Benchmark Almanac

TakeoffBench-v1

Handoff-H1 81.6% tops its leaderboard Claude Fable 5 61.4% leads the models we track
Not in model cards

Agents read residential blueprints and list material quantities by trade. A model judge matches items to expert estimates. The score combines coverage and quantity precision.

Handoff ranks seven general-purpose models alongside its estimating system and human estimators. It publishes the harness and reviews requests for the ten drawing sets.

Made by
Handoff
Released
July 2026
Kind
Tasks from real jobs
Level
Expert
Scored
Graded by a model
Answers
Agent task
Tasks
Public, plus a private test set
Measures
Capability
Language
English
In and out
Text, Documents → Text, Tables
Interaction
Single turn
Refresh
One fixed set
Run by
A host
Occupations
Business and financial operations
Strongest model tested
Claude Fable 5 #12 on the capability index
Last model added
June 2026
Scores refreshed
November 20th, 2026
8
Entries on its own leaderboard, 6 models we track

Handoff-H1 tops the leaderboard with 81.6% Claude Fable 5 leads with 61.4% among models released by June 2026

Best score per entry from the benchmark's own leaderboard, read on November 20th, 2026. 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. The best model we track is Claude Fable 5, at 61.4%. This view shows only models we track, each at its best.

The newest model with a score here came out in June 2026, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:

  1. 1 Handoff-H1 81.6%
  2. 2 Claude Fable 5 61.4%
  3. 3 gpt-5.6 58.6%
  4. 4 Claude Opus 4.8 54.6%
  5. 5 Kimi K2.6 54.5%
  6. 6 Claude Sonnet 4.6 53.9%
  7. 7 GLM-5.2 41.6%
  8. 8 DeepSeek-V4-Pro 34.7%

Source: Official TakeoffBench-v1 leaderboard

#EntryScoreSettingDateSource
1 Handoff-H1 81.6% Official leaderboard
2 Claude Fable 5 61.4% Jun 2026 Official leaderboard
3 gpt-5.6 58.6% Official leaderboard
4 Claude Opus 4.8 54.6% May 2026 Official leaderboard
5 Kimi K2.6 54.5% Apr 2026 Official leaderboard
6 Claude Sonnet 4.6 53.9% Feb 2026 Official leaderboard
7 GLM-5.2 41.6% Jun 2026 Official leaderboard
8 DeepSeek-V4-Pro 34.7% Apr 2026 Official leaderboard
#ModelScoreSettingDateSource
1 Claude Fable 5 61.4% Jun 2026 Official leaderboard
2 Claude Opus 4.8 54.6% May 2026 Official leaderboard
3 Kimi K2.6 54.5% Apr 2026 Official leaderboard
4 Claude Sonnet 4.6 53.9% Feb 2026 Official leaderboard
5 GLM-5.2 41.6% Jun 2026 Official leaderboard
6 DeepSeek-V4-Pro 34.7% Apr 2026 Official leaderboard

Number one over time

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

Anthropic
Own leaderboard Not tested since Jul 2026

Source: Official TakeoffBench-v1 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%) Claude Fable 5 Claude Opus 4.8 Claude Sonnet 4.6 0% 20% 40% 60% 80% 100% 2026 Near the ceiling (85%) Claude Fable 5 Claude Opus 4.8

Source: Official TakeoffBench-v1 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 10 checks pass. Every benchmark

Catalog record 2 pass
  • Pass Task access Public tasks, plus a private test set.
  • Pass Confidence Checked against a primary source.
Scores 4 pass 1 note
  • Pass Independent runs Scores from the official leaderboard (8 entries).
  • Pass Models scored 6 models we track, plus 2 other entries on its leaderboard.
  • Pass Newest score The newest is from June 2026, for GLM-5.2.
  • Note Frontier models None of the top 10 has a score. The strongest tested is Claude Fable 5 (#12).
  • Pass Headroom The best is 61.4%, under 85%, so it still separates models.
Leaderboard import 3 pass
  • Pass Importer We read the board on handoff.ai: 6 rows for models we track and 2 other entries 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