GPT-5.6 LunavsQwen3.7-Plus
GPT-5.6 Luna | Qwen3.7-Plus | |
|---|---|---|
| API pricingUSD per 1M tokens · lower wins · base tier | ||
Input priceWhat you pay for everything you send the model — your question, plus any documents or earlier conversation you include with it. | $0.20 | $0.40 |
Output priceWhat you pay for the text the model writes back. It is normally the dearer half: producing an answer costs more than reading one. | $1.20 | $1.60 |
Cached input priceA reduced rate for text you send over and over. If every request starts with the same instructions or the same document, the provider keeps a copy ready and charges less to read it again. | $0.02 | — |
Cheapest inputLowest input rate across third-party providers, excluding the lab itself. The cheapest endpoint may run a quantised build or a shorter context — see "Available from" on the model page. | $0.20Azure | — |
Cheapest outputLowest output rate across third-party providers, excluding the lab itself. May come from a different provider than the cheapest input. | $1.20Azure | — |
| Benchmarks | ||
Arena Elo (Vision)Community preference (vision) — Real people give two anonymous AIs the same image — a photo, a screenshot, a diagram — and vote for whichever reads it better. The votes become a chess-style Elo rating on arena.ai. It measures which AI people find more useful at looking at things, not how it scores on a fixed test set. Higher is better. | 1253 | 1265 |
Arena Elo (Documents)Community preference (documents) — Real people hand two anonymous AIs the same PDF or document and vote for whichever answers better. The votes become a chess-style Elo rating on arena.ai. Unlike a fixed document benchmark, the files are whatever people actually brought along. Higher is better. | 1462 | 1440 |
| BenchmarksPublished by one model only | ||
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. | 40% | — |
Gray Swan IPI · k = 1Prompt injection robustness — Attackers 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. | 8.3% | — |
Gray Swan IPI · k = 10Prompt injection robustness — Attackers 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. | 38.6% | — |
Gray Swan IPI · k = 15Prompt injection robustness — Attackers 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. | 43.9% | — |
CursorBench v3.2Agentic coding — Cursor'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. | 61.1% | — |
LiveCodeBenchCompetitive coding — Coding problems published so recently the AI can't have seen them in training — a contamination-free test of raw programming skill. Higher is better. | — | 89.6% |
Frontier-Bench v0.1Agentic computer work — A 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. | 14.3% | — |
Terminal-Bench 2.1Agentic terminal coding — Can the AI work in a command-line terminal — running commands and finishing technical setup tasks the way a developer would? Higher is better. | 82.5% | — |
Arena Elo (Text)Community preference — 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. | — | 1458 |
Arena Elo (Code)Community preference (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. | 1517 | — |
| Overview | ||
| Company | OpenAI | Qwen |
| Release date | Jun 26 2026 | Jun 1 2026 |
| Access | Proprietary | Proprietary |
Other comparisons
GPT-5.6 LunavsClaude Opus 5Qwen3.7-PlusvsClaude Opus 5GPT-5.6 LunavsGemini 3.7 FlashQwen3.7-PlusvsGemini 3.7 FlashGPT-5.6 LunavsMuse GlimmerQwen3.7-PlusvsMuse GlimmerGPT-5.6 LunavsGrok 4.6Qwen3.7-PlusvsGrok 4.6GPT-5.6 LunavsDeepSeek-V4-Pro-0813Qwen3.7-PlusvsDeepSeek-V4-Pro-0813GPT-5.6 LunavsMistral Medium 3.5Qwen3.7-PlusvsMistral Medium 3.5
Frequently asked questions
GPT-5.6 Luna and Qwen3.7-Plus are evenly matched across the 2 benchmarks they both report (Arena Elo (Vision), Arena Elo (Documents)). GPT-5.6 Luna is cheaper on both input and output: $0.20 vs $0.40 per million input tokens, and $1.20 vs $1.60 per million output tokens. Figures are base-tier rates. Qwen3.7-Plus shipped 25 days before GPT-5.6 Luna, 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 Arena Elo (Vision), Qwen3.7-Plus leads at 1265 vs GPT-5.6 Luna at 1253. On Arena Elo (Documents), GPT-5.6 Luna leads at 1462 vs Qwen3.7-Plus at 1440.
GPT-5.6 Luna was released by OpenAI on Jun 26 2026.
Qwen3.7-Plus was released by Qwen on Jun 1 2026.
GPT-5.6 Luna is cheaper on both input and output: $0.20 vs $0.40 per million input tokens, and $1.20 vs $1.60 per million output tokens. Figures are base-tier rates. Rates are pay-as-you-go API prices verified on August 18, 2026.