Benchmark Almanac

WorkBuddy User Blind Evaluation

DeepSeek V4.1 Flash 1017 3 leads since November 2026
Not in model cards

Agents complete everyday work requests. WorkBuddy users rate their satisfaction on a four-point scale without seeing the model identity.

Tencent reports four models, 85 internal users, and 259 tasks across 27 categories. It also reports median completion time and cost per task.

Made by
Tencent
Released
November 2026
Kind
Documents and spreadsheets
Level
University
Scored
Graded by people
Answers
Agent task
Tasks
Kept private
Measures
Preference
In and out
Text → Text, Actions
Interaction
Agentic
Environment
WorkBuddy
Refresh
One fixed set
Run by
A host
In views
Agents
Strongest model tested
Claude Haiku 5.5 #20 on the capability index
Last model added
October 2026
Scores refreshed
November 21st, 2026
4
Entries in its paper, 3 models we track

DeepSeek V4.1 Flash 1017 leads with 3 DeepSeek V4.1 Flash 1017 leads with 3

Best score per entry from the benchmark's paper, read on November 21st, 2026. A paper’s table doesn’t add newer models. 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.

Bars start at 2.4.

  1. 1 DeepSeek V4.1 Flash 1017 3
  2. 2 Claude Haiku 5.5 3
  3. 3 Hy4 flash 3
  4. 4 GLM-5.3-Flash 3

Source: The WorkBuddy User Blind Evaluation paper

Source: The WorkBuddy User Blind Evaluation paper

#EntryScoreSettingDateSource
1 DeepSeek V4.1 Flash 1017 3 Oct 2026 Official leaderboard
2 Claude Haiku 5.5 3 Oct 2026 Official leaderboard
3 Hy4 flash 3 Official leaderboard
4 GLM-5.3-Flash 3 Aug 2026 Official leaderboard
#ModelScoreSettingDateSource
1 DeepSeek V4.1 Flash 1017 3 Oct 2026 Official leaderboard
2 Claude Haiku 5.5 3 Oct 2026 Official leaderboard
3 GLM-5.3-Flash 3 Aug 2026 Official leaderboard

Number one over time

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

DeepSeek
Benchmark paper 1 leader

Source: The WorkBuddy User Blind Evaluation paper

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
In the benchmark’s paper
3 3 3 3 3 3 3 3

Source: Official WorkBuddy User Blind Evaluation 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 8 checks pass. Every benchmark

Catalog record 2 pass
  • Pass Task access The tasks are private.
  • Pass Confidence Checked against a primary source.
Scores 2 pass 3 notes
  • Pass Independent runs Scores from the benchmark’s paper (4 entries).
  • Note Models scored Only 3 models we track, plus 1 other entry on its leaderboard.
  • Pass Newest score The newest is from October 2026, for DeepSeek V4.1 Flash 1017.
  • Note Frontier models None of the top 10 has a score. The strongest tested is Claude Haiku 5.5 (#20).
  • Note Headroom Scored as a rating, with no fixed ceiling.
Leaderboard import 3 pass
  • Pass Importer We read the board on huggingface.co: 3 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