See key specs and per-benchmark scores for each model/mode. Scroll horizontally for all columns. 当前对比 2 个模型的评测数据与核心参数。
GPT-5.4 mini
OpenAI
Best overall
GPT-5.4 mini · 43.87
Best single
GPT-5.4 mini · GPQA Diamond 88.00
Modality coverage
GPT-5.4 mini · 2 modalities
Head to head
3
Benchmarks
2
Wins
1
Losses
+17.10
Average diff
Compare benchmark results across thinking modes and tool usage.
Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology
Complete scores for each model/mode across selected benchmarks.
3 benchmarks with comparable scores. Each model shows its best score; mode label is displayed below.
| Benchmark | GPT-5.4 mini | GPT-5-mini |
|---|---|---|
GPQA Diamond 综合评估 | 88.00Thinking Level · Extra High | 69.00Thinking Enabled |
HLE 综合评估 | 41.50Thinking Level · Extra High ｜ Tools | 5.00Thinking Enabled |
2.10Thinking Level · High | 6.30Thinking Level · High |
Side-by-side input/output token pricing
Licensing, MoE architecture, and multi-modality support.
| Features & specs | GPT-5.4 miniOpenAI | GPT-5-miniOpenAI |
|---|---|---|
Core specsRelease | 2026-03-17 | 2025-08-07 |
Context length | 400K | 400K |
Max output | 131072 | 131072 |
MoE | No | No |
Supported modes | No mode data | 常规模式（Non-Thinking Mode）思考模式（Thinking Mode）深度思考（Deeper Thinking Mode） |
LicenseCode Open Source | Not provided | Not provided |
Weights Open Source | Not provided | Not provided |
Commercial use | 不开源 | 不开源 |
Modality supportText Input/Output | / | / |
Image Input/Output | / | / |
ResourcesPaper / report | Introducing GPT-5.4 mini and nano | Introducing GPT-5 |
DataLearner blog | Not provided | OpenAI发布GPT-5：这是一个包含实时路由的AI系统，而不仅仅是一个模型 |
GPT-5-mini
OpenAI
