# GPT-Live-1.1 Benchmark Scores & Performance

> GPT-Live-1.1 has OpenAI system card results. Voice evidence is display-only and does not produce a text-model score.

Canonical page: https://benchlm.ai/models/gpt-live-1-1

Last updated: November 21, 2026

## Model Details

| Property | Value |
|----------|-------|
| Creator | OpenAI |
| Source Type | Proprietary |
| Reasoning Type | Non-Reasoning |
| Context Window | N/A |
| Official model card | [OpenAI model card](https://deploymentsafety.openai.com/gpt-live-1-1/gpt-live-1-1.pdf) |
| Overall Score | Not scored (voice evidence only) |
| Overall Rank | Unranked |

## Family & Coverage

- Family: GPT-Live-1.1
- Variant: base
- Benchmarks covered: 0 of 835
- Related earlier model: [GPT-Live-1](/models/gpt-live-1)
- Coverage note: Speech and voice results appear below; no weighted text-model benchmark rows are stored.

## Speech and voice evidence

[GPT-Live-1.1 system card safety evaluations](/voice-benchmarks/gpt-live-1-1-system-card)

These are provider-reported safety results, not a capability or voice-quality score. OpenAI built the sets around cases where earlier voice models gave poor answers, so the scores are not prevalence-weighted and do not describe real traffic. The API models were run with delegation off, so they show the front-end voice model alone, not the backend model a deployment would use. The ChatGPT configurations of GPT-Live-1.1 and GPT-Live-1.1 Quip are scored separately in the card and are not shown here.

| Metric | Result |
| --- | --- |
| Production prompts: emotional reliance | 0.72 (GPT-Live-1: 0.65) |
| Production prompts: self-harm | 0.78 (GPT-Live-1: 0.77) |
| Production prompts: mental health | 0.62 (GPT-Live-1: 0.61) |
| Synthetic prompts: gore | 0.85 (GPT-Live-1: 0.74) |
| Synthetic prompts: hate | 0.97 (GPT-Live-1: 0.95) |
| Synthetic prompts: illicit behavior | 0.92 (GPT-Live-1: 0.89) |
| Capability benchmarks | Not published |

OpenAI system card · November 19, 2026 · API models with delegation off · share of responses graded not unsafe, higher is better

- [Evaluation source](https://deploymentsafety.openai.com/gpt-live-1-1/gpt-live-1-1.pdf)

Available in the OpenAI API as gpt-live-1.1 since November 19, 2026 through v1/live/sessions only; the Realtime, Responses, and Chat Completions endpoints do not accept it. Audio and text in, audio and text out. It has its own concurrent-session limit, separate from GPT-Live-1. A ChatGPT version of GPT-Live-1.1 and a smaller GPT-Live-1.1 Quip have powered ChatGPT Voice since October 15, 2026; Quip is not offered in the API.

## Other OpenAI Models

- [GPT-6.2 Astra](/models/gpt-6-2-astra) - Score: 90.8
- [GPT-6 Astra](/models/gpt-6-astra) - Score: 83.6
- [GPT-6.2 Sol](/models/gpt-6-2-sol) - Score: 82.3
- [GPT-6.1 Sol](/models/gpt-6-1-sol) - Score: 81.1
- [GPT-6.1 Terra](/models/gpt-6-1-terra) - Score: 80.8
- [GPT-6 Sol](/models/gpt-6-sol) - Score: 73.5
- [GPT-5.6 Sol](/models/gpt-5-6-sol) - Score: 73.2
- [GPT-5.5 Pro](/models/gpt-5-5-pro) - Score: 70.2
- [GPT-5.5](/models/gpt-5-5) - Score: 69.2
- [GPT-5.4 Pro](/models/gpt-5-4-pro) - Score: 68.3
- [GPT-5.6 Terra](/models/gpt-5-6-terra) - Score: 65.9
- [GPT-5.2 Pro](/models/gpt-5-2-pro) - Score: 63.3
- [GPT-5.4](/models/gpt-5-4) - Score: 63
- [GPT-6 Luna](/models/gpt-6-luna) - Score: 61.3
- [GPT-5.6 Luna](/models/gpt-5-6-luna) - Score: 60.3
- [GPT-5.2](/models/gpt-5-2) - Score: 60.2
- [GPT-5.3 Codex](/models/gpt-5-3-codex) - Score: 57.6
- [o3](/models/o3) - Score: 55.5
- [GPT-5](/models/gpt-5) - Score: 54.2
- [GPT-5.1](/models/gpt-5-1) - Score: 52.3
- [o3-pro](/models/o3-pro) - Score: 50.4
- [GPT-5.4 mini](/models/gpt-5-4-mini) - Score: 50.1
- [GPT-5.2-Codex](/models/gpt-5-2-codex) - Score: 49.2
- [GPT-5.1-Codex-Max](/models/gpt-5-1-codex-max) - Score: 45.9
- [GPT-5.4 nano](/models/gpt-5-4-nano) - Score: 44
- [o1](/models/o1) - Score: 43.8
- [GPT-5.1-Codex](/models/gpt-5-1-codex) - Score: 43.8
- [o3-mini](/models/o3-mini) - Score: 43.7
- [GPT-5 mini](/models/gpt-5-mini) - Score: 41.9
- [o1-preview](/models/o1-preview) - Score: 43.5
- [GPT-5 nano](/models/gpt-5-nano) - Score: 40.9
- [GPT-4.1](/models/gpt-4-1) - Score: 38.1
- [GPT-OSS 120B](/models/gpt-oss-120b) - Score: 37.3
- [GPT-4 Turbo](/models/gpt-4-turbo) - Score: 33.8
- [GPT-4.1 mini](/models/gpt-4-1-mini) - Score: 33.1
- [GPT-4o](/models/gpt-4o) - Score: 30.2
- [GPT-OSS 20B](/models/gpt-oss-20b) - Score: 30.2
- [GPT-4o mini](/models/gpt-4o-mini) - Score: 29.9
- [GPT-4.1 nano](/models/gpt-4-1-nano) - Score: 21
- [GPT-4.5](/models/gpt-4-5) - Score: not computed
- [o4-mini](/models/o4-mini) - Score: not computed
- [o1-mini](/models/o1-mini) - Score: not computed
- [GPT-5.2 Instant](/models/gpt-5-2-instant) - Score: not computed
- [GPT-5.3 Instant](/models/gpt-5-3-instant) - Score: not computed
- [GPT-5.3-Codex-Spark](/models/gpt-5-3-codex-spark) - Score: not computed
- [GPT-6 Cyber](/models/gpt-6-cyber) - Score: not computed
- [GPT-5.6 Cyber](/models/gpt-5-6-cyber) - Score: not computed
- [GPT-6 Luna (Decisions)](/models/gpt-6-luna-decisions) - Score: not computed
- [GPT-Live-1](/models/gpt-live-1) - Score: not computed
- [GPT Live Transcribe](/models/gpt-live-transcribe) - Score: not computed
- [GPT Transcribe](/models/gpt-transcribe) - Score: not computed
- [GPT Realtime 2.1](/models/gpt-realtime-2-1) - Score: not computed
- [GPT Realtime 2.1 Mini](/models/gpt-realtime-2-1-mini) - Score: not computed
- [GPT Audio 1.5](/models/gpt-audio-1-5) - Score: not computed
- [GPT Realtime 1.5](/models/gpt-realtime-1-5) - Score: not computed
- [GPT Realtime mini](/models/gpt-realtime-mini) - Score: not computed
- [GPT Realtime](/models/gpt-realtime) - Score: not computed
- [GPT-4o mini TTS](/models/gpt-4o-mini-tts) - Score: not computed
- [o1-pro](/models/o1-pro) - Score: not computed
- [GPT-4o mini Audio](/models/gpt-4o-mini-audio) - Score: not computed
- [GPT-4o Audio](/models/gpt-4o-audio) - Score: not computed
- [Whisper large-v3-turbo](/models/whisper-large-v3-turbo) - Score: not computed
- [GPT Realtime 2](/models/gpt-realtime-2) - Score: not computed
