HF Model & Benchmark Matrix

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

AReaL-SEA-235B-A22B

inclusionAI/AReaL-SEA-235B-A22B

kind
original
quant
bf16 (16-bit)
family
misc
modality
text-generation
root model
Qwen/Qwen3-235B-A22B-Thinking-2507
provider
inclusionAI
license
apache-2.0
language
en
context
32,768
library
—
vRAM (GB)
—
size on disk
—
downloads
31
likes
4
created
—
last modified
2026-03-02T03:19:01+00:00 (2026)
huggingface
https://huggingface.co/inclusionAI/AReaL-SEA-235B-A22B
tags
safetensorsqwen3_moetool-useagentmulti-turnreinforcement-learningGRPOtau2-benchAReaLtext-generationconversationalenarxiv:2601.22607arxiv:2505.24298base_model:Qwen/Qwen3-235B-A22B-Thinking-2507base_model:finetune:Qwen/Qwen3-235B-A22B-Thinking-2507license:apache-2.0region:us

Benchmark scores (0)

no scores extracted for this variant.

Discussions (0)

none scraped.

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