Benchmark Almanac

PAgentBench

In use

Agents act as personal assistants for task management, file operations and system interactions. iFlytek built it in house.

The Spark-X2.6-4B card says it will be open-sourced soon. Grading is not described.

Released
October 2026
Kind
General assistants
Level
Everyday
Scored
Checked automatically
Answers
Agent task
Tasks
Kept private
Last in a launch post
October 2026
Last model added
October 2026
1
Model scored in lab cards
1
Launch post lists it, from 1 lab

Spark-X2.6-4B leads with 74.1%

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 Spark-X2.6-4B 74.1%

Source: Labs’ model cards

#ModelScoreSettingDateSource
1 Spark-X2.6-4B 74.1% Oct 2026 Lab 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
0% 20% 40% 60% 80% 100% 2027 Near the ceiling (85%) Spark-X2.6-4B 0% 20% 40% 60% 80% 100% 2027 Near the ceiling (85%) Spark-X2.6-4B

Source: Labs’ model cards

One lab put it in a launch post in the last six months

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.

iFlytek
DateLaunch postScoreAs the post writes it
Oct 22, 2026 Spark-X2.6-4B 74.1 PAgentBench (in-house)

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%