Benchmark Almanac

RealWorkDecision

Grok 4.7 43.8% leads since October 2026
Not in model cards

Agents review a frozen company workspace and predict the decision an employee made. Expert-written rubrics allow valid alternatives.

The micro1 leaderboard reports pass rates for ten model configurations across 53 frozen workspaces.

Made by
micro1
Released
October 2026
Kind
Tasks from real jobs
Level
University
Scored
Graded by a model
Answers
Agent task
Tasks
Kept private
Measures
Capability
Language
English
In and out
Text → Actions, Text
Interaction
Agentic
Environment
APIs and tools
Items from
Real work and use
Refresh
One fixed set
Run by
A host
Strongest model tested
GPT-6 Astra #4 on the capability index
Last model added
October 2026
Scores refreshed
November 20th, 2026
10
Models scored on its own leaderboard

Grok 4.7 leads with 43.8%

Best score per model from the benchmark's own leaderboard, read on November 20th, 2026. Where a model ran with several settings or harnesses, we keep its best.

  1. 1 Grok 4.7 43.8%
  2. 2 Claude Opus 5 36.1%
  3. 3 Claude Opus 5.5 32.6%
  4. 4 GPT-6 Astra 29.9%
  5. 5 GPT-6.1 Sol 29.2%
  6. 6 Claude Sonnet 5 27.1%
  7. 7 Claude Haiku 5.5 23.6%
  8. 8 Kimi K3 22.9%
  9. 9 Inkling 18.8%
  10. 10 GPT-5.4 Mini 14.6%

Source: Official RealWorkDecision leaderboard

#ModelScoreSettingReleasedRun onSource
1 Grok 4.7 43.8% Sep 2026 Oct 2026 Official leaderboard
2 Claude Opus 5 36.1% Jul 2026 Oct 2026 Official leaderboard
3 Claude Opus 5.5 32.6% Sep 2026 Oct 2026 Official leaderboard
4 GPT-6 Astra 29.9% Sep 2026 Oct 2026 Official leaderboard
5 GPT-6.1 Sol 29.2% Sep 2026 Oct 2026 Official leaderboard
6 Claude Sonnet 5 27.1% Jun 2026 Oct 2026 Official leaderboard
7 Claude Haiku 5.5 23.6% Oct 2026 Oct 2026 Official leaderboard
8 Kimi K3 22.9% Jul 2026 Oct 2026 Official leaderboard
9 Inkling 18.8% Jul 2026 Oct 2026 Official leaderboard
10 GPT-5.4 Mini 14.6% Mar 2026 Oct 2026 Official leaderboard

Number one over time

Lab claims count from the day the card came out, independent runs from the model’s release.

xAI
Own leaderboard 1 leader
Grok 4.7 43.8%

Source: Official RealWorkDecision leaderboard

Scores over time

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

Plot with other benchmarks
On the benchmark’s own leaderboard Best so far
0% 20% 40% 60% 80% 100% 2026 Near the ceiling (85%) Grok 4.7 Claude Opus 5 Claude Sonnet 5 GPT-5.4 Mini 0% 20% 40% 60% 80% 100% 2026 Near the ceiling (85%) Grok 4.7 Claude Opus 5

Source: Official RealWorkDecision 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.

More in Economic work

All 210 in Economic work
  • JobBench In use 130 tasks from 35 occupations workers most want delegated. Agent works through messy reference files, graded by fact-anchored binary rubrics. GLM-5.3 61.4%
  • GDPval In use Real work tasks from 44 occupations with reference files. Experts blindly compare model deliverables with expert work. Metric is win-or-tie rate. Seed2.1 Pro 87.9%
  • GDPval-AA v2.1 In use Agents with shell and web access complete 220 GDPval gold tasks from 44 occupations. Blind pairwise comparisons give Elo ratings. Claude Opus 5.5 1,846
  • AA-Briefcase v1.1 In use Version 1.1 of Artificial Analysis's multi-hour office work evaluation, with Elo ratings fitted by Crowd-BT. Claude Opus 5.5 1,822
  • Agents' Last Exam v1.1 In use Agents complete 122 public long-horizon professional workflow tasks across 55 sub-industries. Deterministic graders check outcomes against hidden references. GPT-6.2 Astra 47.5%
  • CoWorkBench In use Agent completes long-horizon productivity tasks across computer science, finance, law and medicine. Qwen in-house scoring (method unpublished). Claude Fable 5 75.9%

Data audit

All 11 checks pass. Every benchmark

Catalog record 2 pass
  • Pass Task access The tasks are private.
  • Pass Confidence Checked against a primary source.
Scores 5 pass
  • Pass Independent runs Scores from the official leaderboard (10 entries).
  • Pass Models scored 10 models we track.
  • Pass Newest score The newest is from October 2026, for Claude Haiku 5.5.
  • Pass Frontier models 3 of the top 10 have a score, led by GPT-6 Astra (#4).
  • Pass Headroom The best is 43.8%, under 85%, so it still separates models.
Leaderboard import 3 pass
  • Pass Importer We read the board on micro1.ai: 10 rows for models we track at the last read.
  • Pass Last read November 20th, 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