ComplexFuncBench Audio (OpenAI)
gpt-realtime 66.5% Dropped
Speech-to-speech models solve ComplexFuncBench function-calling tasks whose text prompts OpenAI converted into speech. Covers multi-step calls, constraints, implicit parameters and long inputs.
OpenAI built it for the gpt-realtime launch on 2025-08-28. Scoring is assumed to follow ComplexFuncBench, which checks calls against references.
Made by OpenAI Released Aug 2025 Function calling Tasks kept private Last in a launch post Aug 2025 , dropped before it saturated
Last model added Aug 2025
- Level
- Everyday Most adults, without training
- Scored
- Checked automatically A program checks the result against an answer key, unit tests or the expected final state.
- Answers
- Agent task Many steps in a terminal, browser, desktop, app, game or robot.
1
Model scored in lab cards
1
Launch post lists it, from 1 lab
gpt-realtime leads with 66.5%
Best score per model as labs report them in their own cards. Labs pick their own settings, so these compare less cleanly than independent runs.
- 1 gpt-realtime 66.5%
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | gpt-realtime | 66.5% | Aug 2025 | Model card |
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Reported by the lab in its model card
No launch post has listed it since Aug 2025
Launch posts from every lab that has listed it, one tick per post. Tall colored ticks include it, and short gray ones leave it out.
| Date | Launch post | Score | As the post writes it |
|---|---|---|---|
| 28 Aug 2025 | gpt-realtime | 66.5 | ComplexFuncBench Audio, Function Calling |
More in Tool use
- AutomationBench In use Agent completes end-to-end business workflows inside a simulated company exposing dozens of REST APIs. Graded on resulting state.
Gemini 4 Carbon 53.9% - MCP Atlas In use Multi-step workflows over real MCP servers. Scores tool-use competency on realistic tasks.
Muse Spark 1.1 88.1% - BFCL V4 In use Models call functions and tools, including multi-turn agentic tasks with web search and memory. Checked against expected calls and outcomes.
Qwen3.7-Max 75% - τ³-bench Banking In use Agents act as banking customer-service reps over many turns with a simulated user, following policy. Pass^1 on the final database state. Qwen 3.8 Max 55.1%
- Claw-Eval In use 300 human-verified agent tasks (service orchestration, multimodal, multi-turn dialogue) audited via traces and snapshots. Rubric scores with Pass^3 consistency. Claude Sonnet 4.6 81.4%
- DeepSearchQA In use Questions that need multi-step search and synthesis. Final answers graded against references. Kimi K3 95%