DECK-Arena (Internal, Elo) (DECK-Arena)
We show this table for reference; we do not rank on it.
Moonshot AI's internal arena for presentation generation on real-world queries, reported as Elo.
Benchmark score on DECK-Arena — October 29, 2026
We compile the DECK-Arena rows from provider self-reports. Kimi K3.1 Pro leads the table at 1456. We do not use these results to rank models overall.
1 modelAgenticCurrentDisplay onlyUpdated October 29, 2026
Benchmark score table (1 model)
| Rank | Model / configuration | Score | Parameters (B) | Open / closed |
|---|---|---|---|---|
| 1 | Kimi K3.1 ProMoonshot AI | 1456 | Not reported | Pending |
About DECK-Arena
Year
2026
Tasks
Real-world presentation requests
Format
Elo
Difficulty
Professional presentation creation
Models run across python-pptx, pptxjs, and Kimi's in-house DSL in a harness with integrated search and image generation; an automated grader calibrated on more than 10,000 human judgments ranks outputs. It is distinct from the earlier DECK-Bench score. BenchLM stores the provider-published internal benchmark value as display-only launch evidence and does not treat it as an independently reproducible score.
Freshness and provenance
Version
DECK-Arena 2026
Refresh cadence
Quarterly
Staleness state
Current
Question availability
Public benchmark set
BenchLM uses freshness metadata to decide whether a benchmark should still be treated as a strong differentiator, a benchmark to watch, or a display-only reference. For the full scoring policy, see the BenchLM methodology page.
Questions
What does DECK-Arena measure?
Moonshot AI's internal arena for presentation generation on real-world queries, reported as Elo.
Which model scores highest on DECK-Arena?
Kimi K3.1 Pro by Moonshot AI currently leads with a score of 1456 on DECK-Arena.
How many models are evaluated on DECK-Arena?
1 AI models have published results on DECK-Arena in the BenchLM catalog.
Know when it’s worth switching models
The model to choose, the cheaper alternative, and the release we would wait on.
Read a sample issueJoin 6,100+ subscribers.
One email each week. Unsubscribe anytime.