OpenAILanguage modelSuperseded
GPT-5.5
Codename 'Spud': a fresh pre-train that pushed 1M context into the GPT-5 line.
Overall Intelligence
#14
of 56
5.5 pts behind #1
0
races led
169
weeks at #1
83.2
score
- Released
- Apr 23, 2026
- 6 mo ago
- Context
- 1M
- 128K max output
- Price
- $5 / $30
- per 1M in/out · $11.25 blended
- Speed
- 90 tok/s
- 6s to first token
- Modalities
- text · image · audio · video
- outputs text
- Weights
- Closed
- API and apps
The 30-second version
Codename 'Spud': a fresh pre-train that pushed 1M context into the GPT-5 line.
Key takeaways
- 1Codename 'Spud': a fresh pre-train that pushed 1M context into the GPT-5 line.
Where it ranks
Current snapshot · illustrative scores · click any race to watch it
GPT-5.5Best on each axis
Overall
Coding
15Coding+8.1 pts18Frontend & UI+55 Elo16Backend & APIs+8.0 pts18Distributed Systems+10.7 pts14Full-Stack Apps+8.7 pts14Debugging & Repair+9.4 pts14Agentic Coding+9.7 pts11Code Review & Security+6.4 pts13Data Science & SQL+4.4 pts18Mobile Apps+8.2 pts13Terminal & DevOps+10.5 pts11Competitive Programming+116
Hard Reasoning
Science
Writing & Language
Multimodal
Tool Use & Agents
Speed & Cost
Overall Intelligence over time
#1 frontierGPT-5.5Muse Wonder3.5 Flash
Update history
The distilled version first; open any release for the deeper breakdown.
The GPT-5 family