Benchmark Almanac

Speko Speech-to-Speech Benchmark (20-turn concierge call)

Not in model cards
Version 20-turn

Voice agents try to book a flight, handle a failed booking, and remember a changed date. Eight automated checks score their actions and replies.

Speko compared nine models on its speech leaderboard. Each ran the same call three times. Checks that a call never reached were omitted from its average.

Made by
Speko
Released
July 2026
Kind
Customer service
Level
Everyday
Scored
Checked automatically
Answers
Agent task
Measures
Capability
Language
English
In and out
Audio → Audio, Actions
Interaction
Agentic
Items from
Written by experts
Refresh
One fixed set
Run by
A host
Last model added
July 2026
Scores refreshed
November 21st, 2026
3
Entries on its own leaderboard, 2 models we track

gpt-realtime leads with 1.00 gpt-realtime leads with 1.00

Best score per entry from the benchmark's own leaderboard, read on November 21st, 2026. Where a model ran with several settings or harnesses, we keep its best. Names in gray aren't in our model list: fine-tunes, agent systems, products and older models. They don't count toward leaders. This view shows only models we track, each at its best.

  1. 1 gpt-realtime 1.00
  2. 2 GPT-Realtime-2.1 Mini 0.96
  3. 3 grok-voice-think-fast 0.55

Source: Official Speko Speech-to-Speech Benchmark (20-turn concierge call) leaderboard

Source: Official Speko Speech-to-Speech Benchmark (20-turn concierge call) leaderboard

#EntryScoreSettingDateSource
1 gpt-realtime 1.00 Aug 2025 Official leaderboard
2 GPT-Realtime-2.1 Mini 0.96 Jul 2026 Official leaderboard
3 grok-voice-think-fast 0.55 Official leaderboard
#ModelScoreSettingDateSource
1 gpt-realtime 1.00 Aug 2025 Official leaderboard
2 GPT-Realtime-2.1 Mini 0.96 Jul 2026 Official leaderboard

Scores over time

All the scores we have, one dot each, so a model tested at several settings appears more than once.

On the benchmark’s own leaderboard
0.96 0.97 0.98 0.99 1.00 2026 0.96 0.97 0.98 0.99 1.00 2026

Source: Official Speko Speech-to-Speech Benchmark (20-turn concierge call) leaderboard

No lab model card reports it yet

We read the headline results of 540 launch posts from 57 labs, and none of them list this benchmark.

Versions

More in Tool use

All 265 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 Neon 56.3%
  • MCP Atlas In use Multi-step workflows over real MCP servers. Scores tool-use competency on realistic tasks. Gemini 4 Argon 90.7%
  • 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%
  • Toolathlon-Verified In use 108 long-horizon tasks across 32 apps through about 600 MCP tools. Execution-based checkers inspect final environment state. GLM-5.3-Flash 78.4%
  • DeepSearchQA In use Questions that need multi-step search and synthesis. Final answers graded against references. Kimi K3 95%

Data audit

7 of 8 checks pass, 1 warning. Look first at the Task access check. We don’t know whether the tasks are public. Every benchmark

Catalog record 1 warning 1 pass
  • Warning Task access We don’t know whether the tasks are public.
  • Pass Confidence Checked against a primary source.
Scores 2 pass 3 notes
  • Pass Independent runs Scores from the official leaderboard (3 entries).
  • Note Models scored Only 2 models we track, plus 1 other entry on its leaderboard.
  • Pass Newest score The newest is from July 2026, for GPT-Realtime-2.1 Mini.
  • Note Frontier models None of its models are on the capabilities index.
  • Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
  • Pass Importer We read the board on speko.com: 2 rows for models we track and 1 other entry at the last read.
  • Pass Last read November 21st, 2026.
  • Pass Read worked The last read worked.
Consistency 1 pass 1 note
  • Note Lab claims No model has both a lab number and an independent run.
  • Pass Known issues No published audit found problems.

How we check