TreasuryQA Bench
Agents search scanned Treasury volumes and read tables to find or calculate a number. A script checks whether the answer falls within the accepted range.
Veris ranks 12 models on 70 questions. The authors wrote 55 new questions and adapted 15 from OfficeQA Pro v2. They published three worked examples.
- Released
- October 2026
- Kind
- Documents and spreadsheets
- Level
- School
- Scored
- Checked automatically
- Answers
- Agent task
- Tasks
- Public, plus a private test set
- Measures
- Capability
- Subject
- Economics and business
- Language
- English
- Interaction
- Agentic
- Environment
- APIs and tools
- Items from
- Written by experts, Another benchmark, Real work and use
- Refresh
- One fixed set
- Run by
- A host
- Based on
- OfficeQA Pro V2
- In views
- Agents, Law and finance
- Strongest model tested
-
Gemini 4 Carbon #3 on the capability index
- Last model added
- November 2026
- Scores refreshed
- November 20th, 2026
Gemini 4 Hydrogen leads with 82.4%
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. Every run is in the next chart.
- 1
Gemini 4 Hydrogen 82.4%
- 2
Gemini 4 Argon 81.9%
- 3
Gemini 4 Carbon 81%
- 4 Claude Opus 5.5 65.2%
- 5
Gemini 3.8 Flash 52.4%
- 6 GPT-6.1 Sol 52.4%
- 7 Claude Sonnet 5.5 42.9%
- 8
DeepSeek V4.1 Flash 41.9%
- 9 GLM-5.3-Flash 40%
- 10 Kimi K3 35.2%
- 11 Grok 4.7 22.9%
- 12 GPT-5.6 Terra 16.7%
Source: Official TreasuryQA Bench leaderboard
| # | Model | Score ± | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | | 82.4% 74.3 to 90 | Gemini CLI | Nov 2026 | Official leaderboard |
| 2 | | 81.9% 73.8 to 89.5 | Gemini CLI | Sep 2026 | Official leaderboard |
| 3 | | 81% 72.4 to 88.6 | Gemini CLI | Oct 2026 | Official leaderboard |
| 4 | Claude Opus 5.5 | 65.2% 55.7 to 74.3 | Claude Code | Sep 2026 | Official leaderboard |
| 5 | | 52.4% ±10 | Gemini CLI | Sep 2026 | Official leaderboard |
| 6 | GPT-6.1 Sol | 52.4% ±10 | Codex | Sep 2026 | Official leaderboard |
| 7 | Claude Sonnet 5.5 | 42.9% 33.3 to 52.9 | Claude Code | Sep 2026 | Official leaderboard |
| 8 | | 41.9% ±9.5 | Pi | Sep 2026 | Official leaderboard |
| 9 | GLM-5.3-Flash | 40% 31 to 50 | Pi | Aug 2026 | Official leaderboard |
| 10 | Kimi K3 | 35.2% ±9.5 | Pi | Jul 2026 | Official leaderboard |
| 11 | Grok 4.7 | 22.9% 16.2 to 30 | Grok CLI | Sep 2026 | Official leaderboard |
| 12 | GPT-5.6 Terra | 16.7% 10 to 23.8 | Codex | Jul 2026 | Official leaderboard |
Rankings by part
We read 2 parts from the benchmark’s own leaderboard: Clear and Very blurry. Each ranks models on one part of the test. Gemini 4 Argon leads Clear and Gemini 4 Hydrogen leads Very blurry. Arrows show how far a model moved from its overall rank among the models we track.
Clear
12 models we track have a score here.
- 1
Gemini 4 Argon ↑1 92%
- 2
Gemini 4 Hydrogen ↓1 87%
- 3
Gemini 4 Carbon 82%
- 4 GPT-6.1 Sol ↑2 74%
- 5 Claude Opus 5.5 ↓1 63%
- 6
Gemini 3.8 Flash ↓1 58%
- 7 Claude Sonnet 5.5 56%
- 8 GLM-5.3-Flash ↑1 55%
- 9 Kimi K3 ↑1 50%
- 10
DeepSeek V4.1 Flash ↓2 49%
Very blurry
12 models we track have a score here.
- 1
Gemini 4 Hydrogen 85%
- 2
Gemini 4 Carbon ↑1 80%
- 3
Gemini 4 Argon ↓1 70%
- 4 Claude Opus 5.5 60%
- 5
Gemini 3.8 Flash 37%
- 6 GPT-6.1 Sol 25%
- 7
DeepSeek V4.1 Flash ↑1 22%
- 8 GLM-5.3-Flash ↑1 18%
- 9 Kimi K3 ↑1 12%
- 10 Claude Sonnet 5.5 ↓3 12%
The best score, 82.4%, costs $6.93 a task
Runs on the cost frontier score higher than any run that's cheaper. Gemini 4 Argon comes within 0.5 points of the best for $3.07 a task, about half the cost. The costs are the leaderboard's own estimates, so compare them only within this benchmark.
Source: Official TreasuryQA Bench leaderboard
| Model | Effort | Harness | Score | Cost per task | Output tokens |
|---|---|---|---|---|---|
| Gemini CLI | 82.4% | $6.93 | |||
| Gemini CLI | 81.9% | $3.07 | |||
| Gemini CLI | 81% | $4.73 | |||
| Claude Opus 5.5 | Claude Code | 65.2% | $1.56 | ||
| Gemini CLI | 52.4% | $1.75 | |||
| GPT-6.1 Sol | Codex | 52.4% | $0.60 | ||
| Claude Sonnet 5.5 | Claude Code | 42.9% | $1.21 | ||
| Pi | 41.9% | $0.23 | |||
| GLM-5.3-Flash | Pi | 40% | $0.29 | ||
| Kimi K3 | Pi | 35.2% | $2.81 | ||
| Grok 4.7 | Grok CLI | 22.9% | $6.00 | ||
| GPT-5.6 Terra | Codex | 16.7% | $1.03 |
2 models have held number one on the official leaderboard since its release in October 2026
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: Official TreasuryQA Bench 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 TreasuryQA Bench 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
- 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 Public tasks, plus a private test set.
- Pass Confidence Checked against a primary source.
Scores 5 pass
- Pass Independent runs Scores from the official leaderboard (12 entries).
- Pass Models scored 12 models we track.
- Pass Newest score The newest is from November 2026, for Gemini 4 Hydrogen.
- Pass Frontier models 5 of the top 10 have a score, led by Gemini 4 Carbon (#3).
- Pass Headroom The best is 82.4%, under 85%, so it still separates models.
Leaderboard import 3 pass
- Pass Importer We read the board on veris.ai: 12 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.