--- library_name: transformers license: mit license_link: https://huggingface.co/ornith-ai/Ornith-1.5-397B/blob/main/LICENSE pipeline_tag: text-generation --- # Ornith-1.5-397B Chirp Chirp! 🐦 We are introducing Ornith-1.5, a major step toward building foundation models through end-to-end self-improvement. Ornith-1.5 extends Ornith-1.0 by expanding the self-improvement loop from scaffold and rollout optimization to jointly optimizing task generation, scaffold construction, and solution rollouts. Rather than relying on a fixed set of human-curated tasks and manually designed harnesses, Ornith-1.5 continuously generates new training tasks, discovers effective strategies for solving them, and improves the policy through reinforcement learning. For more details on the task, harness, and rollout reward design, please refer to our [blog](https://ornith.ai/ornith_1_5.html). Ornith 1.5 397B Benchmark Results ## Ornith 1.5 397B This model card documents **Ornith-1.5-397B**, the flagship member of the Ornith-1.5 family — a 397B mixture-of-experts model. It scores 86.1 on Terminal-Bench 2.1 and 56.0 on DeepSWE, performing on par with Claude Opus 4.8 (85.0 and 59.0) while outperforming leading open-source models of similar scale, including GLM-5.2 and DeepSeek-V4-Flash-0731. ### Benchmarks
Ornith-1.5-397B DeepSeek-V4-Flash-0731 (284B) GLM-5.2 (753B) Claude Opus 4.8 Kimi K3 (2.8T) Ornith-1.0-397B
Coding
Terminal-Bench 2.1 (Terminus-2) 86.1 82.7 81 85 88.3 77.5
Terminal-Bench 2.1 (Claude Code) 85.2 81.8 82.7 78.9 - 78.2
SWE-bench Verified 86 81.6 83 85.8 86.2 82.4
SWE-bench Pro 65.1 64.4 62.1 68 - 62.2
SWE-bench Multilingual 79.6 77.9 78.4 75.7 - 78.9
DeepSWE 56 54.4 46.2 59 67.5 8
Frontier-Bench v0.1 13.5 6.1 5.1 21.1 23 2.7
NL2Repo 59.5 54.2 48.9 69.7 - 48.2
SWE Atlas - QnA 55.6 51.6 50 59.7 59.7 41.2
Reasoning
HLE (no tools) 44.6 35 40.5 49.8 43.5 30.2
HLE (with tools) 56.1 50.8 54.7 57.9 56 47.5
GPQA Diamond 92.8 91.4 91.2 93.6 93.5 88.1
Agentic
MCP-Atlas 80 74.6 77.8 82.2 82.3 76.4
Toolathlon-Verified 71.2 70.3 48.2 76.2 73.2 43.2
WideSearch 80.8 77.3 79 72.9 - 75.2
BrowseComp 86.6 84.8 85.6 84.3 91.2 79.7
ClawEval 81.4 77.6 78.8 80.2 - 77.1

* All results reported for Ornith-1.5 are averaged over five independent runs.
* Terminal-Bench 2.1 (Terminus-2): We evaluate Terminal-Bench 2.1 using the Harbor/Terminus-2 framework with parser=json, temperature=1.0, top_p=1.0, and a 128K context window. Each run uses a 4-hour timeout with 32 CPU cores and 48GB RAM, and results are averaged over 5 runs. We adjust the Qwen chat template to ensure consistency between training and inference (https://huggingface.co/ornith-ai/Ornith-1.5-397B/blob/main/chat_template.jinja), and modify Harbor to align with vLLM's reasoning_content key.
* Terminal-Bench 2.1 (Claude Code): We evaluate Terminal-Bench 2.1 using Claude Code 2.1.126 with parser=json, temperature=1.0, top_p=1.0, max_new_tokens=131072. Results are averaged over 5 runs. Again, Qwen chat template needs to be modified.
* SWE-Bench Verified, Pro and Multilingual: using OpenHands harness with temp=1.0, top_p=0.95, 256k context window. Anti-hacking safeguards are applied throughout evaluation: Git history is removed from the local repository image to prevent access to prior solutions or commits; network access is disabled, preventing the model from retrieving external information or resources.
* DeepSWE: Evaluated using the Claude Code harness with temperature=1.0, top_p=0.95, and a 256K context window.
* SWE Atlas QnA: using mini SWE agent harness with temp=1.0, top_p=0.95, 128K context window. Results are averaged over 5 runs.
* NL2Repo: with temperature=1.0, top_p=1.0, 400K context, 48K output. Access to specified GitHub repositories and pip packages is blocked to prevent reward hacking.
* HLE: Evaluated using Claude 4.6 Opus as the judge model.
* MCP-Atlas: All models were evaluated in thinking mode on the 500-task public subset, with a 10-minute timeout per task. We use Claude 4.8 Opus as the judge model.
* Toolathlon-Verified: We use the official evaluation service with the maximum token limit set to 128K.
* ClawEval: An agentic code benchmark over real-user task distributions; temp=0.6 and 256K context.

## Quickstart
📝 NOTE

Ornith-1.5-397B is a reasoning model: by default the assistant turn opens with a <think> … </think> block before the final answer. The serving recipes below enable a reasoning parser so the chain-of-thought is returned in a separate reasoning_content field, and a tool-call parser so the model's <tool_call> blocks are surfaced as OpenAI-style tool_calls.

Serving Ornith-1.5-397B requires recent runtimes:

Recommended sampling parameters:

### Serving Ornith-1.5-397B Ornith-1.5-397B is a ~397B mixture-of-experts model (≈800 GB in bf16), so multi-GPU serving is required. The recipes below use 8-way tensor parallelism on a single node (e.g., 8× H200 141GB); adjust `--tensor-parallel-size` / `--tp` to match your hardware, or use FP8/INT4 quantized builds for smaller deployments. #### vLLM ```bash vllm serve ornith-ai/Ornith-1.5-397B \ --served-model-name Ornith-1.5-397B \ --host 0.0.0.0 --port 8000 \ --tensor-parallel-size 8 \ --max-model-len 262144 \ --gpu-memory-utilization 0.90 \ --enable-prefix-caching \ --enable-auto-tool-choice --tool-call-parser qwen3_xml \ --reasoning-parser qwen3 \ --trust-remote-code ``` #### SGLang ```bash python -m sglang.launch_server \ --model-path ornith-ai/Ornith-1.5-397B \ --served-model-name Ornith-1.5-397B \ --host 0.0.0.0 --port 8000 \ --tp 8 \ --context-length 262144 \ --mem-fraction-static 0.85 \ --tool-call-parser qwen3_coder \ --reasoning-parser qwen3 ``` #### For Long-Context Ornith-1.5-397B handles context windows of up to 262,144 tokens. When a task's combined input and output must go beyond this limit, we suggest extending the effective window with RoPE scaling — YaRN is the technique we validate against, and it is already built into both vLLM and SGLang. With a scaling factor of 4.0, the usable window grows to roughly 1M tokens. You can turn YaRN on in either of two ways: - **Edit the checkpoint's `config.json`.** Add a `rope_scaling` block to the model configuration: ```json { "rope_scaling": { "rope_type": "yarn", "factor": 4.0, "original_max_position_embeddings": 262144 } } ``` - **Override at launch time.** Leave the checkpoint untouched and extend the serve commands above with the equivalent flags. vLLM: ```bash VLLM_ALLOW_LONG_MAX_MODEL_LEN=1 vllm serve ornith-ai/Ornith-1.5-397B ... --hf-overrides '{"rope_scaling": {"rope_type": "yarn", "factor": 4.0, "original_max_position_embeddings": 262144}}' --max-model-len 1000000 ``` SGLang: ```bash SGLANG_ALLOW_OVERWRITE_LONGER_CONTEXT_LEN=1 python -m sglang.launch_server ... --json-model-override-args '{"rope_scaling": {"rope_type": "yarn", "factor": 4.0, "original_max_position_embeddings": 262144}}' --context-length 1000000 ```
📝 NOTE

Open-source runtimes implement YaRN statically: the same scaling factor is applied to every request regardless of its length, which can slightly hurt quality on ordinary-length inputs. Only enable rope_scaling when your workload genuinely needs the longer window, and size factor to match it — the target window is roughly factor × 262,144, so if your requests top out around 524,288 tokens, factor: 2.0 is the better setting.

### Using Ornith-1.5-397B via the Chat Completions API Once a vLLM or SGLang server is running, talk to it with any OpenAI-compatible client. #### Basic Usage ```python from openai import OpenAI client = OpenAI( base_url="http://localhost:8000/v1", api_key="EMPTY", # any non-empty string works for a local server ) response = client.chat.completions.create( model="Ornith-1.5-397B", messages=[ {"role": "user", "content": "Write a one-line Python lambda that squares a number."} ], temperature=0.6, top_p=0.95, max_tokens=1024, ) message = response.choices[0].message # reasoning_content holds the trace; content holds the final answer. print("reasoning:", getattr(message, "reasoning_content", None)) print("answer:", message.content) ``` You can also stream tokens, or hand the model tools — Ornith-1.5-397B emits well-formed function calls that the server parses into the standard `tool_calls` field: ```python tools = [ { "type": "function", "function": { "name": "get_weather", "description": "Get the current weather for a city", "parameters": { "type": "object", "properties": {"city": {"type": "string"}}, "required": ["city"], }, }, } ] response = client.chat.completions.create( model="Ornith-1.5-397B", messages=[{"role": "user", "content": "What is the weather in Paris right now?"}], tools=tools, tool_choice="auto", temperature=0.6, max_tokens=2048, ) tool_call = response.choices[0].message.tool_calls[0] print(tool_call.function.name, tool_call.function.arguments) # -> get_weather {"city": "Paris"} ``` You can point any OpenAI-compatible SDK (Python, Node.js, etc.) or `curl` at the same `/v1/chat/completions` endpoint. ## Agentic Usage Ornith-1.5-397B excels in tool-calling and agentic coding. It exposes an OpenAI-compatible endpoint with tool calling and works out of the box with standard agent frameworks. **Examples of using Ornith with agents:** #### Ollama ```bash ollama run hf.co/ornith-ai/Ornith-1.5-397B-GGUF ``` #### Atomic.chat ```bash # Atomic.chat loads a GGUF build of Ornith (ornith-ai/Ornith-1.5-397B-GGUF) # through llama.cpp's OpenAI-compatible API on port 8000. llama-server -hf ornith-ai/Ornith-1.5-397B-GGUF --port 8000 -c 262144 ``` #### llama.cpp ```bash # llama.cpp — serve an OpenAI-compatible API on port 8000. llama-server -hf ornith-ai/Ornith-1.5-397B-GGUF --port 8000 -c 262144 ``` #### Hermes Agent ```bash # Hermes talks to any OpenAI-compatible endpoint — point it at your Ornith server. export OPENAI_BASE_URL="http://localhost:8000/v1" export OPENAI_API_KEY="EMPTY" export MODEL="ornith-ai/Ornith-1.5-397B" ``` #### OpenClaw ```bash # OpenClaw talks to any OpenAI-compatible endpoint — point it at your Ornith server. export OPENAI_BASE_URL="http://localhost:8000/v1" export OPENAI_API_KEY="EMPTY" export OPENAI_MODEL="ornith-ai/Ornith-1.5-397B" ``` #### Unsloth Studio ```bash pip install unsloth # Load Ornith for fast local inference or fine-tuning (Python): # from unsloth import FastLanguageModel # model, tokenizer = FastLanguageModel.from_pretrained( # "ornith-ai/Ornith-1.5-397B", # max_seq_length=262144, # load_in_4bit=True, # ) ``` ### Coding CLIs Ornith-1.5-397B is optimized for terminal-based coding agents. Point any OpenAI-compatible coding CLI at your Ornith-1.5-397B endpoint (set `OPENAI_BASE_URL` and `OPENAI_API_KEY`) to understand large codebases, automate tedious work, and ship faster. #### OpenCode ```bash # Register your local Ornith endpoint as a provider in ~/.config/opencode/opencode.json: # # { # "$schema": "https://opencode.ai/config.json", # "provider": { # "ornith": { # "npm": "@ai-sdk/openai-compatible", # "name": "Ornith (local)", # "options": { "baseURL": "http://localhost:8000/v1", "apiKey": "EMPTY" }, # "models": { "ornith-ai/Ornith-1.5-397B": { "name": "Ornith-1.5-397B" } } # } # } # } opencode ``` ### Citation If you find our work helpful, feel free to give us a cite. ```bibtex @misc{ornith_1_5, title = {{Ornith-1.5}: From Self-Scaffolding to Self-Improvement}, url = {https://ornith.ai/ornith_1_5.html}, author = {{Ornith Team}}, year = {2026} } ```