PPTGen-Bench
Agents create slide decks from text requests. Tencent renders the decks to PDF with LibreOffice. A judging agent assesses appearance and applies penalties for serious faults.
Tencent compares seven models in the Hy4 appendix. The judge runs in Claude Code. The appendix gives no task count.
- Made by
- Tencent
- Released
- November 2026
- Kind
- Documents and spreadsheets
- Level
- School
- Scored
- Graded by a model
- Answers
- Agent task
- Tasks
- Kept private
- Measures
- Capability
- Interaction
- Single turn
- Refresh
- One fixed set
- Run by
- A host
- Strongest model tested
- Claude Opus 5.5 #5 on the capability index
- Last model added
- November 2026
- Scores refreshed
- November 21st, 2026
Claude Opus 5.5 leads with 67.7
Best score per model 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.
- 1 Claude Opus 5.5 67.7
- 2 GPT-6.1 Sol 66.5
- 3 Kimi K3.1 Pro 64.5
- 4
DeepSeek V4.1 Flash 1017 62.5
- 5
Tencent Hy4 60.9
- 6 GLM-5.3 53.9
- 7
Tencent Hy4 preview 49.0
Source: The PPTGen-Bench paper
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Claude Opus 5.5 | 67.7 | Sep 2026 | Official leaderboard | |
| 2 | GPT-6.1 Sol | 66.5 | Sep 2026 | Official leaderboard | |
| 3 | Kimi K3.1 Pro | 64.5 | Oct 2026 | Official leaderboard | |
| 4 | | 62.5 | Oct 2026 | Official leaderboard | |
| 5 | | 60.9 | Nov 2026 | Official leaderboard | |
| 6 | GLM-5.3 | 53.9 | Aug 2026 | Official leaderboard | |
| 7 | | 49.0 | 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.
Source: The PPTGen-Bench paper
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: Official PPTGen-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 9 checks pass. Every benchmark
Catalog record 2 pass
- Pass Task access The tasks are private.
- Pass Confidence Checked against a primary source.
Scores 3 pass 2 notes
- Pass Independent runs Scores from the benchmark’s paper (7 entries).
- Pass Models scored 7 models we track.
- Pass Newest score The newest is from November 2026, for Tencent Hy4.
- Note Frontier models Only 2 of the top 10 have a score. The strongest tested is Claude Opus 5.5 (#5).
- Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
- Pass Importer We read the board on huggingface.co: 7 rows for models we track 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.