BAAI/AREX-2
image-text-to-text model by BAAI
Older snapshot: check the original source for current information.
From the publisher
Model card & documentation
Source previewRead the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.
AREX-2: Advancing Self-Improving Agents through Long-Horizon Reflective Tasks AREX-2 is a 27B-parameter long-horizon agent model from the Beijing Academy of Artificial Intelligence (BAAI). It learns to improve a solution over multiple test-time rounds: propose, measure, reflect, and revise. AREX-2 is trained on machine-learning and algorithmic-programming tasks with verifiable feedback, together with the existing AREX deep-research data. The learned self-improvement behavior transfers to deep research without adding new search trajectories. solution refinement. decide what to change next. also improves the model's deep-research performance. grows. AREX-2 is evaluated on algorithmic programming, machine-learning engineering, deep research, and general agentic reasoning. Results follow the protocols reported in the AREX-2 paper. Model Params Frontier-CS MLE-Lite Closed-weight models GPT-5.6 Sol-76.472.7 Claude Opus 4.8-74.563.6 GPT-5.5-72.168.2 Gemini-3.1-Pro-68.9- Qwen3.7-Max-61.9- Open-weight models Kimi-K32.8T-72.7 Naive-N0.5-Flash309B-73.7 DeepSeek-V4-Pro1.6T44.754.5 DeepSeek-V4-Flash284B39.151.5 Kimi-K2.7-Code1T54.7- GLM-5.3-Flash320B50.4- Kimi-K2.61T46.966.7 Frontis-MA1-35B35B-71.2 BigBang-V135B-59.1 Qwen3.6-35B-A3B35B23.439.4 AREX-227B70.781.8 Frontier-CS is the 188-task Agent Track. MLE-Lite reports Any Medal averaged over three seeds. Model Params BrowseComp…
Read the full model card ↗ · Preview checked 2026-11-15T00:16:18.162Z
Inside the original model card — Document outline
- Introduction
- Key features
- Evaluation
- Coding and machine-learning engineering
- General agentic reasoning and deep research
- Inference
- Intended use
- License
- Citation
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Links from the model card
References supplied by the publisher, not independently verified endorsements. Check the destination before downloading files or entering credentials.
Documentation belongs to its respective authors. Reported project/model license: apache-2.0. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
Model overview
BAAI/AREX-2 is a image-text-to-text model repository published by BAAI on Hugging Face. The source reports the transformers library.
This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.
Model facts
- Task
- image-text-to-text
- Library
- transformers
- Recent downloads (30 days)
- 3,028
- Cumulative likes
- 208
- Hugging Face trending score
- 53
- Reported safetensors parameters
- 27,356,728,560
- Architecture
- Qwen3_5ForConditionalGeneration
- License
- apache-2.0
- Access
- Not gated by Hugging Face
- Created
- 2026-09-29T17:56:21.000Z
- Last modified
- 2026-10-01T07:13:17.000Z
Compatibility and lineage
Language coverage was not reported.
Reported base models: Qwen/Qwen3.8-27B
Parameter count is not a RAM/VRAM requirement. Check precision, quantization, context length and runtime compatibility in the model card; no hardware or API-cost claim is inferred here.
Use and evaluate
Check license terms and access requirements first. Review the model card’s documented loading instructions, evaluations and safety limitations. Benchmark scores are not imported by this directory, and popularity is not an accuracy ranking.
No model weights are downloaded or executed by AltAPIs. Never enable remote model code without reviewing it.
Source and freshness
Source: Hugging Face Hub. Metadata observed 2026-11-13T06:55:57.230Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.