CursorBench 3.1 63.2% cursor.com for Composer 2.5 on CursorBench 3.1 (opens in a new tab) CursorBench Accuracy Reported May 18, 2026 Model page Cursor Self-reported Record for Composer 2.5 on CursorBench 3.1 CursorBench 4.0 27.7% cursor.com for Composer 2.5 on CursorBench 4.0 (opens in a new tab) CursorBench Accuracy Reported September 10, 2026 Benchmark leaderboard Cursor Self-reported Record for Composer 2.5 on CursorBench 4.0 SWE-bench Multilingual 79.8% cursor.com for Composer 2.5 on SWE-bench Multilingual (opens in a new tab) Resolved Tasks Reported May 18, 2026 Model page Cursor Self-reported Record for Composer 2.5 on SWE-bench Multilingual SWE-bench Multilingual — Cursor standard harness Configuration: Cursor standard harness 79.2% cursor.com for Composer 2.5 on SWE-bench Multilingual — Cursor standard harness (opens in a new tab) Resolved Tasks Reported June 25, 2026 Blog post Cursor Self-reported Record for Composer 2.5 on SWE-bench Multilingual — Cursor standard harness SWE-bench Multilingual — Cursor strict harness Configuration: Cursor strict harness 71.6% cursor.com for Composer 2.5 on SWE-bench Multilingual — Cursor strict harness (opens in a new tab) Resolved Tasks Reported June 25, 2026 Blog post Cursor Self-reported Record for Composer 2.5 on SWE-bench Multilingual — Cursor strict harness SWE-bench Verified — Vals AI mini-swe-agent Configuration: mini-swe-agent harness 79.6% vals.ai for Composer 2.5 on SWE-bench Verified — Vals AI mini-swe-agent (opens in a new tab) Archived copy (opens in a new tab) Resolved Tasks Reported September 1, 2026 Benchmark leaderboard Vals AI Independent Record for Composer 2.5 on SWE-bench Verified — Vals AI mini-swe-agent Terminal-Bench 2.0 69.3% cursor.com for Composer 2.5 on Terminal-Bench 2.0 (opens in a new tab) Terminal-Bench Accuracy Reported May 18, 2026 Model page Cursor Self-reported Record for Composer 2.5 on Terminal-Bench 2.0 Terminal-Bench 2.1 — Vals AI Terminus 2 Configuration: Terminus-2 harness 58.4% vals.ai for Composer 2.5 on Terminal-Bench 2.1 — Vals AI Terminus 2 (opens in a new tab) Archived copy (opens in a new tab) Terminal-Bench Accuracy Reported September 28, 2026 Benchmark leaderboard Vals AI Independent Record for Composer 2.5 on Terminal-Bench 2.1 — Vals AI Terminus 2 Vibe Code Bench 1.1 — Cursor CLI, October 2026 evaluation Configuration: Cursor CLI harness 49.6% vals.ai for Composer 2.5 on Vibe Code Bench 1.1 — Cursor CLI, October 2026 evaluation (opens in a new tab) Archived copy (opens in a new tab) Vibe Code Bench Score Reported October 6, 2026 Benchmark leaderboard Vals AI Independent Record for Composer 2.5 on Vibe Code Bench 1.1 — Cursor CLI, October 2026 evaluation