Compare AI models
| 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. | 52% | 58% |
BullshitBench v2Nonsense detection — Given a confidently-worded but nonsensical prompt, does the AI spot that it makes no sense and push back — instead of playing along and inventing an answer? The score is how often it clearly called out the nonsense. Higher is better. | 48% | — |
SWE-Bench VerifiedCoding — Real coding tasks pulled from open-source projects — the AI has to find and fix actual bugs. A human-checked version of the original SWE-Bench. Higher is better. | 76.2% | — |
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% |
ARC-AGI-2Abstract reasoning — Puzzle-style tests of abstract reasoning and pattern-finding — the kind of thing people find easy but AIs often struggle with. Higher is better. | 31.1% | — |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 91.9% | — |
MMMUMultimodal — Tests the AI on understanding images and text together across many college subjects. Higher is better. | 81% | — |
| Overview | ||
| Company | SpaceXAI | |
| Release date | Nov 18 2025 | Mar 19 2026 |
| Access | Closed | Closed |
| Model details | View model | View model |
Other comparisons
Gemini 3.0 ProvsClaude Sonnet 5.5Composer 2vsClaude Sonnet 5.5Gemini 3.0 ProvsGPT-6.1 SolComposer 2vsGPT-6.1 SolGemini 3.0 ProvsMuse Spark 1.3Composer 2vsMuse Spark 1.3Gemini 3.0 ProvsDeepSeek-V4.1-FlashComposer 2vsDeepSeek-V4.1-FlashGemini 3.0 ProvsMistral Medium 3.5Composer 2vsMistral Medium 3.5Gemini 3.0 ProvsKimi K3Composer 2vsKimi K3Frequently asked questions
Composer 2 leads Gemini 3.0 Pro on 1 of the 1 benchmark they both report (Next.js Evals). Gemini 3.0 Pro shipped 121 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 2 leads at 58% vs Gemini 3.0 Pro at 52%.