GPT-5.1 Instant: benchmark results

OpenAI's fast GPT-5.1 Instant tier for low-latency chat. Provider: OpenAI. Released 2025-11-12. Access: API.

Unified ELO 1590 ± 1, rank #293 of 1392 rated models, from 13 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
ZeroEval GPQA Diamond88.1GPQA Diamond Score84.2
LLM Stats Score36.69LLM Stats Score (conservative rating)80.3
SEAL - Fortress30.36Score57.1
SEAL - MASK63.33Score53
LLM Stats (BrowseComp Long Context 128k)90Score (%)37.5
SEAL - MultiChallenge51.23Score27.6
SEAL - TutorBench49.08Score26.9
SEAL - Humanity's Last Exam6.8Score24
SEAL - Humanity's Last Exam (Text Only)6.49Score23.3
SEAL - VISTA34.87Score21
EnigmaEval1.94Score (self-reported)18
SEAL - MultiNRC18.29Score16.3

Interactive version: theaggregate.ai/model?slug=gpt-5-1-instant · How It Works · Data refreshed daily, snapshot 2026-09-05.