Construction's Last Exam v2
Version 2
Models measure construction drawings, answer questions across sheets, and price quantities under contract rules. The board reports geometry, drawing reasoning, and estimating separately.
Togal reports scores for 22 models across the three tracks. The answer files contain scores on 60 tasks and nine additional unscored estimating tasks.
- Made by
- Togal.AI
- Released
- October 2026
- Kind
- Tasks from real jobs
- Level
- Expert
- Scored
- Checked automatically
- Answers
- Agent task
- Measures
- Capability
- Subject
- Civil engineering
- Language
- English
- Interaction
- Agentic
- Environment
- APIs and tools
- Items from
- Real work and use
- Refresh
- New versions replace it
- Run by
- A host
- Based on
- Construction's Last Exam
- In views
- Agents
- Strongest model tested
- Claude Fable 5.1 #8 on the capability index
- Last model added
- September 2026
- Scores refreshed
- November 20th, 2026
Gemini 3.6 Flash leads with 36.8% among models released by September 2026
Best score per model from the benchmark's own leaderboard, read on November 20th, 2026. Plain mean of the geometric, reasoning, and end-to-end track scores. Where a model ran with several settings or harnesses, we keep its best. Every run is in the next chart.
The newest model with a score here came out in September 2026, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:
- GPT-6.2 Astra
- Claude Fable 5.2
-
Gemini 4 Carbon
- GPT-6 Astra
- and 14 more
- 1
Gemini 3.6 Flash 36.8%
- 2 Claude Fable 5.1 35.3%
- 3
Gemini 3.7 Flash 31.6%
- 4 Claude Opus 5 31.5%
- 5
Gemini 3.5 Flash-Lite 22.4%
- 6 Claude Opus 4.6 21.6%
- 7
Gemini 3.1 Flash-Lite 19.1%
- 8 Claude Sonnet 5 14.3%
- 9 Claude Haiku 4.5 12.4%
Source: Official Construction's Last Exam v2 leaderboard
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | | 36.8% | Jul 2026 | Official leaderboard | |
| 2 | Claude Fable 5.1 | 35.3% | Sep 2026 | Official leaderboard | |
| 3 | | 31.6% | Aug 2026 | Official leaderboard | |
| 4 | Claude Opus 5 | 31.5% | Jul 2026 | Official leaderboard | |
| 5 | | 22.4% | Jul 2026 | Official leaderboard | |
| 6 | Claude Opus 4.6 | 21.6% | Feb 2026 | Official leaderboard | |
| 7 | | 19.1% | Mar 2026 | Official leaderboard | |
| 8 | Claude Sonnet 5 | 14.3% | Jun 2026 | Official leaderboard | |
| 9 | Claude Haiku 4.5 | 12.4% | Oct 2025 | Official leaderboard |
Rankings by part
We read 10 parts from the benchmark’s own leaderboard, each ranking models on one part of the test, such as Geometric, Reasoning and End-to-end. Gemini 3.7 Flash leads 3 of them, and 3 other models lead the rest. Arrows show how far a model moved from its overall rank among the models we track.
Geometric
9 models we track have a score here.
- 1
Gemini 3.7 Flash ↑2 19.2%
- 2
Gemini 3.6 Flash ↓1 13.8%
- 3 Claude Fable 5.1 ↓1 12.5%
- 4 Claude Opus 5 12.1%
- 5
Gemini 3.1 Flash-Lite ↑2 5.60%
- 6
Gemini 3.5 Flash-Lite ↓1 5.40%
- 7 Claude Haiku 4.5 ↑2 3.90%
- 8 Claude Opus 4.6 ↓2 3.80%
- 9 Claude Sonnet 5 ↓1 2.70%
Reasoning
9 models we track have a score here.
- 1
Gemini 3.6 Flash 83.2%
- 2 Claude Opus 5 ↑2 67.9%
- 3
Gemini 3.7 Flash 67.5%
- 4 Claude Fable 5.1 ↓2 65.9%
- 5
Gemini 3.5 Flash-Lite 55.3%
- 6 Claude Opus 4.6 47.1%
- 7
Gemini 3.1 Flash-Lite 46.6%
- 8 Claude Sonnet 5 35.8%
- 9 Claude Haiku 4.5 31.9%
End-to-end
9 models we track have a score here.
- 1 Claude Fable 5.1 ↑1 27.6%
- 2 Claude Opus 5 ↑2 14.6%
- 3 Claude Opus 4.6 ↑3 14%
- 4
Gemini 3.6 Flash ↓3 13.4%
- 5
Gemini 3.7 Flash ↓2 8.00%
- 6
Gemini 3.5 Flash-Lite ↓1 6.40%
- 7
Gemini 3.1 Flash-Lite 5.10%
- 8 Claude Sonnet 5 4.50%
- 9 Claude Haiku 4.5 1.40%
Linear
9 models we track have a score here.
- 1
Gemini 3.7 Flash ↑2 18.7%
- 2 Claude Opus 5 ↑2 14.8%
- 3 Claude Fable 5.1 ↓1 8.70%
- 4
Gemini 3.1 Flash-Lite ↑3 7.30%
- 5
Gemini 3.6 Flash ↓4 6.20%
- 6
Gemini 3.5 Flash-Lite ↓1 3.10%
- 7 Claude Opus 4.6 ↓1 2.10%
- 8 Claude Haiku 4.5 ↑1 1.40%
- 9 Claude Sonnet 5 ↓1 0.10%
Areas
9 models we track have a score here.
- 1 Claude Fable 5.1 ↑1 16.9%
- 2
Gemini 3.7 Flash ↑1 13.6%
- 3
Gemini 3.6 Flash ↓2 11.6%
- 4 Claude Opus 5 10.6%
- 5
Gemini 3.5 Flash-Lite 7.70%
- 6
Gemini 3.1 Flash-Lite ↑1 6.20%
- 7 Claude Sonnet 5 ↑1 4.80%
- 8 Claude Opus 4.6 ↓2 4.70%
- 9 Claude Haiku 4.5 3.50%
Counting
9 models we track have a score here.
- 1
Gemini 3.7 Flash ↑2 25%
- 2
Gemini 3.6 Flash ↓1 18.2%
- 3 Claude Opus 5 ↑1 12.7%
- 4 Claude Fable 5.1 ↓2 11.1%
- 5 Claude Haiku 4.5 ↑4 5.00%
- 6
Gemini 3.1 Flash-Lite ↑1 4.40%
- 7
Gemini 3.5 Flash-Lite ↓2 3.90%
- 8 Claude Opus 4.6 ↓2 3.60%
- 9 Claude Sonnet 5 ↓1 1.40%
Legend
9 models we track have a score here.
- 1 Claude Opus 5 ↑3 70%
- 2
Gemini 3.6 Flash ↓1 64.4%
- 3 Claude Fable 5.1 ↓1 50%
- 4
Gemini 3.7 Flash ↓1 25%
- 5
Gemini 3.5 Flash-Lite 20%
- 6 Claude Haiku 4.5 ↑3 0%
- 7 Claude Opus 4.6 ↓1 0%
- 8
Gemini 3.1 Flash-Lite ↓1 0%
- 9 Claude Sonnet 5 ↓1 0%
Assemblies
9 models we track have a score here.
- 1 Claude Fable 5.1 ↑1 97.8%
- 2 Claude Opus 5 ↑2 95.6%
- 3 Claude Opus 4.6 ↑3 93.7%
- 4 Claude Sonnet 5 ↑4 90.6%
- 5
Gemini 3.6 Flash ↓4 82.2%
- 6 Claude Haiku 4.5 ↑3 78.1%
- 7
Gemini 3.5 Flash-Lite ↓2 76.9%
- 8
Gemini 3.7 Flash ↓5 75%
- 9
Gemini 3.1 Flash-Lite ↓2 70.6%
Drawing QA
9 models we track have a score here.
- 1
Gemini 3.6 Flash 85.7%
- 2
Gemini 3.5 Flash-Lite ↑3 71.4%
- 3
Gemini 3.7 Flash 71.4%
- 4
Gemini 3.1 Flash-Lite ↑3 57.1%
- 5 Claude Haiku 4.5 ↑4 28.6%
- 6 Claude Opus 4.6 28.6%
- 7 Claude Sonnet 5 ↑1 28.6%
- 8 Claude Opus 5 ↓4 28.6%
- 9 Claude Fable 5.1 ↓7 28.6%
Text search
9 models we track have a score here.
- 1
Gemini 3.6 Flash 100%
- 2
Gemini 3.7 Flash ↑1 86.1%
- 3 Claude Opus 5 ↑1 77.5%
- 4 Claude Fable 5.1 ↓2 75.6%
- 5 Claude Opus 4.6 ↑1 66.1%
- 6
Gemini 3.1 Flash-Lite ↑1 58.7%
- 7
Gemini 3.5 Flash-Lite ↓2 52.9%
- 8 Claude Sonnet 5 23.8%
- 9 Claude Haiku 4.5 20.8%
The best score, 36.8%, costs $1.00 for the full run
Runs on the cost frontier score higher than any run that's cheaper. The costs are the leaderboard's own estimates, so compare them only within this benchmark.
Source: Official Construction's Last Exam v2 leaderboard
| Model | Effort | Harness | Score | Cost of the full run | Output tokens |
|---|---|---|---|---|---|
| 36.8% | $1.00 | ||||
| Claude Fable 5.1 | 35.3% | $13 | |||
| 31.6% | $1.10 | ||||
| Claude Opus 5 | 31.5% | $7.50 | |||
| 22.4% | $0.60 | ||||
| Claude Opus 4.6 | 21.6% | $6.50 | |||
| 19.1% | $0.40 | ||||
| Claude Sonnet 5 | 14.3% | $3.00 | |||
| Claude Haiku 4.5 | 12.4% | $1.30 |
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: Official Construction's Last Exam v2 leaderboard
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: Official Construction's Last Exam v2 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.
Versions
We switch the top row to each new version when it comes out. Open it for one row per version. An old version stays in play while people still test it, so whoever first takes it past 85% gets credit for closing it out.
Source: Official leaderboards
More 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
9 of 10 checks pass, 1 warning. Look first at the Task access check. We don’t know whether the tasks are public. Every benchmark
Catalog record 1 warning 1 pass
- Warning Task access We don’t know whether the tasks are public.
- Pass Confidence Checked against a primary source.
Scores 4 pass 1 note
- Pass Independent runs Scores from the official leaderboard (9 entries).
- Pass Models scored 9 models we track.
- Pass Newest score The newest is from September 2026, for Claude Fable 5.1.
- Note Frontier models 1 of the top 10 has a score, which is fine for a retired test. The strongest tested is Claude Fable 5.1 (#8).
- Pass Headroom The best is 36.8%, under 85%, so it still separates models.
Leaderboard import 3 pass
- Pass Importer We read the board on cle.togal.ai: 9 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.