BlogLLM Benchmark Scores as Published, Side by Side
DECK-Arena: Results as Published
Every result the catalog holds for DECK-Arena: 5 models from 5 developers, read from 1 page. Each number is as printed by the company named beside it; nothing is ranked or rescored. Models are listed by developer, newest first.
Area Knowledge WorkMaintainer Moonshot AIIntroduced 2026Data version 2026103001, as of 2026-10-30
DECK-Arena is an in-house presentation-generation test of Moonshot AI on real-world queries. Models build slides through python-pptx, pptxjs and Kimi's in-house DSL in a harness with search and image generation. An automated grader calibrated on more than 10,000 human judgments compares the decks, and the result is an Elo score.
DECK-Arena (Internal, Elo)
| Model | Value | Printed by | Setup as printed |
|---|---|---|---|
| GPT-6 AstraOpenAI, released 2026-09-03 | 1423 | Moonshot AI, Introducing Kimi K3.1 Prochecked 2026-10-24 | Effort: max; Fallback: with fallback |
| Claude Opus 5.5Anthropic, released 2026-09-22 | 1253 | Moonshot AI, Introducing Kimi K3.1 Prochecked 2026-10-24 | Effort: max; Fallback: with fallback |
| DeepSeek-V4.1-Flash-1017DeepSeek, released 2026-10-17 | 1231 | Moonshot AI, Introducing Kimi K3.1 Prochecked 2026-10-24 | Effort: max |
| Kimi K3.1 ProMoonshot AI, released 2026-10-23 | 1456 | Moonshot AI, Introducing Kimi K3.1 Prochecked 2026-10-24 | Effort: max |
| GLM-5.3Z.ai, released 2026-08-18 | 1119 | Moonshot AI, Introducing Kimi K3.1 Prochecked 2026-10-24 | Effort: max |
Every number here is read from the same catalog file as the benchmark table, data version 2026103001, and is the number the table shows for that model and test. Where one page printed a model under several setups, each value is listed. The catalog is public in armanobosyan/sugra-llm-benchmarks; a wrong number can be reported from the table, with Report an error under the value, or as an issue in that repository.