Cursor Bench (2025 internal version)
Agents answer real agent requests from Cursor engineers in Cursor's harness. Graders compare against hand-curated solutions and check use of the codebase's existing abstractions.
Cursor introduced it in the Composer post of 2025-10-29 and used it again for Composer 1.5 in 2026-02. Cursor says CursorBench 3 roughly doubled the problem scope of the initial version, so scores are not comparable.
- Level
- Expert Specialists with years of training, often over hours of work
- Scored
- Graded by a model A language model scores each response, usually against a rubric.
- Answers
- Code A program or patch run against tests.
No scores here yet
No lab, leaderboard or Epoch AI run has reported a score for Cursor Bench (2025 internal version) yet.
Labs headline it less often now, last in Feb 2026
Launch posts from every lab that has listed it, one tick per post. Tall colored ticks include it, and short gray ones leave it out.
| Date | Launch post | Score | As the post writes it |
|---|---|---|---|
| 9 Feb 2026 | Composer 1.5 | Cursor Bench (chart, internal version before CursorBench 3.0) | |
| 29 Oct 2025 | Composer 1 | Intelligence (Cursor Bench score), chart only |
Versions
We switch the top row to each new version when it comes out. Open it for one row per version. An old version stays in play while people still test it, so whoever first takes it past 85% gets credit for closing it out.
More in Coding
- SWE-bench Verified In use 500 human-validated GitHub issues from 12 Python repos. Agent writes a patch that must pass hidden tests. Claude Opus 4.7 83.5%
- SWE-bench Multilingual In use 300 GitHub-issue tasks across nine programming languages in SWE-bench format. Patch graded by repository tests. Claude Opus 5.5 93.9%
- LiveCodeBench v6 In use Competitive programming problems collected after model cutoffs from LeetCode, AtCoder, Codeforces. Scored pass@1 on hidden tests.
DeepSeek-V4-Pro 93.5% - DeepSWE In use 113 original long-horizon engineering tasks across 91 repos and five languages, written from scratch. Hand-written verifiers accept alternative solutions. GPT-6 Astra 74.1%
- SciCode In use Scientist-curated research coding problems split into subproblems across natural sciences. Code checked against test cases.
Seed2.1 Pro 59.8% - Codeforces rating In use Model solves recent Codeforces contest problems. An Elo-style rating is computed from simulated contest performance. DeepSeek V4.1 Flash 3,471