GPT-5.6 SolvsComposer 2.5
GPT-5.6 Sol | Composer 2.5 | |
|---|---|---|
| Benchmarks | ||
Nonsense detection BullshitBench v2Given 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. | 47% | — |
Prompt injection robustness Gray Swan IPI · k = 1Attackers hide malicious instructions inside content the AI reads — a web page, an email, a document — and try to hijack what it does. Gray Swan's indirect prompt injection benchmark measures how often such an attack succeeds when the attacker gets a single try. Lower is better. | 3.1% | — |
Prompt injection robustness Gray Swan IPI · k = 10Attackers hide malicious instructions inside content the AI reads — a web page, an email, a document — and try to hijack what it does. This variant gives the attacker 10 tries and counts an attack as successful if any of them works. Lower is better. | 16.3% | — |
Prompt injection robustness Gray Swan IPI · k = 15Attackers hide malicious instructions inside content the AI reads — a web page, an email, a document — and try to hijack what it does. This variant gives the attacker 15 tries and counts an attack as successful if any of them works. Lower is better. | 20% | — |
Agentic coding SWE-Bench ProCan 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. | — | 54% |
Multilingual coding SWE-Bench MultilingualLike SWE-Bench, but the coding problems span many programming languages, not just one. Tests how broadly the AI can code. Higher is better. | — | 79.8% |
Agentic coding CursorBench v3.2Cursor's own test of harder, real-world coding tasks inside a code editor, on the refreshed v3.2 task set. Scores aren't comparable with v3.1. Higher is better. | 67.2%Best | 56.1% |
Agentic coding CursorBench v3.1Cursor's own test of harder, real-world coding tasks inside a code editor. Higher is better. | — | 63.2% |
Agentic coding DeepSWE 1.1Artificial Analysis' independent test of deep, agentic software-engineering work — the AI has to plan and carry out substantial coding tasks end to end. (Version 1.1 of the test.) Higher is better. | 73% | — |
Agentic coding DeepSWE 1.0Artificial 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. | — | 18% |
Next.js coding Next.js EvalsVercel'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. | 92% | 92% |
Supabase coding Supabase Evals · with skillsSupabase's own open benchmark: a coding agent is dropped into a real Supabase project and asked to do real work — set up a schema, fix a broken security policy, debug an Edge Function — and every run is checked against a live Supabase stack. This is the headline number, where the agent has Supabase's own skills loaded, as most people building on Supabase would. The score is the share of scenarios it got right. Higher is better. | 95.5% | — |
Supabase coding Supabase Evals · no skillsThe same Supabase scenarios, but with none of Supabase's skills loaded — so it measures what the model already knows about building on Supabase, rather than how well it follows Supabase's supplied instructions. Higher is better. | 90.9% | — |
Agentic computer work Frontier-Bench v0.1A hard, ever-evolving set of real computer tasks — coding, system administration, data work, and more — that an AI agent has to complete on its own. Run by the Harbor / Laude Institute team as the successor to Terminal-Bench (v0.1 is the first release of the task set). The score is the share of tasks solved. Higher is better. | 34.4% | — |
Agentic terminal coding Terminal-Bench 2.1Can the AI work in a command-line terminal — running commands and finishing technical setup tasks the way a developer would? Higher is better. | 88.8%Best | 73% |
Agentic terminal coding Terminal-Bench 2.0Can 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. | — | 69.3% |
Browser agent BU BenchCan the AI drive a real web browser to finish tasks — clicking, filling forms, and navigating sites the way a person would? Run by Browser Use on their BU Bench task set. Higher is better. | 67% | — |
Knowledge work GDPval-AA v2economically valuable knowledge work (v2, re-based Elo) | 1748 | — |
Community preference Arena Elo (Text)Real people chat with two anonymous AIs side by side and vote for the answer they prefer. Votes become a chess-style Elo rating on arena.ai — it measures which AI people actually like, not test scores. Higher is better. | 1481 | — |
Community preference (code) Arena Elo (Code)Like the text arena, but people vote on which AI writes better code. The votes become a chess-style Elo rating on arena.ai. Higher is better. | 1620 | — |
| Overview | ||
| Company | OpenAI | SpaceXAI |
| Release date | Jun 26 2026 | May 18 2026 |
| Access | Proprietary | Proprietary |
Which is better: GPT-5.6 Sol or Composer 2.5?
GPT-5.6 Sol leads Composer 2.5 on 2 of the 3 benchmarks they both report (CursorBench v3.2, Next.js Evals, Terminal-Bench 2.1). Composer 2.5 shipped 39 days before GPT-5.6 Sol, 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 CursorBench v3.2, GPT-5.6 Sol leads at 67.2% vs Composer 2.5 at 56.1%. On Next.js Evals, both models score 92%. On Terminal-Bench 2.1, GPT-5.6 Sol leads at 88.8% vs Composer 2.5 at 73%.
Frequently asked questions
GPT-5.6 Sol was released by OpenAI on Jun 26 2026.
Composer 2.5 was released by SpaceXAI on May 18 2026.
GPT-5.6 Sol leads on CursorBench v3.2 — GPT-5.6 Sol 67.2% vs Composer 2.5 56.1%.
Other comparisons
GPT-5.6 SolvsClaude Opus 5Composer 2.5vsClaude Opus 5GPT-5.6 SolvsGemini 3.7 FlashComposer 2.5vsGemini 3.7 FlashGPT-5.6 SolvsMuse GlimmerComposer 2.5vsMuse GlimmerGPT-5.6 SolvsDeepSeek-V4-Pro-0813Composer 2.5vsDeepSeek-V4-Pro-0813GPT-5.6 SolvsMistral Medium 3.5Composer 2.5vsMistral Medium 3.5GPT-5.6 SolvsKimi K3Composer 2.5vsKimi K3