GPT-5.4 minivsQwen3.7-Plus
GPT-5.4 mini | Qwen3.7-Plus | |
|---|---|---|
| Specifications | ||
Context windowHow much text the model can hold in mind at once — your question, any documents you attach, the conversation so far, and its own reply. Go past it and the earliest part falls out of view. | 400k | — |
| 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. | $0.75 | $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. | $4.50 | $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. | $0.075 | — |
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. | $0.75Azure | — |
Cheapest outputLowest output rate across third-party providers, excluding the lab itself. May come from a different provider than the cheapest input. | $4.50Azure | — |
| 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. | 1252 | 1265 |
| 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. | 32% | — |
Supabase Evals · with skillsSupabase coding — Supabase'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. | 81.8% | — |
Supabase Evals · no skillsSupabase coding — The 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. | 63.6% | — |
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% |
BU BenchBrowser agent — Can 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. | 36% | — |
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. | 1398 | — |
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. | — | 1440 |
| Overview | ||
| Company | OpenAI | Qwen |
| Release date | Mar 17 2026 | Jun 1 2026 |
| Access | Proprietary | Proprietary |
Other comparisons
GPT-5.4 minivsClaude Opus 5Qwen3.7-PlusvsClaude Opus 5GPT-5.4 minivsGemini 3.7 FlashQwen3.7-PlusvsGemini 3.7 FlashGPT-5.4 minivsMuse GlimmerQwen3.7-PlusvsMuse GlimmerGPT-5.4 minivsGrok 4.6Qwen3.7-PlusvsGrok 4.6GPT-5.4 minivsDeepSeek-V4-Pro-0813Qwen3.7-PlusvsDeepSeek-V4-Pro-0813GPT-5.4 minivsMistral Medium 3.5Qwen3.7-PlusvsMistral Medium 3.5
Frequently asked questions
Qwen3.7-Plus leads GPT-5.4 mini on 1 of the 1 benchmark they both report (Arena Elo (Vision)). Qwen3.7-Plus is cheaper on both input and output: $0.40 vs $0.75 per million input tokens, and $1.60 vs $4.50 per million output tokens. Figures are base-tier rates. GPT-5.4 mini shipped 76 days before Qwen3.7-Plus, 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-5.4 mini at 1252.
GPT-5.4 mini was released by OpenAI on Mar 17 2026.
Qwen3.7-Plus was released by Qwen on Jun 1 2026.
Qwen3.7-Plus is cheaper on both input and output: $0.40 vs $0.75 per million input tokens, and $1.60 vs $4.50 per million output tokens. Figures are base-tier rates. Rates are pay-as-you-go API prices verified on August 18, 2026.