# Composer 2.5

Composer 2.5 is an AI model released by Cursor (now part of SpaceXAI) on May 18 2026. Tracked results include 81% on Next.js Evals, 54% on SWE-Bench Pro and 79.8% on SWE-Bench Multilingual.

## Facts

| Field | Value |
| --- | --- |
| Model | Composer 2.5 |
| Developer | Cursor (now part of SpaceXAI) |
| Release date | Monday, May 18 2026 |
| Licensing | Closed |

## Tracked benchmark scores

| Benchmark | Score | Source | What it measures |
| --- | --- | --- | --- |
| SWE-Bench Pro | 54% | Lab | Can the AI fix real bugs in real software? It's handed actual problems from open-source projects and has to write code that genuinely solves them. Higher is better. |
| SWE-Bench Multilingual | 79.8% | Lab | Like SWE-Bench, but the coding problems span many programming languages, not just one. Tests how broadly the AI can code. Higher is better. |
| CursorBench 4.0 | 27.7% | [CursorBench](https://cursor.com/cursorbench), retrieved 2026-09-28 | Cursor's own test of coding agents on ambiguous, multi-file tasks taken from real Cursor sessions — editing, refactoring, investigating a codebase, understanding what the user meant, managing jobs and following a design. Cursor runs each model at several reasoning efforts; each release here carries the score of its best listed effort. Scores aren't comparable with earlier CursorBench versions. Higher is better. |
| DeepSWE 1.0 | 18% | Lab | Artificial Analysis' independent test of deep, agentic software-engineering work — the AI has to plan and carry out substantial coding tasks end to end. Higher is better. |
| Next.js Evals | 81% | [Next.js Evals](https://nextjs.org/evals) | Vercel's open eval of how well AI coding agents build and migrate real Next.js apps — measured as the share of tasks the agent completes successfully. Higher is better. |
| Terminal-Bench 2.1 | 73% | Lab | Can the AI work in a command-line terminal — running commands and finishing technical setup tasks the way a developer would? Higher is better. |
| Terminal-Bench 2.0 | 69.3% | Lab | Can the AI work in a command-line terminal — running commands and finishing technical setup tasks the way a developer would? (Version 2.0 of the test.) Higher is better. |
| threejseval | 1071 | [threejseval](https://threejseval.com/ranking) | Every model gets the same prompt — "the Eiffel Tower", "a glass fishbowl", "a robot arm picking toys into a box" — and builds a 3D scene in Three.js. Real people then see two scenes side by side, names hidden, and vote for the one they prefer. The votes become a chess-style Elo rating on threejseval.com, averaged across all the prompts. It measures whether the scene looks and moves right to a human eye, not whether the code passes a test. Higher is better. |

## Questions and answers

### When was Composer 2.5 released?

Composer 2.5 was released by Cursor (now part of SpaceXAI) on Monday, May 18 2026.

### Who made Composer 2.5?

Composer 2.5 was built by Cursor (now part of SpaceXAI). Elon Musk's AI company building the Grok series of models. Founded in 2023 as xAI, now part of SpaceX. Cursor (Anysphere) and its Composer coding models were acquired in 2026 and are tracked here.

### What benchmark scores did Composer 2.5 get?

Composer 2.5 reports 8 tracked benchmark scores — SWE-Bench Pro: 54%; SWE-Bench Multilingual: 79.8%; CursorBench 4.0: 27.7%; DeepSWE 1.0: 18%; Next.js Evals: 81%; Terminal-Bench 2.1: 73%; Terminal-Bench 2.0: 69.3%; threejseval: 1071. Tracked scores may come from lab reports or independent benchmarks; source details accompany the benchmark data.

### Is Composer 2.5 open source?

No. Composer 2.5 is a closed model. The weights are not published — it is available only through the provider's own API, apps, or partner platforms.

### What came before and after Composer 2.5?

SpaceXAI's previous tracked release was Grok 4.3 Beta on Apr 17 2026, 31 days earlier. It was followed by Grok 4.5 on Jul 8 2026.


---

Canonical page: https://aireleasetracker.com/model/xai/composer-2.5
Site index: https://aireleasetracker.com/llms.txt
Source: AI Release Tracker (https://aireleasetracker.com). Most benchmark scores come from lab launch material; gathered results identify the leaderboard that published them.