Composer 1.5vsComposer 2
Composer 1.5 | Composer 2 | |
|---|---|---|
| Benchmarks | ||
Next.js EvalsNext.js coding — 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. | 67% | 58% |
| BenchmarksPublished by one model only | ||
SWE-Bench MultilingualMultilingual coding — Like SWE-Bench, but the coding problems span many programming languages, not just one. Tests how broadly the AI can code. Higher is better. | — | 73.7% |
Terminal-Bench 2.0Agentic terminal coding — 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. | — | 61.7% |
| Overview | ||
| Company | SpaceXAI | SpaceXAI |
| Release date | Feb 9 2026 | Mar 19 2026 |
| Access | Proprietary | Proprietary |
Other comparisons
Composer 1.5vsClaude Fable 5.1Composer 2vsClaude Fable 5.1Composer 1.5vsGPT-6 AstraComposer 2vsGPT-6 AstraComposer 1.5vsGemini 3.8 FlashComposer 2vsGemini 3.8 FlashComposer 1.5vsMuse Spark 1.3Composer 2vsMuse Spark 1.3Composer 1.5vsDeepSeek-V4.1-FlashComposer 2vsDeepSeek-V4.1-FlashComposer 1.5vsMistral Medium 3.5Composer 2vsMistral Medium 3.5
Frequently asked questions
Composer 1.5 leads Composer 2 on 1 of the 1 benchmark they both report (Next.js Evals). Composer 1.5 shipped 38 days before Composer 2, so benchmark comparisons should account for the intervening progress.
Published specifications for these two models are limited — see each model page for the latest details.
On Next.js Evals, Composer 1.5 leads at 67% vs Composer 2 at 58%.