HF Model & Benchmark Matrix

24,078 variants · 14,984 scores · 120 benchmarks

Home/Models/inclusionAI/AReaL-boba-RL-7B

AReaL-boba-RL-7B

inclusionAI/AReaL-boba-RL-7B

kind: original
quant: bf16 (16-bit)
family: misc
modality: —
root model: inclusionAI/AReaL-boba-RL-7B
provider: inclusionAI
license: apache-2.0
language: —
context: —
library: —
vRAM (GB): —
size on disk: —
downloads: 14
likes: 21
created: —
last modified: 2025-03-30T02:09:50+00:00 (2025)
huggingface: https://huggingface.co/inclusionAI/AReaL-boba-RL-7B
tags: pytorchqwen2license:apache-2.0region:us

Benchmark scores (3)

benchmark	category	score	context	conf	evidence
AIME 2024	math	55.0		low	`\| R1-Distill-Qwen-7B \| 55.0 \| 39.7 \| 47.1 \|`
GPQA Diamond	reasoning	47.1		low	`\| R1-Distill-Qwen-7B \| 55.0 \| 39.7 \| 47.1 \|`
AIME 2025	math	39.7		low	`\| R1-Distill-Qwen-7B \| 55.0 \| 39.7 \| 47.1 \|`

Discussions (0)

none scraped.

Hugging Face model & benchmark data scraped & matrix-ified. 24,078 variants · 14,984 scores · 120 benchmarks.