Benchmarks

9 results across 4 benchmarks

Benchmark results for Composer 2.5
BenchmarkScoreSource
CursorBench 3.163.2%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
CursorBench 4.027.7%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
SWE-bench Multilingual79.8%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
SWE-bench Multilingual — Cursor standard harnessConfiguration: Cursor standard harness79.2%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
SWE-bench Multilingual — Cursor strict harnessConfiguration: Cursor strict harness71.6%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
SWE-bench Verified — Vals AI mini-swe-agentConfiguration: mini-swe-agent harness79.6%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
Terminal-Bench 2.069.3%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
Terminal-Bench 2.1 — Vals AI Terminus 2Configuration: Terminus-2 harness58.4%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
Vibe Code Bench 1.1 — Cursor CLI, October 2026 evaluationConfiguration: Cursor CLI harness49.6%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