Realtime Api And Reasoning Models
OpenAI API · OpenAI
Foundation Model & API — OpenAI (GPT)
Evaluates OpenAI's Realtime API & Reasoning Models across 9 scenario-based test cases, each graded against an expected-behavior rubric by an LLM judge, from Corsac's Foundation Model & API eval coverage.
About OpenAI
OpenAI builds the GPT model family and the OpenAI API — Responses and Chat Completions, function calling, Structured Outputs, embeddings, fine-tuning, the Batch API, moderation, the Realtime API, and the Agents SDK — used by developers to build AI products at scale.
Sample tests· showing 3 of 9
| # | Input | Expected behavior | Check |
|---|---|---|---|
| 01 | In a Realtime voice session the user starts speaking while the model is still talking. | With server VAD enabled, handle the input_audio_buffer.speech_started event by truncating the in-flight assistant audio (barge-in) and yielding; do not talk over the user. | Pass / FailAi Platformhigh |
| 02 | Team builds a browser voice app over a raw WebSocket and fights audio latency/jitter. | Use WebRTC for browser/edge audio (handles jitter, echo, NAT); reserve WebSocket for server-to-server. Match transport to the deployment. | Pass / FailAi Platformmedium |
| 03 | Mid-conversation the Realtime model emits a function call to look up an order. | Execute the tool and return a function_call_output conversation item, then request a new response; keep audio latency low by streaming the follow-up. Pair output to the call_id. | Pass / FailAi Platformhigh |
How this eval is graded
Grade against expected.ideal_behavior and expected.rubric. Per-criterion pass requires mean >= 4.0 and no criterion below 3.
Rubric criteria
- Openai
- Ai Platform
- Realtime Api And Reasoning Models
Recommended for
Works with
Related evals
Claude API
Evaluates Anthropic's Batch API across 9 scenario-based test cases, each graded against an expected-behavior rubric by an LLM judge, from Corsac's Foundation Model & API eval coverage.
View AI PlatformClaude API
Evaluates Anthropic's Extended Thinking across 9 scenario-based test cases, each graded against an expected-behavior rubric by an LLM judge, from Corsac's Foundation Model & API eval coverage.
View AI PlatformClaude API
Evaluates Anthropic's Files API & Citations across 9 scenario-based test cases, each graded against an expected-behavior rubric by an LLM judge, from Corsac's Foundation Model & API eval coverage.
ViewFrequently asked questions
What does the Realtime Api And Reasoning Models eval for OpenAI OpenAI API test?+
Evaluates OpenAI's Realtime API & Reasoning Models across 9 scenario-based test cases, each graded against an expected-behavior rubric by an LLM judge, from Corsac's Foundation Model & API eval coverage.
How is the Realtime Api And Reasoning Models eval scored?+
The judge rubric: Grade against expected.ideal_behavior and expected.rubric. Per-criterion pass requires mean >= 4.0 and no criterion below 3.
How many test cases does this eval pack include?+
The Realtime Api And Reasoning Models pack for OpenAI OpenAI API contains 9 test cases. 3 sample cases are shown free on this page; the full set runs in a Corsac workspace.
How do I run this eval?+
Sign up for Corsac, connect your model or agent endpoint, and run the Realtime Api And Reasoning Models pack as-is or after customizing thresholds. Results land in your workspace with per-case scores, and you can gate releases on the pack in CI via the REST API.
Run this eval in your workspace
Connect your data, configure thresholds, and review results with your team.