Benchmark Almanac

Mobile Actions

Fading

Model converts natural-language phone requests into on-device function calls (calendar, email, maps, flashlight, Wi-Fi). Call accuracy.

Identification inferred: the Reka Edge card lists 'Mobile Actions (Tool Use)' without a link. The dataset is mainly a FunctionGemma fine-tuning set.

Made by
Google
Released
December 2025
Kind
Function calling
Level
Everyday
Scored
Checked automatically
Answers
Short answer
Tasks
All public
Last in a launch post
March 2026, dropped after it saturated
Last model added
March 2026
1
Model scored in lab cards
1
Launch post lists it, from 1 lab

Reka Edge leads with 88.4%

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. 1 Reka Edge 88.4%

Source: Labs’ model cards

#ModelScoreSettingDateSource
1 Reka Edge 88.4% Mar 2026 Lab model card

Reka’s own number for Reka Edge passed 85% in March 2026

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
0% 20% 40% 60% 80% 100% 2026 Near the ceiling (85%) Reka Edge 0% 20% 40% 60% 80% 100% 2026 Near the ceiling (85%) Reka Edge

Source: Labs’ model cards

Labs headline it less often now, last in March 2026

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.

Reka
DateLaunch postScoreAs the post writes it
Mar 11, 2026 Reka Edge 88.4 Mobile Actions

More in Tool use

All 144 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. 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%