BenchmarksDECK-Arena (Internal, Elo-score)
DECK-Arena (Internal, Elo-score)
Generating useful presentations for real-world requests, scored by internal Elo.
Test definition
- Author / evaluator
- Reported by Moonshot AI
- Version / family
- DECK-Arena (Internal, Elo-score) / DECK-Arena
- Evidence available
- 5 results in 1 comparison groups
How the test is scored
Internal presentation-generation Elo. Models use python-pptx, pptxjs and Kimi DSL with search and image generation; automated grader calibrated on 10,000+ human judgments.
Comparison notes
Publisher-reported results, read 24 October 2026. Compare reported values only within the same source row; tool settings, subsets, versions, judges and metrics must not be combined.
A different task split, tool policy, judge or reasoning effort can change the result. Choose one comparison group below.
Results by evaluator
Select a publication and metric to compare the recorded field.
selfKimi K3.1 Pro: complete release evaluation · DECK-Arena (Internal, Elo-score)
- 1,456
- 1,423
- 1,253
- 1,231
- 1,119
Bars start at zero. 5 reported results in this comparison group; ties share a rank. Source ↗
All observations
Every numeric result, with its source and reported run conditions.
5 results
| Model | Result (Elo) | Source | Run |
|---|---|---|---|
| Kimi K3.1 Pro | 1,456 | self | DetailsInternal presentation-generation Elo. Models use python-pptx, pptxjs and Kimi DSL with search and image generation; automated grader calibrated on 10,000+ human judgments. Read 24 October 2026. All 47 source rows and six comparison columns are retained, with text-only HLE and both ZeroBench metrics split explicitly. Kimi uses max reasoning effort, temperature 1.0 and top-p 0.95 unless a row states otherwise; proprietary comparison columns are labelled max with fallback. Comparison figures include quoted external results and mixed harnesses. Missing cells remain null and do not enter ranks. Lower hallucination rates rank first; every other rank compares larger values within the same row. Terminal-Bench Science’s September DeepSeek score is attributed separately according to footnote 2. These publication claims do not populate independent boards. Highspeed has no independently identified results and inherits none of these scores.
|
| GPT-6 Astra | 1,423 | self | DetailsInternal presentation-generation Elo. Models use python-pptx, pptxjs and Kimi DSL with search and image generation; automated grader calibrated on 10,000+ human judgments. Read 24 October 2026. All 47 source rows and six comparison columns are retained, with text-only HLE and both ZeroBench metrics split explicitly. Kimi uses max reasoning effort, temperature 1.0 and top-p 0.95 unless a row states otherwise; proprietary comparison columns are labelled max with fallback. Comparison figures include quoted external results and mixed harnesses. Missing cells remain null and do not enter ranks. Lower hallucination rates rank first; every other rank compares larger values within the same row. Terminal-Bench Science’s September DeepSeek score is attributed separately according to footnote 2. These publication claims do not populate independent boards. Highspeed has no independently identified results and inherits none of these scores.
|
| Claude Opus 5.5 | 1,253 | self | DetailsInternal presentation-generation Elo. Models use python-pptx, pptxjs and Kimi DSL with search and image generation; automated grader calibrated on 10,000+ human judgments. Read 24 October 2026. All 47 source rows and six comparison columns are retained, with text-only HLE and both ZeroBench metrics split explicitly. Kimi uses max reasoning effort, temperature 1.0 and top-p 0.95 unless a row states otherwise; proprietary comparison columns are labelled max with fallback. Comparison figures include quoted external results and mixed harnesses. Missing cells remain null and do not enter ranks. Lower hallucination rates rank first; every other rank compares larger values within the same row. Terminal-Bench Science’s September DeepSeek score is attributed separately according to footnote 2. These publication claims do not populate independent boards. Highspeed has no independently identified results and inherits none of these scores.
|
| DeepSeek V4.1 Flash 1017 | 1,231 | self | DetailsInternal presentation-generation Elo. Models use python-pptx, pptxjs and Kimi DSL with search and image generation; automated grader calibrated on 10,000+ human judgments. Read 24 October 2026. All 47 source rows and six comparison columns are retained, with text-only HLE and both ZeroBench metrics split explicitly. Kimi uses max reasoning effort, temperature 1.0 and top-p 0.95 unless a row states otherwise; proprietary comparison columns are labelled max with fallback. Comparison figures include quoted external results and mixed harnesses. Missing cells remain null and do not enter ranks. Lower hallucination rates rank first; every other rank compares larger values within the same row. Terminal-Bench Science’s September DeepSeek score is attributed separately according to footnote 2. These publication claims do not populate independent boards. Highspeed has no independently identified results and inherits none of these scores.
|
| GLM 5.3 | 1,119 | self | DetailsInternal presentation-generation Elo. Models use python-pptx, pptxjs and Kimi DSL with search and image generation; automated grader calibrated on 10,000+ human judgments. Read 24 October 2026. All 47 source rows and six comparison columns are retained, with text-only HLE and both ZeroBench metrics split explicitly. Kimi uses max reasoning effort, temperature 1.0 and top-p 0.95 unless a row states otherwise; proprietary comparison columns are labelled max with fallback. Comparison figures include quoted external results and mixed harnesses. Missing cells remain null and do not enter ranks. Lower hallucination rates rank first; every other rank compares larger values within the same row. Terminal-Bench Science’s September DeepSeek score is attributed separately according to footnote 2. These publication claims do not populate independent boards. Highspeed has no independently identified results and inherits none of these scores.
|
Reproduction
Public execution instructions have not been verified in this catalogue. This status does not claim that the benchmark is closed or impossible to run.
Execution documentation ↗