| Composer 2.5 | Vibe Code Bench 1.1 — Cursor CLI, October 2026 evaluation | 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 ScoreReported Benchmark leaderboardVals AIIndependentRecord for Composer 2.5 on Vibe Code Bench 1.1 — Cursor CLI, October 2026 evaluation | 50004 |
| Composer 2.5 | Terminal-Bench 2.1 — Vals AI Terminus 2 | 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 AccuracyReported Benchmark leaderboardVals AIIndependentRecord for Composer 2.5 on Terminal-Bench 2.1 — Vals AI Terminus 2 | 50004 |
| Composer 2.5 | CursorBench 4.0 | 27.7% | cursor.com for Composer 2.5 on CursorBench 4.0 (opens in a new tab)CursorBench AccuracyReported Benchmark leaderboardCursorSelf-reportedRecord for Composer 2.5 on CursorBench 4.0 | 50004 |
| Composer 2.5 | SWE-bench Verified — Vals AI mini-swe-agent | 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 TasksReported Benchmark leaderboardVals AIIndependentRecord for Composer 2.5 on SWE-bench Verified — Vals AI mini-swe-agent | 50004 |
| Composer 2.5 | SWE-bench Multilingual — Cursor standard harness | 79.2% | cursor.com for Composer 2.5 on SWE-bench Multilingual — Cursor standard harness (opens in a new tab)Resolved TasksReported Blog postCursorSelf-reportedRecord for Composer 2.5 on SWE-bench Multilingual — Cursor standard harness | 50004 |
| Composer 2.5 | SWE-bench Multilingual — Cursor strict harness | 71.6% | cursor.com for Composer 2.5 on SWE-bench Multilingual — Cursor strict harness (opens in a new tab)Resolved TasksReported Blog postCursorSelf-reportedRecord for Composer 2.5 on SWE-bench Multilingual — Cursor strict harness | 50004 |
| Composer 2.5 | SWE-bench Multilingual | 79.8% | cursor.com for Composer 2.5 on SWE-bench Multilingual (opens in a new tab)Resolved TasksReported Model pageCursorSelf-reportedRecord for Composer 2.5 on SWE-bench Multilingual | 50004 |
| Composer 2.5 | Terminal-Bench 2.0 | 69.3% | cursor.com for Composer 2.5 on Terminal-Bench 2.0 (opens in a new tab)Terminal-Bench AccuracyReported Model pageCursorSelf-reportedRecord for Composer 2.5 on Terminal-Bench 2.0 | 50004 |
| Composer 2.5 | CursorBench 3.1 | 63.2% | cursor.com for Composer 2.5 on CursorBench 3.1 (opens in a new tab)CursorBench AccuracyReported Model pageCursorSelf-reportedRecord for Composer 2.5 on CursorBench 3.1 | 50004 |
| Composer 1 | CursorBench 3.0 | 38.0% | cursor.com for Composer 1 on CursorBench 3.0 (opens in a new tab)CursorBench AccuracyReported Technical reportCursorSelf-reportedRecord for Composer 1 on CursorBench 3.0 | 50001 |
| Composer 1 | SWE-bench Multilingual | 56.9% | cursor.com for Composer 1 on SWE-bench Multilingual (opens in a new tab)Resolved TasksReported Technical reportCursorSelf-reportedRecord for Composer 1 on SWE-bench Multilingual | 50001 |
| Composer 1 | Terminal-Bench 2.0 | 40.0% | cursor.com for Composer 1 on Terminal-Bench 2.0 (opens in a new tab)Terminal-Bench AccuracyReported Technical reportCursorSelf-reportedRecord for Composer 1 on Terminal-Bench 2.0 | 50001 |
| Composer 1.5 | SWE-bench Multilingual | 65.9% | cursor.com for Composer 1.5 on SWE-bench Multilingual (opens in a new tab)Resolved TasksReported Technical reportCursorSelf-reportedRecord for Composer 1.5 on SWE-bench Multilingual | 50002 |
| Composer 1.5 | CursorBench 3.0 | 44.2% | cursor.com for Composer 1.5 on CursorBench 3.0 (opens in a new tab)CursorBench AccuracyReported Technical reportCursorSelf-reportedRecord for Composer 1.5 on CursorBench 3.0 | 50002 |
| Composer 1.5 | Terminal-Bench 2.0 | 47.9% | cursor.com for Composer 1.5 on Terminal-Bench 2.0 (opens in a new tab)Terminal-Bench AccuracyReported Technical reportCursorSelf-reportedRecord for Composer 1.5 on Terminal-Bench 2.0 | 50002 |
| Composer 2 | SWE-bench Multilingual | 73.7% | cursor.com for Composer 2 on SWE-bench Multilingual (opens in a new tab)Resolved TasksReported Technical reportCursorSelf-reportedRecord for Composer 2 on SWE-bench Multilingual | 50003 |
| Composer 2 | CursorBench 3.0 | 61.3% | cursor.com for Composer 2 on CursorBench 3.0 (opens in a new tab)CursorBench AccuracyReported Technical reportCursorSelf-reportedRecord for Composer 2 on CursorBench 3.0 | 50003 |
| Composer 2 | Terminal-Bench 2.0 | 61.7% | cursor.com for Composer 2 on Terminal-Bench 2.0 (opens in a new tab)Terminal-Bench AccuracyReported Technical reportCursorSelf-reportedRecord for Composer 2 on Terminal-Bench 2.0 | 50003 |