GPT-5.5 Instant
OpenAI·
LLMsflagshipcloud
Overview
Default ChatGPT model, replacing GPT-5.3 Instant. API identifier 'chat-latest'. Hallucination-focused update with material gains on math and multimodal reasoning vs. its predecessor. Architecture not publicly disclosed.
Capabilities and innovations
Default ChatGPT modelAPI identifier: chat-latestMultimodal (text + image)Reduced hallucinations on high-stakes promptsTool use / function callingChatGPT default for hundreds of millions of users52.5% Hallucination Reduction vs 5.3 Instant (high-stakes, internal eval)AIME 2025 Jump 65.4 to 81.2 vs 5.3 InstantLow-latency 'Instant' tier — OpenAI states GPT-5.5 matches GPT-5.4 per-token latency in real-world serving (no AA Instant entry yet)
Benchmarks
| Benchmark | Score | Source |
|---|---|---|
| MMMU-Pro | 76% | vendor MMMU-Pro 76 (vs. 69.2 for GPT-5.3 Instant) — vendor-reported. |
- GPQA Diamond: not reported by the vendor
- Humanity’s Last Exam (no tools): not reported by the vendor
- SWE-bench Verified: not reported by the vendor
- SWE-bench Pro: not reported by the vendor
- MMLU: not reported by the vendor
- MMLU-Pro: not reported by the vendor
- Terminal-Bench 2.x: not reported by the vendor
API pricing
$5 per million input tokens, $30 per million output tokens (USD, cheapest OpenRouter endpoint, checked 2026-05-11)
Links
More from OpenAI
Data curated by AI Model Timeline. See the methodology for admission criteria, benchmark eras and source priority.