FINAL-Bench/Darwin-180B-RSI
image-text-to-text model by FINAL-Bench
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.
[](https://www.superclueai.com/homepage) This model line was evaluated by SuperCLUE, China's most widely cited LLM benchmark, on its private November 2026 test set. Darwin-180B-RSI-R3 scored 73.68 in mathematical and scientific reasoning: #1 among open-weight models and #2 overall among 19 models, right behind OpenAI's GPT-6.1-Sol (76.32) and ahead of Google Gemini-4-Argon (71.05), DeepSeek-V4.1-Flash (71.05), xAI Grok-4.7 (68.42) and Qwen3.8-Max (68.42). On the overall intelligence index it placed 9th of 19 and 5th among open-weight models. It is the only Korean model on the board. Darwin-180B-RSI inherited its expert layers from Qwen3.8-Flash-Next and rebuilt only the attention and shared-expert layers through recursive self-improvement. On the same board the parent, Qwen3.8-Flash, placed 15th overall (39.81) with 57.89 in math and science reasoning; Darwin placed 9th (43.08) with 73.68. Overall intelligence index, November 2026 (screenshot) Source: SuperCLUE general leaderboard, November 2026 (screenshots taken November 5, 2026). Scores are SuperCLUE's, not VIDRAFT's. reasoning · MoE 512…
Read the full model card ↗ · Preview checked 2026-11-12T07:23:47.794Z
Inside the original model card — Document outline
- 🏆 SuperCLUE November 2026: #1 open-weight model in math and science reasoning
- Darwin-180B-RSI
- 180B Mixture-of-Experts · vision-language · #1 on ten Hugging Face official leaderboards: nine by th
- 🏆 Head-to-head with Chinese frontier models
- 🧬 The Darwin Family
- 🧬 Darwin — evolve the parent, keep what works
- Lineage
- 📄 Darwin Platform & Research
- 🔁 RSI — a model that improves from its own work
- Next round: Darwin-180B-RSI-R3
- Model-level RSI vs. harness-level RSI
- 🏛️ ZTC — it knows before it answers
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: other. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
Model overview
FINAL-Bench/Darwin-180B-RSI is a image-text-to-text model repository published by FINAL-Bench 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)
- 679
- Cumulative likes
- 111
- Hugging Face trending score
- 48
- Reported safetensors parameters
- 179,999,981,459
- Architecture
- Qwen4ExpForConditionalGeneration
- License
- other
- Access
- Not gated by Hugging Face
- Created
- 2026-09-28T03:15:04.000Z
- Last modified
- 2026-10-05T02:05:28.000Z
Compatibility and lineage
Reported languages: en, ko, zh, ja, multilingual
Base-model lineage was not included.
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 2026-10-05T06:38:48.905Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.