SWE-Bench Verified (OpenCode) leaderboard
As of November 14, 2026, among the results listed here, LiquidAI LFM2.5-24B-A2B has the highest reported SWE-Bench Verified (OpenCode) score, 51.0%, published by Liquid, ahead of LiquidAI LFM3-1.7B at 43.4%. 3 models have a SWE-Bench Verified (OpenCode) result in our records.
Scores as the model makers published them, not re-run by us; each row links to its announcement.
3 models ranked · 1 maker
| Rank | Model | Score | Setting | Reported by | Date |
|---|---|---|---|---|---|
| 1 | LFM2.5-24B-A2B | 51.0% | Not published | Liquid | October 13, 2026 (model release) |
| 2 | LFM3-1.7B | 43.4% | Not published | Liquid | November 6, 2026 (model release) |
| 3 | LFM2.5-2.6BRetired | 18.0% | Not published | Liquid | November 6, 2026 (model release) |
How much to trust these numbers
- Source
- Reported by the model makers themselves. Not re-run by LLMBenchmark or anyone independent.
- Settings
- All ranked results use the same reported setting.
- Spread
- 51.0% to 18.0% across 3 models.
- Freshness
- Newest result published November 6, 2026; oldest October 13, 2026.
What SWE-Bench Verified (OpenCode) measures
It tests autonomous coding work, including finding relevant files; the score is the percentage of tasks resolved.