| Gemini 4 Carbon | 28 Oct 2026 | 61.20% | Google-reported launch evaluation; source chart: https://storage.googleapis.com/gweb-uniblog-publish-prod/images/gemini_4_carbon__evals-table.original.png; methodology: deepmind.google/models/evals-methodology/gemini-4-carbon | Yes | Source | |
| Gemini 4 Argon | 13 Oct 2026 | 55% | Google-reported launch evaluation; source chart: https://storage.googleapis.com/gweb-uniblog-publish-prod/original_images/gemini-4-argon_table_blog.gif | Yes | Source |
