Agnes-AI/Agnes-2.5-Pro-Alpha

Agnes 2.5 Pro Alpha

Hello! 👋 Today we are introducing Agnes 2.5 Pro Alpha, our most capable reasoning model for advanced coding, scientific problem solving, long-context analysis, multimodal understanding, and agentic workflows.

Highlights:

• Competitive benchmark performance: Agnes outperforms Qwen3.5-397B on six of the eight evaluations visualized below, with particularly clear gains on Terminal-Bench v2.1, CritPt, and AA-Omniscience Accuracy.
• Built for demanding work: a 1M-token context window, up to 65,536 output tokens, extended reasoning, tool calling, and text, image understanding.

Agnes 2.5 Pro Alpha

A multimodal reasoning model available through the Agnes AI API. The model combines long-context understanding with strong coding and scientific reasoning, while retaining the throughput and pricing needed for production workloads.

Benchmarks

Agnes 2.5 Pro Alpha is evaluated against the same comparison set selected for Ornith-1.0-397B: Qwen3.5-397B, Qwen3.7-Max, GLM-5.2-744B, MiniMax-M3-428B, DeepSeek-V4-Pro-1.6T, Claude Opus 4.7, and Claude Opus 4.8. Every result below is an independent Artificial Analysis benchmark measurement.

Benchmark	Agnes 2.5 Pro Alpha	Qwen3.5 397B	Qwen3.7 Max	GLM-5.2 744B	MiniMax-M3 428B	DeepSeek-V4-Pro 1.6T	Claude Opus 4.7	Claude Opus 4.8
Agentic Work & Coding
GDPval-AA v2 †	33.8	23.2	38.6	50.3	44.3	54.5	49.5	54.2
τ³-Banking	12.4	13.4	11.8	34.6	15.3	39.6	34.6	34.2
Terminal-Bench v2.1	67.0	51.3	74.5	77.9	65.2	78.7	83.1	84.6
SciCode	42.2	42.0	48.8	50.5	45.4	49.2	54.5	53.5
Long Context & Scientific Reasoning
AA-LCR	73.0	72.7	74.7	76.7	80.3	75.3	75.3	73.0
Humanity's Last Exam	33.6	29.0	40.5	41.1	39.0	41.0	42.3	48.7
GPQA Diamond	87.6	89.3	92.3	89.5	92.9	92.8	91.4	92.0
CritPt	10.9	1.7	13.4	20.9	3.7	18.0	12.0	20.9
Knowledge Reliability
AA-Omniscience Accuracy	33.5	30.8	31.1	24.3	16.7	49.1	48.9	48.8
Non-Hallucination Rate	11.9	11.1	74.4	73.7	81.6	5.2	57.7	60.7

† GDPval-AA v2 uses Artificial Analysis' normalized score, (Elo − 500) / 2000. Non-Hallucination Rate is 1 − hallucination rate. Higher is better for every benchmark. Snapshot checked August 18, 2026; values may change as evaluations are updated.

Model Information

Property	Value
Developed by	Agnes AI
Model name	Agnes 2.5 Pro Alpha
Model type	Multimodal reasoning model
License	Apache License 2.0
Languages	English, Chinese
Context window	1,048,576 tokens
Maximum output	65,536 tokens
Input modalities	Text, image
Output modality	Text
Precision	BF16
Tool calling	Yes
Streaming	Yes
Release date	July 2026

License

This repository is licensed under the Apache License 2.0.

Agnes 2.5 Pro Alpha is a post-trained derivative of Qwen/Qwen3.5-397B-A17B, which is also licensed under Apache License 2.0. Original copyright notices are retained. Additional post-training was performed by Agnes AI.

See the LICENSE file in this repository for the full terms.

Hardware Requirements

The Quickstart launch command uses 8-GPU tensor parallelism. The checkpoint is a large multi-shard BF16 package; a single GPU is not sufficient.

Resource	Recommendation
GPUs	8× NVIDIA H200 (141 GB) or equivalent
Tensor parallel	--tp 8
Host memory / disk	Fast NVMe with about 1 TB free for weights, tokenizer files, and download cache
Context length	The sample command sets --context-length 1024000. If you hit out-of-memory errors, lower this value
Network	Optional. The same model is also served at https://apihub.agnes-ai.com/v1 without local GPUs

Quickstart

REASONING MODEL

Agnes 2.5 Pro Alpha uses extended reasoning for complex tasks and is available through OpenAI-compatible Chat Completions and Responses APIs. Keep API keys in environment variables and use publicly accessible URLs for image inputs.

SGLang

python -m sglang.launch_server \
    --model-path Agnes-AI/Agnes-2.5-Pro-Alpha \
    --served-model-name agnes-2.5-pro-alpha \
    --tp 8 \
    --host 0.0.0.0 --port 8000 \
    --context-length 1024000 \
    --mem-fraction-static 0.85 \
    --tool-call-parser qwen3_coder \
    --reasoning-parser qwen3

Chat Completions

export AGNES_API_KEY="your-api-key"

curl https://apihub.agnes-ai.com/v1/chat/completions \
  -H "Authorization: Bearer ${AGNES_API_KEY}" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "agnes-2.5-pro-alpha",
    "messages": [
      {
        "role": "user",
        "content": "Review this API handler for security issues and provide a corrected version."
      }
    ],
    "temperature": 1.0,
    "max_tokens": 2000
  }'

Python

pip install openai

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["AGNES_API_KEY"],
    base_url="https://apihub.agnes-ai.com/v1",
)

response = client.chat.completions.create(
    model="agnes-2.5-pro-alpha",
    messages=[
        {
            "role": "user",
            "content": "Design a fault-tolerant event processing architecture.",
        }
    ],
    temperature=1.0,
    max_tokens=2000,
)

print(response.choices[0].message.content)

Image Understanding

response = client.chat.completions.create(
    model="agnes-2.5-pro-alpha",
    messages=[
        {
            "role": "user",
            "content": [
                {"type": "text", "text": "Explain this chart and call out anomalies."},
                {
                    "type": "image_url",
                    "image_url": {"url": "https://example.com/chart.png"},
                },
            ],
        }
    ],
)

Responses API

curl https://apihub.agnes-ai.com/v1/responses \
  -H "Authorization: Bearer ${AGNES_API_KEY}" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "agnes-2.5-pro-alpha",
    "input": "Create a step-by-step migration plan from a monolith to services.",
    "max_output_tokens": 2000
  }'

Recommended Inference Settings

Use sampling rather than greedy decoding. Leave enough max_tokens / max_output_tokens for extended reasoning.

Setting	Recommended
temperature	1.0
top_p	0.95
top_k	20
repetition_penalty	1.05
max_tokens	2000 or higher

Raise max_tokens if a response stops early.

Model Capabilities

Capability	Support
Advanced reasoning	Yes
Coding and debugging	Yes
Long-context analysis	1M tokens
Maximum output	65,536 tokens
Image understanding	Yes, via public image URL
Tool calling	Yes
Streaming	Yes
OpenAI-compatible APIs	Chat Completions and Responses

Agnes 2.5 Pro Alpha is especially well suited to repository-level coding, technical research, document synthesis, visual analysis, and tool-enabled agents that need to reason across long and complex contexts.

Responsible Use

Model outputs can contain errors. Validate high-impact decisions and tool actions in the application layer, and review the applicable Agnes AI service terms before sending sensitive or regulated data.

Citation

@misc{agnes25proalpha2026,
  title        = {Agnes 2.5 Pro Alpha},
  author       = {{Agnes AI}},
  year         = {2026},
  month        = jul,
  howpublished = {API model},
  url          = {https://wiki.agnes-ai.com/en/docs/agnes-25-pro-alpha}
}