Benchmark Almanac

STATE-Bench

GPT-5.5 58.9%
Not in model cards

Agents work multi-step enterprise tasks in travel, customer support and shopping with a sandbox database, domain tools and a simulated user. They must apply the right policy.

450 tasks. A second Agent Learning Track adds train trajectories and a retrieval hook for memories or skills. Reports pass@1, pass^5 and a UX rating.

Made by
Microsoft
Released
June 2026
Kind
Customer service
Level
Expert
Scored
Graded by a model
Answers
Agent task
Tasks
All public
Strongest model tested
GPT-5.5 #20 on the capability index
Last model added
April 2026
Scores refreshed
November 12th, 2026
2
Models scored on its own leaderboard

GPT-5.5 leads with 58.9%

Best score per model from the benchmark's own leaderboard, read on November 12th, 2026. Where a model ran with several settings or harnesses, we keep its best.

  1. 58.9 GPT-5.5
  2. 58.6 GPT-5.4
  1. 1 GPT-5.5 high 58.9%
  2. 2 GPT-5.4 high 58.6%

Source: Official STATE-Bench leaderboard

#ModelScoreSettingDateSource
1 GPT-5.5 58.9% high Apr 2026 Official leaderboard
2 GPT-5.4 58.6% high Mar 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 Best so far
0% 20% 40% 60% 80% 100% 2026 Near the ceiling (85%) GPT-5.5 GPT-5.4 0% 20% 40% 60% 80% 100% 2026 Near the ceiling (85%) GPT-5.5

Source: Official STATE-Bench leaderboard

No lab model card reports it yet

We read the headline results of 522 launch posts from 52 labs, and none of them list this benchmark.

Versions

Replaces STATE-Bench Main 0.7.0

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%