// head_to_head
GPT-5.4 Mini vs Qwen3.6 27B
Published LiveBench scores across all seven categories, live list pricing, context windows, and the measured cost of a point of capability — for both models, side by side.
GPT-5.4 Mini scores higher, Qwen3.6 27B costs less — it depends on your workload.
GPT-5.4 Mini is ahead by 2.3 points overall, and Qwen3.6 27B lists 1.8× cheaper per blended million tokens. Whether 2.3 points is worth that depends on how much a wrong answer costs you. Qwen3.6 27B also leads on measured cost per point of capability, at $0.1074 per point.
openai
GPT-5.4 Mini
- Blended / 1M
- $1.69
- Context
- 400K
- Released
- Mar 17, 2026
- Overall score
- 66.4
qwen
Qwen3.6 27B
- Blended / 1M
- $0.915
- Context
- 262K
- Released
- Apr 27, 2026
- Overall score
- 64.0
Specs and pricing
| Metric | GPT-5.4 Mini | Qwen3.6 27B |
|---|---|---|
| LiveBench overall Mean of the seven LiveBench category scores, 0–100. Higher is better. | 66.4win | 64.0 |
| Cost per point Measured benchmark spend divided by overall score — dollars per point of capability. | $0.1871 | $0.1074win |
| Blended price / 1M 3:1 input:output mix, the usual shape of production traffic. | $1.69 | $0.915win |
| Input price / 1M | $0.750 | $0.320win |
| Output price / 1M | $4.50 | $2.70win |
| Cached input / 1M Price of an input token served from the prompt cache, where the provider publishes one. | $0.075win | $0.150 |
| Context window | 400Kwin | 262K |
| Max output tokens | 128K | 262Kwin |
Benchmarks by category
An overall score averages away the thing you probably care about. These are the seven LiveBench categories scored separately — GPT-5.4 Mini on top, Qwen3.6 27B below, both out of 100.
What each one costs to run
Per-token prices are hard to feel. These are monthly list costs for both models across five workload shapes, using each provider's published cached-input rate where there is one.
| Workload | GPT-5.4 Mini | Qwen3.6 27B |
|---|---|---|
| Support chatbot 1.2K in / 400 out × 200K requests | $491.40/mo | $280.56/mo |
| RAG assistant 8K in / 600 out × 100K requests | $600.00/mo | $350.00/mo |
| Coding agent 40K in / 4K out × 20K requests | $582.00/mo | $376.80/mo |
| Document extraction 20K in / 1.5K out × 50K requests | $1,054/mo | $514.00/mo |
| Bulk classification 500 in / 20 out × 5M requests | $1,988/mo | $985.00/mo |
Which should you pick?
You are running this at volume
Qwen3.6 27B
Lowest measured cost per point of capability at $0.1074 per point — the gap compounds with every request.
Quality matters more than the bill
GPT-5.4 Mini
Highest overall LiveBench score of the two at 66.4.
The workload is coding or agentic work
GPT-5.4 Mini
Leads on agentic coding — 41.7 against 39.3.
You need to fit large documents in one call
GPT-5.4 Mini
Wider context window — 400K against 262K.
GPT-5.4 Mini vs Qwen3.6 27B FAQ
Which is better, GPT-5.4 Mini or Qwen3.6 27B?
GPT-5.4 Mini scores higher, Qwen3.6 27B costs less — it depends on your workload. GPT-5.4 Mini is ahead by 2.3 points overall, and Qwen3.6 27B lists 1.8× cheaper per blended million tokens. Whether 2.3 points is worth that depends on how much a wrong answer costs you. Qwen3.6 27B also leads on measured cost per point of capability, at $0.1074 per point.
Is GPT-5.4 Mini cheaper than Qwen3.6 27B?
Qwen3.6 27B is cheaper. On a 3:1 input:output blend, GPT-5.4 Mini lists at $1.69 per million tokens and Qwen3.6 27B at $0.915 — Qwen3.6 27B is 1.8× cheaper. Input and output are priced separately — GPT-5.4 Mini charges $0.750 in and $4.50 out, Qwen3.6 27B charges $0.320 and $2.70 — so the model that looks cheaper flips depending on how output-heavy your workload is.
GPT-5.4 Mini vs Qwen3.6 27B: which scores higher on benchmarks?
GPT-5.4 Mini scores 66.4 and Qwen3.6 27B scores 64.0 overall on LiveBench, the mean of its seven categories. That is a 2.3-point lead for GPT-5.4 Mini. Category scores differ from the overall figure — a model can lead on reasoning and trail on coding, which the per-category table above breaks out.
Which gives better value for money, GPT-5.4 Mini or Qwen3.6 27B?
Qwen3.6 27B. Cost per point divides the measured dollars LiveBench spent running the benchmark by the score it earned, so it captures something token pricing misses: a reasoning model can emit many times more tokens than its per-token rate suggests. GPT-5.4 Mini works out at $0.1871 per point and Qwen3.6 27B at $0.1074.
Does GPT-5.4 Mini or Qwen3.6 27B have a bigger context window?
GPT-5.4 Mini has the larger context window: 400K for GPT-5.4 Mini against 262K for Qwen3.6 27B. Note that a window you can fill is not a window you should fill — retrieval quality usually degrades well before the limit, and you pay for every token you put in it.
Do GPT-5.4 Mini and Qwen3.6 27B support prompt caching?
Both publish a cached-input rate: $0.075 per million for GPT-5.4 Mini and $0.150 for Qwen3.6 27B, against full input rates of $0.750 and $0.320. On a workload with a long stable prefix — a system prompt, a tool schema, a retrieved corpus — that changes the economics more than the headline price does.
Related comparisons
How these numbers are produced
- Price — provider list price from OpenRouter, refreshed every 15 minutes. “Blended” is a 3:1 input:output mix.
- Scores — LiveBench release 2026-06-25, using their own category map. Each model shows its strongest published run. A blank means “not evaluated”, never “bad”.
- Cost per point — the measured dollars LiveBench spent on the run, divided by the score it earned.
- “Win” — awarded only past a threshold: one full point on a benchmark score, 10% on a price, 25% on a context window. Anything tighter reports as a tie, because effort settings alone move a LiveBench score by more than that.
Published benchmarks rank models on someone else's tasks. Before committing, see LLM & agent evaluation for building an eval on your own.