Rubicon-Preview

Home/Models/inclusionAI/Rubicon-Preview

inclusionAI/Rubicon-Preview

kind: original
quant: bf16 (16-bit)
family: misc
modality: text-generation
root model: inclusionAI/Rubicon-Preview
provider: inclusionAI
license: apache-2.0
language: —
context: —
library: transformers
vRAM (GB): —
size on disk: —
downloads: 22
likes: 25
created: —
last modified: 2025-08-19T09:45:23+00:00 (2025)
huggingface: https://huggingface.co/inclusionAI/Rubicon-Preview
tags: transformerssafetensorsqwen3_moetext-generationconversationalarxiv:2508.12790license:apache-2.0endpoints_compatibledeploy:azureregion:us

benchmark	category	score	conf	evidence
MATH-500	math	94.75	low	`\| Qwen3-30B-A3B \| 77.50 \| 70.00 \| 94.75 \| 63.00 \| 63.77 \| 73.80 \|`
MMLU	knowledge	79.53	low	`\| Qwen3--30B-A3B \| 79.53 \| 68.75 \| 77.55 \| 77.72 \| 79.52 \| 73.64 \| 78.16 \|`
AIME 2024	math	77.5	low	`\| Qwen3-30B-A3B \| 77.50 \| 70.00 \| 94.75 \| 63.00 \| 63.77 \| 73.80 \|`
AIME 2025	math	70.0	low	`\| Qwen3-30B-A3B \| 77.50 \| 70.00 \| 94.75 \| 63.00 \| 63.77 \| 73.80 \|`
GPQA	reasoning	63.0	low	`\| Qwen3-30B-A3B \| 77.50 \| 70.00 \| 94.75 \| 63.00 \| 63.77 \| 73.80 \|`

none scraped.