💜Qwen3.5 - How to Run Locally Guide

Run the new Qwen3.5 LLMs including new Medium series: Qwen3.5-35B-A3B, 27B, 122B-A10B, and 397B-A17B on your local device!

Qwen3.5 is Alibaba’s new model family, including Qwen3.5-35B-A3B, 27B, 122B-A10B and 397B-A17B. The multimodal hybrid reasoning LLMs deliver the strongest performances for their sizes. They support 256K context across 201 languages, have thinking and non-thinking modes, and excel in agentic coding, vision, chat, and long-context tasks. The 35B and 27B models work on a 21GB Mac / RAM device. See all GGUFs here.

All Qwen3.5 Medium models are now available!

Looping / over-thinking issues? Please use the correct inference settings.

Qwen3.5-397B-A17B is comparable to Gemini 3 Pro, Claude Opus 4.5, and GPT-5.2. The full 397B model is ~807GB on disk, and 3-bit runs on a 192GB Mac / RAM device or 4-bit MXFP4 on a 256GB Mac. See quantization benchmarks for our GGUFs!

All uploads use Unsloth Dynamic 2.0 for SOTA quantization performance - so 4-bit has important layers upcasted to 8 or 16-bit. Thank you Qwen for providing Unsloth with day zero access. You can also fine-tune Qwen3.5 with Unsloth.

35B-A3B27B122B-A10B397B-A17BFine-tune Qwen3.5

⚙️ Usage Guide

Table: Inference hardware requirements (units = total memory: RAM + VRAM, or unified memory)

Qwen3.5	3-bit	4-bit	6-bit	8-bit	BF16
27B	14 GB	17 GB	24 GB	30 GB	54 GB
35B-A3B	17 GB	22 GB	30 GB	38 GB	70 GB
122B-A10B	60 GB	70 GB	106 GB	132 GB	245 GB
397B-A17B	180 GB	214 GB	340 GB	512 GB	810 GB

For best performance, make sure your total available memory (VRAM + system RAM) exceeds the size of the quantized model file you’re downloading. If it doesn’t, llama.cpp can still run via SSD/HDD offloading, but inference will be slower.

Between 27B and 35B-A3B, use 27B if you want slightly more accurate results and can't fit in your device. Go for 35B-A3B if you want much faster inference.

Recommended Settings

• Maximum context window: 262,144 (can be extended to 1M via YaRN)

• presence_penalty = 0.0 to 2.0 default this is off, but to reduce repetitions, you can use this, however using a higher value may result in slight decrease in performance

• Adequate Output Length: 32,768 tokens for most queries

As Qwen3.5 is hybrid reasoning, thinking and non-thinking mode have different settings:

Thinking mode:

General tasks	Precise coding tasks (e.g. WebDev)
temperature = 1.0	temperature = 0.6
top_p = 0.95	top_p = 0.95
tok_k = 20	tok_k = 20
min_p = 0.0	min_p = 0.0
presence_penalty = 1.5	presence_penalty = 0.0
repeat penalty = disabled or 1.0	repeat penalty = disabled or 1.0

Thinking mode for general tasks:

temperature=1.0, top_p=0.95, top_k=20, min_p=0.0, presence_penalty=1.5, repetition_penalty=1.0

Thinking mode for precise coding tasks:

temperature=0.6, top_p=0.95, top_k=20, min_p=0.0, presence_penalty=0.0, repetition_penalty=1.0

Instruct (non-thinking) mode settings:

General tasks	Reasoning tasks
temperature = 0.7	temperature = 1.0
top_p = 0.8	top_p = 0.95
tok_k = 20	tok_k = 20
min_p = 0.0	min_p = 0.0
presence_penalty = 1.5	presence_penalty = 1.5
repeat penalty = disabled or 1.0	repeat penalty = disabled or 1.0

To disable thinking / reasoning, use --chat-template-kwargs "{\"enable_thinking\": false}"

Instruct (non-thinking) for general tasks:

temperature=0.7, top_p=0.8, top_k=20, min_p=0.0, presence_penalty=1.5, repetition_penalty=1.0

Instruct (non-thinking) for reasoning tasks:

temperature=1.0, top_p=0.95, top_k=20, min_p=0.0, presence_penalty=1.5, repetition_penalty=1.0

Qwen3.5 Inference Tutorials:

Because Qwen3.5 comes in many different sizes, we'll be using Dynamic 4-bit MXFP4_MOE GGUF variants for all inference workloads. Click below to navigate to designated model instructions:

Qwen3.5-35B-A3BQwen3.5-27BQwen3.5-122B-A10BQwen3.5-397B-A17B

Unsloth Dynamic GGUF uploads:

Qwen3.5-35B-A3B	Qwen3.5-27B	Qwen3.5-122B-A10B	Qwen3.5-397B-A17B

presence_penalty = 0.0 to 2.0 default this is off, but to reduce repetitions, you can use this, however using a higher value may result in slight decrease in performance

Qwen3.5-35B-A3B

For this guide we will be utilizing Dynamic 4-bit which works great on a 24GB RAM / Mac device for fast inference. Because the model is only around 72GB at full F16 precision, we won't need to worry much about performance. GGUF: Qwen3.5-35B-A3B-GGUF

✨ Run in llama.cpp

1

Obtain the latest llama.cpp on GitHub here. You can follow the build instructions below as well. Change -DGGML_CUDA=ON to -DGGML_CUDA=OFF if you don't have a GPU or just want CPU inference.

apt-get update
apt-get install pciutils build-essential cmake curl libcurl4-openssl-dev -y
git clone https://github.com/ggml-org/llama.cpp
cmake llama.cpp -B llama.cpp/build \
    -DBUILD_SHARED_LIBS=OFF -DGGML_CUDA=ON
cmake --build llama.cpp/build --config Release -j --clean-first --target llama-cli llama-mtmd-cli llama-server llama-gguf-split
cp llama.cpp/build/bin/llama-* llama.cpp

2

If you want to use llama.cpp directly to load models, you can do the below: (:Q3_K_XL) is the quantization type. You can also download via Hugging Face (point 3). This is similar to ollama run . Use export LLAMA_CACHE="folder" to force llama.cpp to save to a specific location. The model has a maximum of 256K context length.

Follow one of the specific commands below, according to your use-case:

Thinking mode:

Precise coding tasks (e.g. WebDev):

export LLAMA_CACHE="unsloth/Qwen3.5-35B-A3B-GGUF"
./llama.cpp/llama-cli \
    -hf unsloth/Qwen3.5-35B-A3B-GGUF:Q4_K_M \
    --ctx-size 16384 \
    --temp 0.6 \
    --top-p 0.95 \
    --top-k 20 \
    --min-p 0.00

General tasks:

export LLAMA_CACHE="unsloth/Qwen3.5-35B-A3B-GGUF"
./llama.cpp/llama-cli \
    -hf unsloth/Qwen3.5-35B-A3B-GGUF:Q4_K_M \
    --ctx-size 16384 \
    --temp 1.0 \
    --top-p 0.95 \
    --top-k 20 \
    --min-p 0.00

Non-thinking mode:

General tasks:

export LLAMA_CACHE="unsloth/Qwen3.5-35B-A3B-GGUF"
./llama.cpp/llama-cli \
    -hf unsloth/Qwen3.5-35B-A3B-GGUF:Q4_K_M \
    --ctx-size 16384 \
    --temp 0.7 \
    --top-p 0.8 \
    --top-k 20 \
    --min-p 0.00 \
    --chat-template-kwargs "{\"enable_thinking\": false}"

Reasoning tasks:

export LLAMA_CACHE="unsloth/Qwen3.5-35B-A3B-GGUF"
./llama.cpp/llama-cli \
    -hf unsloth/Qwen3.5-35B-A3B-GGUF:Q4_K_M \
    --ctx-size 16384 \
    --temp 1.0 \
    --top-p 0.95 \
    --top-k 20 \
    --min-p 0.00 \
    --chat-template-kwargs "{\"enable_thinking\": false}"

3

Download the model via (after installing pip install huggingface_hub hf_transfer ). You can choose Q4_K_M or other quantized versions like UD-Q4_K_XL . We recommend using at least 2-bit dynamic quant UD-Q2_K_XL to balance size and accuracy. If downloads get stuck, see: Hugging Face Hub, XET debugging

hf download unsloth/Qwen3.5-35B-A3B-GGUF \
    --local-dir unsloth/Qwen3.5-35B-A3B-GGUF \
    --include "*Q4_K_M*" # Use "*UD-Q2_K_XL*" for Dynamic 2bit

4

Then run the model in conversation mode:

./llama.cpp/llama-cli \
    --model unsloth/Qwen3.5-35B-A3B-GGUF/Qwen3.5-35B-A3B-Q4_K_M.gguf \
    --mmproj unsloth/Qwen3.5-35B-A3B-GGUF/mmproj-F16.gguf \
    --seed 3407 \
    --temp 1.0 \
    --top-p 0.95 \
    --min-p 0.01 \
    --top-k 40

Qwen3.5-27B

For this guide we will be utilizing Dynamic 4-bit which works great on a 18GB RAM / Mac device for fast inference. GGUF: Qwen3.5-27B-GGUF

1

Obtain the latest llama.cpp on GitHub here. You can follow the build instructions below as well. Change -DGGML_CUDA=ON to -DGGML_CUDA=OFF if you don't have a GPU or just want CPU inference.

apt-get update
apt-get install pciutils build-essential cmake curl libcurl4-openssl-dev -y
git clone https://github.com/ggml-org/llama.cpp
cmake llama.cpp -B llama.cpp/build \
    -DBUILD_SHARED_LIBS=OFF -DGGML_CUDA=ON
cmake --build llama.cpp/build --config Release -j --clean-first --target llama-cli llama-mtmd-cli llama-server llama-gguf-split
cp llama.cpp/build/bin/llama-* llama.cpp

2

If you want to use llama.cpp directly to load models, you can do the below: (:Q3_K_XL) is the quantization type. You can also download via Hugging Face (point 3). This is similar to ollama run . Use export LLAMA_CACHE="folder" to force llama.cpp to save to a specific location. The model has a maximum of 256K context length.

Follow one of the specific commands below, according to your use-case:

Thinking mode:

Precise coding tasks (e.g. WebDev):

export LLAMA_CACHE="unsloth/Qwen3.5-27B-GGUF"
./llama.cpp/llama-cli \
    -hf unsloth/Qwen3.5-27B-GGUF:Q4_K_M \
    --ctx-size 16384 \
    --temp 0.6 \
    --top-p 0.95 \
    --top-k 20 \
    --min-p 0.00

General tasks:

export LLAMA_CACHE="unsloth/Qwen3.5-27B-GGUF"
./llama.cpp/llama-cli \
    -hf unsloth/Qwen3.5-27B-GGUF:Q4_K_M \
    --ctx-size 16384 \
    --temp 1.0 \
    --top-p 0.95 \
    --top-k 20 \
    --min-p 0.00

Non-thinking mode:

General tasks:

export LLAMA_CACHE="unsloth/Qwen3.5-27B-GGUF"
./llama.cpp/llama-cli \
    -hf unsloth/Qwen3.5-27B-GGUF:Q4_K_M \
    --ctx-size 16384 \
    --temp 0.7 \
    --top-p 0.8 \
    --top-k 20 \
    --min-p 0.00 \
    --chat-template-kwargs "{\"enable_thinking\": false}"

Reasoning tasks:

export LLAMA_CACHE="unsloth/Qwen3.5-27B-GGUF"
./llama.cpp/llama-cli \
    -hf unsloth/Qwen3.5-27B-GGUF:Q4_K_M \
    --ctx-size 16384 \
    --temp 1.0 \
    --top-p 0.95 \
    --top-k 20 \
    --min-p 0.00 \
    --chat-template-kwargs "{\"enable_thinking\": false}"

3

Download the model via (after installing pip install huggingface_hub hf_transfer ). You can choose MXFP4_MOE or other quantized versions like UD-Q4_K_XL . We recommend using at least 2-bit dynamic quant UD-Q2_K_XL to balance size and accuracy. If downloads get stuck, see: Hugging Face Hub, XET debugging

hf download unsloth/Qwen3.5-27B-GGUF \
    --local-dir unsloth/Qwen3.5-27B-GGUF \
    --include "*Q4_K_M*" # Use "*UD-Q2_K_XL*" for Dynamic 2bit

4

Then run the model in conversation mode:

./llama.cpp/llama-cli \
    --model unsloth/Qwen3.5-27B-GGUF/Qwen3.5-27B-Q4_K_M.gguf \
    --mmproj unsloth/Qwen3.5-27B-GGUF/mmproj-F16.gguf \
    --seed 3407 \
    --temp 1.0 \
    --top-p 0.95 \
    --min-p 0.01 \
    --top-k 40

Qwen3.5-122B-A10B

For this guide we will be utilizing Dynamic 4-bit which works great on a 70GB RAM / Mac device for fast inference. GGUF: Qwen3.5-122B-A10B-GGUF

1

Obtain the latest llama.cpp on GitHub here. You can follow the build instructions below as well. Change -DGGML_CUDA=ON to -DGGML_CUDA=OFF if you don't have a GPU or just want CPU inference.

apt-get update
apt-get install pciutils build-essential cmake curl libcurl4-openssl-dev -y
git clone https://github.com/ggml-org/llama.cpp
cmake llama.cpp -B llama.cpp/build \
    -DBUILD_SHARED_LIBS=OFF -DGGML_CUDA=ON
cmake --build llama.cpp/build --config Release -j --clean-first --target llama-cli llama-mtmd-cli llama-server llama-gguf-split
cp llama.cpp/build/bin/llama-* llama.cpp

2

If you want to use llama.cpp directly to load models, you can do the below: (:Q3_K_XL) is the quantization type. You can also download via Hugging Face (point 3). This is similar to ollama run . Use export LLAMA_CACHE="folder" to force llama.cpp to save to a specific location. The model has a maximum of 256K context length.

Follow one of the specific commands below, according to your use-case:

Thinking mode:

Precise coding tasks (e.g. WebDev):

export LLAMA_CACHE="unsloth/Qwen3.5-122B-A10B-GGUF"
./llama.cpp/llama-cli \
    -hf unsloth/Qwen3.5-122B-A10B-GGUF:MXFP4_MOE \
    --ctx-size 16384 \
    --temp 0.6 \
    --top-p 0.95 \
    --top-k 20 \
    --min-p 0.00

General tasks:

export LLAMA_CACHE="unsloth/Qwen3.5-122B-A10B-GGUF"
./llama.cpp/llama-cli \
    -hf unsloth/Qwen3.5-122B-A10B-GGUF:MXFP4_MOE \
    --ctx-size 16384 \
    --temp 1.0 \
    --top-p 0.95 \
    --top-k 20 \
    --min-p 0.00

Non-thinking mode:

General tasks:

export LLAMA_CACHE="unsloth/Qwen3.5-122B-A10B-GGUF"
./llama.cpp/llama-cli \
    -hf unsloth/Qwen3.5-122B-A10B-GGUF:MXFP4_MOE \
    --ctx-size 16384 \
    --temp 0.7 \
    --top-p 0.8 \
    --top-k 20 \
    --min-p 0.00 \
    --chat-template-kwargs "{\"enable_thinking\": false}"

Reasoning tasks:

export LLAMA_CACHE="unsloth/Qwen3.5-122B-A10B-GGUF"
./llama.cpp/llama-cli \
    -hf unsloth/Qwen3.5-122B-A10B-GGUF:MXFP4_MOE \
    --ctx-size 16384 \
    --temp 1.0 \
    --top-p 0.95 \
    --top-k 20 \
    --min-p 0.00 \
    --chat-template-kwargs "{\"enable_thinking\": false}"

3

Download the model via (after installing pip install huggingface_hub hf_transfer ). You can choose MXFP4_MOE (dynamic 4bit) or other quantized versions like UD-Q4_K_XL . We recommend using at least 2-bit dynamic quant UD-Q2_K_XL to balance size and accuracy. If downloads get stuck, see: Hugging Face Hub, XET debugging

hf download unsloth/Qwen3.5-122B-A10B-GGUF \
    --local-dir unsloth/Qwen3.5-122B-A10B-GGUF \
    --include "*MXFP4_MOE*" # Use "*UD-Q2_K_XL*" for Dynamic 2bit

4

Then run the model in conversation mode:

./llama.cpp/llama-cli \
    --model unsloth/Qwen3.5-122B-A10B-GGUF/MXFP4_MOE/Qwen3.5-122B-A10B-MXFP4_MOE-00001-of-00003.gguf \
    --mmproj unsloth/Qwen3.5-122B-A10B-GGUF/mmproj-F16.gguf \
    --ctx-size 16384 \
    --temp 0.6 \
    --top-p 0.95 \
    --top-k 20 \
    --min-p 0.00
    --seed 3407

Qwen3.5-397B-A17B

For 397B-A17B, Unsloth 4-bit dynamic quant UD-Q4_K_XL uses 214GB of disk space - this can directly fit on a 256GB M3 Ultra, and also works well in a 1x24GB card and 256GB of RAM with MoE offloading for 25+ tokens/s. The 3-bit quant will fit on a 192GB RAM and 8-bit requires 512GB RAM/VRAM. GGUF: Qwen3.5-397B-A17B-GGUF

1

Obtain the latest llama.cpp on GitHub here. You can follow the build instructions below as well. Change -DGGML_CUDA=ON to -DGGML_CUDA=OFF if you don't have a GPU or just want CPU inference.

apt-get update
apt-get install pciutils build-essential cmake curl libcurl4-openssl-dev -y
git clone https://github.com/ggml-org/llama.cpp
cmake llama.cpp -B llama.cpp/build \
    -DBUILD_SHARED_LIBS=OFF -DGGML_CUDA=ON
cmake --build llama.cpp/build --config Release -j --clean-first --target llama-cli llama-mtmd-cli llama-server llama-gguf-split
cp llama.cpp/build/bin/llama-* llama.cpp

2

If you want to use llama.cpp directly to load models, you can do the below: (:Q3_K_XL) is the quantization type. You can also download via Hugging Face (point 3). This is similar to ollama run . Use export LLAMA_CACHE="folder" to force llama.cpp to save to a specific location. Remember the model has only a maximum of 256K context length.

Follow this for thinking mode:

export LLAMA_CACHE="unsloth/Qwen3.5-397B-A17B-GGUF"
./llama.cpp/llama-cli \
    -hf unsloth/Qwen3.5-397B-A17B-GGUF:MXFP4_MOE \
    --ctx-size 16384 \
    --temp 0.6 \
    --top-p 0.95 \
    --top-k 20 \
    --min-p 0.00

Follow this for non-thinking mode:

export LLAMA_CACHE="unsloth/Qwen3.5-397B-A17B-GGUF"
./llama.cpp/llama-cli \
    -hf unsloth/Qwen3.5-397B-A17B-GGUF:MXFP4_MOE \
    --ctx-size 16384 \
    --temp 0.7 \
    --top-p 0.8 \
    --top-k 20 \
    --min-p 0.00 \
    --chat-template-kwargs "{\"enable_thinking\": false}"

3

Download the model via (after installing pip install huggingface_hub hf_transfer ). You can choose MXFP4_MOE (dynamic 4bit) or other quantized versions like UD-Q4_K_XL . We recommend using at least 2-bit dynamic quant UD-Q2_K_XL to balance size and accuracy. If downloads get stuck, see: Hugging Face Hub, XET debugging

hf download unsloth/Qwen3.5-397B-A17B-GGUF \
    --local-dir unsloth/Qwen3.5-397B-A17B-GGUF \
    --include "*MXFP4_MOE*" # Use "*UD-Q2_K_XL*" for Dynamic 2bit

4

You can edit --threads 32 for the number of CPU threads, --ctx-size 16384 for context length, --n-gpu-layers 2 for GPU offloading on how many layers. Try adjusting it if your GPU goes out of memory. Also remove it if you have CPU only inference.

./llama.cpp/llama-cli \
    --model unsloth/Qwen3.5-397B-A17B-GGUF/MXFP4_MOE/Qwen3.5-397B-A17B-MXFP4_MOE-00001-of-00006.gguf \
    --mmproj unsloth/Qwen3.5-397B-A17B-GGUF/mmproj-F16.gguf \
    --ctx-size 16384 \
    --temp 0.6 \
    --top-p 0.95 \
    --top-k 20 \
    --min-p 0.00
    --seed 3407

🦙 Llama-server serving & OpenAI's completion library

To deploy Qwen3.5-397B-A17B for production, we use llama-server In a new terminal say via tmux, deploy the model via:

./llama.cpp/llama-server \
    --model unsloth/Qwen3.5-397B-A17B-GGUF/MXFP4_MOE/Qwen3.5-397B-A17B-MXFP4_MOE-00001-of-00006.gguf \
    --mmproj unsloth/Qwen3.5-397B-A17B-GGUF/mmproj-F16.gguf \
    --alias "unsloth/Qwen3.5-397B-A17B" \
    --temp 0.6 \
    --top-p 0.95 \
    --ctx-size 16384 \
    --top-k 20 \
    --min-p 0.00 \
    --port 8001

Then in a new terminal, after doing pip install openai, do:

from openai import OpenAI
import json
openai_client = OpenAI(
    base_url = "http://127.0.0.1:8001/v1",
    api_key = "sk-no-key-required",
)
completion = openai_client.chat.completions.create(
    model = "unsloth/Qwen3.5-397B-A17B",
    messages = [{"role": "user", "content": "Create a Snake game."},],
)
print(completion.choices[0].message.content)

To disable thinking / reasoning, use --chat-template-kwargs "{\"enable_thinking\": false}"

👾 OpenAI Codex & Claude Code

To run the model via local coding agentic workloads, you can follow our guide. Just change the model name 'GLM-4.7-Flash' to your desired 'Qwen3.5' and ensure you follow the correct Qwen3.5 parameters and usage instructions. Use the llama-server we just set up just then.

Claude Code

OpenAI Codex

After following the instructions for Claude Code for example you will see:

We can then ask say Create a Python game for Chess :

🔨Tool Calling with Qwen3.5

See Tool Calling Guide for more details on how to do tool calling. In a new terminal (if using tmux, use CTRL+B+D), we create some tools like adding 2 numbers, executing Python code, executing Linux functions and much more:

import json, subprocess, random
from typing import Any
def add_number(a: float | str, b: float | str) -> float:
    return float(a) + float(b)
def multiply_number(a: float | str, b: float | str) -> float:
    return float(a) * float(b)
def substract_number(a: float | str, b: float | str) -> float:
    return float(a) - float(b)
def write_a_story() -> str:
    return random.choice([
        "A long time ago in a galaxy far far away...",
        "There were 2 friends who loved sloths and code...",
        "The world was ending because every sloth evolved to have superhuman intelligence...",
        "Unbeknownst to one friend, the other accidentally coded a program to evolve sloths...",
    ])
def terminal(command: str) -> str:
    if "rm" in command or "sudo" in command or "dd" in command or "chmod" in command:
        msg = "Cannot execute 'rm, sudo, dd, chmod' commands since they are dangerous"
        print(msg); return msg
    print(f"Executing terminal command `{command}`")
    try:
        return str(subprocess.run(command, capture_output = True, text = True, shell = True, check = True).stdout)
    except subprocess.CalledProcessError as e:
        return f"Command failed: {e.stderr}"
def python(code: str) -> str:
    data = {}
    exec(code, data)
    del data["__builtins__"]
    return str(data)
MAP_FN = {
    "add_number": add_number,
    "multiply_number": multiply_number,
    "substract_number": substract_number,
    "write_a_story": write_a_story,
    "terminal": terminal,
    "python": python,
}
tools = [
    {
        "type": "function",
        "function": {
            "name": "add_number",
            "description": "Add two numbers.",
            "parameters": {
                "type": "object",
                "properties": {
                    "a": {
                        "type": "string",
                        "description": "The first number.",
                    },
                    "b": {
                        "type": "string",
                        "description": "The second number.",
                    },
                },
                "required": ["a", "b"],
            },
        },
    },
    {
        "type": "function",
        "function": {
            "name": "multiply_number",
            "description": "Multiply two numbers.",
            "parameters": {
                "type": "object",
                "properties": {
                    "a": {
                        "type": "string",
                        "description": "The first number.",
                    },
                    "b": {
                        "type": "string",
                        "description": "The second number.",
                    },
                },
                "required": ["a", "b"],
            },
        },
    },
    {
        "type": "function",
        "function": {
            "name": "substract_number",
            "description": "Substract two numbers.",
            "parameters": {
                "type": "object",
                "properties": {
                    "a": {
                        "type": "string",
                        "description": "The first number.",
                    },
                    "b": {
                        "type": "string",
                        "description": "The second number.",
                    },
                },
                "required": ["a", "b"],
            },
        },
    },
    {
        "type": "function",
        "function": {
            "name": "write_a_story",
            "description": "Writes a random story.",
            "parameters": {
                "type": "object",
                "properties": {},
                "required": [],
            },
        },
    },
    {
        "type": "function",
        "function": {
            "name": "terminal",
            "description": "Perform operations from the terminal.",
            "parameters": {
                "type": "object",
                "properties": {
                    "command": {
                        "type": "string",
                        "description": "The command you wish to launch, e.g `ls`, `rm`, ...",
                    },
                },
                "required": ["command"],
            },
        },
    },
    {
        "type": "function",
        "function": {
            "name": "python",
            "description": "Call a Python interpreter with some Python code that will be ran.",
            "parameters": {
                "type": "object",
                "properties": {
                    "code": {
                        "type": "string",
                        "description": "The Python code to run",
                    },
                },
                "required": ["code"],
            },
        },
    },
]

We then use the below functions (copy and paste and execute) which will parse the function calls automatically and call the OpenAI endpoint for any model:

from openai import OpenAI
def unsloth_inference(
    messages,
    temperature = 0.6,
    top_p = 0.95,
    top_k = 20,
    min_p = 0.00,
    repetition_penalty = 1.0,
):
    messages = messages.copy()
    openai_client = OpenAI(
        base_url = "http://127.0.0.1:8001/v1",
        api_key = "sk-no-key-required",
    )
    model_name = next(iter(openai_client.models.list())).id
    print(f"Using model = {model_name}")
    has_tool_calls = True
    original_messages_len = len(messages)
    while has_tool_calls:
        print(f"Current messages = {messages}")
        response = openai_client.chat.completions.create(
            model = model_name,
            messages = messages,
            temperature = temperature,
            top_p = top_p,
            tools = tools if tools else None,
            tool_choice = "auto" if tools else None,
            extra_body = {"top_k": top_k, "min_p": min_p, "repetition_penalty" :repetition_penalty,}
        )
        tool_calls = response.choices[0].message.tool_calls or []
        content = response.choices[0].message.content or ""
        tool_calls_dict = [tc.to_dict() for tc in tool_calls] if tool_calls else tool_calls
        messages.append({"role": "assistant", "tool_calls": tool_calls_dict, "content": content,})
        for tool_call in tool_calls:
            fx, args, _id = tool_call.function.name, tool_call.function.arguments, tool_call.id
            out = MAP_FN[fx](**json.loads(args))
            messages.append({"role": "tool", "tool_call_id": _id, "name": fx, "content": str(out),})
        else:
            has_tool_calls = False
    return messages

After launching Qwen3.5 via llama-server like in Qwen3.5 or see Tool Calling Guide for more details, we then can do some tool calls.

📊 Benchmarks

Unsloth GGUF Benchmarks

Qwen3.5-397B-A17B Benchmarks

Benjamin Marie (third-party) benchmarked Qwen3.5-397B-A17B using Unsloth GGUFs on a 750-prompt mixed suite (LiveCodeBench v6, MMLU Pro, GPQA, Math500), reporting both overall accuracy and relative error increase (how much more often the quantized model makes mistakes vs. the original).

Key results (accuracy; change vs. original; relative error increase):

• Original weights: 81.3%

• UD-Q4_K_XL: 80.5% (−0.8 points; +4.3% relative error increase)

• UD-Q3_K_XL: 80.7% (−0.6 points; +3.5% relative error increase)

UD-Q4_K_XL and UD-Q3_K_XL stay extremely close to the original, well under a 1-point accuracy drop on this suite, which Ben insinuates that you can sharply reduce memory footprint (~500 GB less) with little to no practical loss on the tested tasks.

How to choose: Q3 scoring slightly higher than Q4 here is completely plausible as normal run-to-run variance at this scale, so treat Q3 and Q4 as effectively similar quality in this benchmark:

• Pick Q3 if you want the smallest footprint / best memory savings

• Pick Q4 if you want a slightly more conservative option with similar results

All listed quants utilize our dynamic metholodgy. Even UD-IQ2_M uses a the same methodology of dynamic however the conversion process is different to UD-Q2-K-XL where K-XL is usually faster than UD-IQ2_M even though it's bigger, so that is why UD-IQ2_M may perform better than UD-Q2-K-XL.

Official Qwen Benchmarks

Qwen3.5-35B-A3B, 27B and 122B-A10B Benchmarks

You can view further below for benchmarks in table format:

Language

Knowledge

Benchmark	GPT-5-mini 2025-08-07	GPT-OSS-120B	Qwen3-235B-A22B	Qwen3.5-122B-A10B	Qwen3.5-27B	Qwen3.5-35B-A3B
MMLU-Pro	83.7	80.8	84.4	86.7	86.1	85.3
MMLU-Redux	93.7	91.0	93.8	94.0	93.2	93.3
C-Eval	82.2	76.2	92.1	91.9	90.5	90.2
SuperGPQA	58.6	54.6	64.9	67.1	65.6	63.4

Instruction Following

Benchmark	GPT-5-mini 2025-08-07	GPT-OSS-120B	Qwen3-235B-A22B	Qwen3.5-122B-A10B	Qwen3.5-27B	Qwen3.5-35B-A3B
IFEval	93.9	88.9	87.8	93.4	95.0	91.9
IFBench	75.4	69.0	51.7	76.1	76.5	70.2
MultiChallenge	59.0	45.3	50.2	61.5	60.8	60.0

Long Context

Benchmark	GPT-5-mini 2025-08-07	GPT-OSS-120B	Qwen3-235B-A22B	Qwen3.5-122B-A10B	Qwen3.5-27B	Qwen3.5-35B-A3B
AA-LCR	68.0	50.7	60.0	66.9	66.1	58.5
LongBench v2	56.8	48.2	54.8	60.2	60.6	59.0

STEM & Reasoning

Benchmark	GPT-5-mini 2025-08-07	GPT-OSS-120B	Qwen3-235B-A22B	Qwen3.5-122B-A10B	Qwen3.5-27B	Qwen3.5-35B-A3B
HLE w/ CoT	19.4	14.9	18.2	25.3	24.3	22.4
GPQA Diamond	82.8	80.1	81.1	86.6	85.5	84.2
HMMT Feb 25	89.2	90.0	85.1	91.4	92.0	89.0
HMMT Nov 25	84.2	90.0	89.5	90.3	89.8	89.2

Coding

Benchmark	GPT-5-mini 2025-08-07	GPT-OSS-120B	Qwen3-235B-A22B	Qwen3.5-122B-A10B	Qwen3.5-27B	Qwen3.5-35B-A3B
SWE-bench Verified	72.0	62.0	--	72.0	72.4	69.2
Terminal Bench 2	31.9	18.7	--	49.4	41.6	40.5
LiveCodeBench v6	80.5	82.7	75.1	78.9	80.7	74.6
CodeForces	2160	2157	2146	2100	1899	2028
OJBench	40.4	41.5	32.7	39.5	40.1	36.0
FullStackBench en	30.6	58.9	61.1	62.6	60.1	58.1
FullStackBench zh	35.2	60.4	63.1	58.7	57.4	55.0

General Agent

Benchmark	GPT-5-mini 2025-08-07	GPT-OSS-120B	Qwen3-235B-A22B	Qwen3.5-122B-A10B	Qwen3.5-27B	Qwen3.5-35B-A3B
BFCL-V4	55.5	--	54.8	72.2	68.5	67.3
TAU2-Bench	69.8	--	58.5	79.5	79.0	81.2
VITA-Bench	13.9	--	31.6	33.6	41.9	31.9
DeepPlanning	17.9	--	17.1	24.1	22.6	22.8

Search Agent

Benchmark	GPT-5-mini 2025-08-07	GPT-OSS-120B	Qwen3-235B-A22B	Qwen3.5-122B-A10B	Qwen3.5-27B	Qwen3.5-35B-A3B
HLE w/ tool	35.8	19.0	--	47.5	48.5	47.4
Browsecomp	48.1	41.1	--	63.8	61.0	61.0
Browsecomp-zh	49.5	42.9	--	69.9	62.1	69.5
WideSearch	47.2	40.4	--	60.5	61.1	57.1
Seal-0	34.2	45.1	--	44.1	47.2	41.4

Multilingualism

Benchmark	GPT-5-mini 2025-08-07	GPT-OSS-120B	Qwen3-235B-A22B	Qwen3.5-122B-A10B	Qwen3.5-27B	Qwen3.5-35B-A3B
MMMLU	86.2	78.2	83.4	86.7	85.9	85.2
MMLU-ProX	78.5	74.5	77.9	82.2	82.2	81.0
NOVA-63	51.9	51.1	55.4	58.6	58.1	57.1
INCLUDE	81.8	74.0	81.0	82.8	81.6	79.7
Global PIQA	88.5	84.1	85.7	88.4	87.5	86.6
PolyMATH	67.3	54.0	60.1	68.9	71.2	64.4
WMT24++	80.7	74.4	75.8	78.3	77.6	76.3
MAXIFE	85.3	83.7	83.2	87.9	88.0	86.6

Notes (Language)

• CodeForces: evaluated on an internal query set.

• TAU2-Bench: followed official setup except airline domain fixes per Claude Opus 4.5 system card.

• Search Agent: context-folding (256k) with pruning of earlier tool responses after a threshold.

• WideSearch: 256k context window without context management.

• MMLU-ProX: averaged accuracy over 29 languages.

• WMT24++: averaged over 55 languages using XCOMET-XXL.

• MAXIFE: accuracy over English + multilingual original prompts (23 settings).

• -- means not available / not applicable.

Vision Language

STEM and Puzzle

Benchmark	GPT-5-mini 2025-08-07	Claude-Sonnet-4.5	Qwen3-VL-235B-A22B	Qwen3.5-122B-A10B	Qwen3.5-27B	Qwen3.5-35B-A3B
MMMU	79.0	79.6	80.6	83.9	82.3	81.4
MMMU-Pro	67.3	68.4	69.3	76.9	75.0	75.1
MathVision	71.9	71.1	74.6	86.2	86.0	83.9
Mathvista(mini)	79.1	79.8	85.8	87.4	87.8	86.2
DynaMath	81.4	78.8	82.8	85.9	87.7	85.0
ZEROBench	3	4	4	9	10	8
ZEROBench_sub	27.3	26.3	28.4	36.2	36.2	34.1
VlmsAreBlind	75.8	85.5	79.5	96.7	96.9	97.0
BabyVision	20.9 / 34.5	18.6 / 34.5	22.2 / 34.5	40.2 / 34.5	44.6 / 34.8	38.4 / 29.6

General VQA

Benchmark	GPT-5-mini 2025-08-07	Claude-Sonnet-4.5	Qwen3-VL-235B-A22B	Qwen3.5-122B-A10B	Qwen3.5-27B	Qwen3.5-35B-A3B
RealWorldQA	79.0	70.3	81.3	85.1	83.7	84.1
MMStar	74.1	73.8	78.7	82.9	81.0	81.9
MMBenchEN-DEV-v1.1	86.8	88.3	89.7	92.8	92.6	91.5
SimpleVQA	56.8	57.6	61.3	61.7	56.0	58.3
HallusionBench	63.2	59.9	66.7	67.6	70.0	67.9

Text Recognition and Document Understanding

Benchmark	GPT-5-mini 2025-08-07	Claude-Sonnet-4.5	Qwen3-VL-235B-A22B	Qwen3.5-122B-A10B	Qwen3.5-27B	Qwen3.5-35B-A3B
OmniDocBench1.5	77.0	85.8	84.5	89.8	88.9	89.3
CharXiv(RQ)	68.6	67.2	66.1	77.2	79.5	77.5
MMLongBench-Doc	50.3	--	56.2	59.0	60.2	59.5
CC-OCR	70.8	68.1	81.5	81.8	81.0	80.7
AI2D_TEST	88.2	87.0	89.2	93.3	92.9	92.6
OCRBench	821	766	87.5	92.1	89.4	91.0

Spatial Intelligence

Benchmark	GPT-5-mini 2025-08-07	Claude-Sonnet-4.5	Qwen3-VL-235B-A22B	Qwen3.5-122B-A10B	Qwen3.5-27B	Qwen3.5-35B-A3B
ERQA	54.0	45.0	52.5	62.0	60.5	64.8
CountBench	91.0	90.0	93.7	97.0	97.8	97.8
RefCOCO(avg)	--	--	91.1	91.3	90.9	89.2
ODInW13	--	--	43.2	44.5	41.1	42.6
EmbSpatialBench	80.7	71.8	84.3	83.9	84.5	83.1
RefSpatialBench	9.0	2.2	69.9	69.3	67.7	63.5
LingoQA	62.4	12.8	66.8	80.8	82.0	79.2
Hypersim	--	--	11.0	12.7	13.0	13.1
SUNRGBD	--	--	34.9	36.2	35.4	33.4
Nuscene	--	--	13.9	15.4	15.2	14.6

Video Understanding

Benchmark	GPT-5-mini 2025-08-07	Claude-Sonnet-4.5	Qwen3-VL-235B-A22B	Qwen3.5-122B-A10B	Qwen3.5-27B	Qwen3.5-35B-A3B
VideoMME(w sub.)	83.5	81.1	83.8	87.3	87.0	86.6
VideoMME(w/o sub.)	78.9	75.3	79.0	83.9	82.8	82.5
VideoMMMU	82.5	77.6	80.0	82.0	82.3	80.4
MLVU	83.3	72.8	83.8	87.3	85.9	85.6
MVBench	--	--	75.2	76.6	74.6	74.8
LVBench	--	--	63.6	74.4	73.6	71.4
MMVU	69.8	70.6	71.1	74.7	73.3	72.3

Visual Agent

Benchmark	GPT-5-mini 2025-08-07	Claude-Sonnet-4.5	Qwen3-VL-235B-A22B	Qwen3.5-122B-A10B	Qwen3.5-27B	Qwen3.5-35B-A3B
ScreenSpot Pro	--	36.2	62.0	70.40	70.28	68.60
OSWorld-Verified	--	61.4	38.1	58.01	56.15	54.49
AndroidWorld	--	--	63.7	66.4	64.2	71.1

Tool Calling

Benchmark	GPT-5-mini 2025-08-07	Claude-Sonnet-4.5	Qwen3-VL-235B-A22B	Qwen3.5-122B-A10B	Qwen3.5-27B	Qwen3.5-35B-A3B
TIR-Bench	24.6 / 42.5	27.6 / 42.5	29.8 / 42.5	53.2 / 42.5	59.8 / 42.3	55.5 / 38.0
V*	71.7 / 90.1	58.6 / 89.0	85.9 / 89.5	93.2 / 90.1	93.7 / 89.0	92.7 / 89.5

Medical VQA

Benchmark	GPT-5-mini 2025-08-07	Claude-Sonnet-4.5	Qwen3-VL-235B-A22B	Qwen3.5-122B-A10B	Qwen3.5-27B	Qwen3.5-35B-A3B
SLAKE	70.5	73.6	54.7	81.6	80.0	78.7
PMC-VQA	36.3	55.9	41.2	63.3	62.4	62.0
MedXpertQA-MM	34.4	54.0	47.6	67.3	62.4	61.4

Notes (Vision Language)

• MathVision: Qwen score uses a fixed prompt; other models use the higher of runs with/without \boxed{} formatting.

• BabyVision: scores are reported as “with CI / without CI”.

• TIR-Bench and V*: scores are reported as “with CI / without CI”.

• -- means not available / not applicable.

Qwen3.5-397B-A17B Benchmarks

You can view further below for Qwen3.5-397B-A17B benchmarks in table format:

Language Benchmarks

Knowledge

Benchmark	GPT5.2	Claude 4.5 Opus	Gemini-3 Pro	Qwen3-Max-Thinking	K2.5-1T-A32B	Qwen3.5-397B-A17B
MMLU-Pro	87.4	89.5	89.8	85.7	87.1	87.8
MMLU-Redux	95.0	95.6	95.9	92.8	94.5	94.9
SuperGPQA	67.9	70.6	74.0	67.3	69.2	70.4
C-Eval	90.5	92.2	93.4	93.7	94.0	93.0

Instruction Following

Benchmark	GPT5.2	Claude 4.5 Opus	Gemini-3 Pro	Qwen3-Max-Thinking	K2.5-1T-A32B	Qwen3.5-397B-A17B
IFEval	94.8	90.9	93.5	93.4	93.9	92.6
IFBench	75.4	58.0	70.4	70.9	70.2	76.5
MultiChallenge	57.9	54.2	64.2	63.3	62.7	67.6

Long Context

Benchmark	GPT5.2	Claude 4.5 Opus	Gemini-3 Pro	Qwen3-Max-Thinking	K2.5-1T-A32B	Qwen3.5-397B-A17B
AA-LCR	72.7	74.0	70.7	68.7	70.0	68.7
LongBench v2	54.5	64.4	68.2	60.6	61.0	63.2

STEM

Benchmark	GPT5.2	Claude 4.5 Opus	Gemini-3 Pro	Qwen3-Max-Thinking	K2.5-1T-A32B	Qwen3.5-397B-A17B
GPQA	92.4	87.0	91.9	87.4	87.6	88.4
HLE	35.5	30.8	37.5	30.2	30.1	28.7
HLE-Verified¹	43.3	38.8	48	37.6	--	37.6

Reasoning

Benchmark	GPT5.2	Claude 4.5 Opus	Gemini-3 Pro	Qwen3-Max-Thinking	K2.5-1T-A32B	Qwen3.5-397B-A17B
LiveCodeBench v6	87.7	84.8	90.7	85.9	85.0	83.6
HMMT Feb 25	99.4	92.9	97.3	98.0	95.4	94.8
HMMT Nov 25	100	93.3	93.3	94.7	91.1	92.7
IMOAnswerBench	86.3	84.0	83.3	83.9	81.8	80.9
AIME26	96.7	93.3	90.6	93.3	93.3	91.3

General Agent

Benchmark	GPT5.2	Claude 4.5 Opus	Gemini-3 Pro	Qwen3-Max-Thinking	K2.5-1T-A32B	Qwen3.5-397B-A17B
BFCL-V4	63.1	77.5	72.5	67.7	68.3	72.9
TAU2-Bench	87.1	91.6	85.4	84.6	77.0	86.7
VITA-Bench	38.2	56.3	51.6	40.9	41.9	49.7
DeepPlanning	44.6	33.9	23.3	28.7	14.5	34.3
Tool Decathlon	43.8	43.5	36.4	18.8	27.8	38.3
MCP-Mark	57.5	42.3	53.9	33.5	29.5	46.1

Search Agent³

Benchmark	GPT5.2	Claude 4.5 Opus	Gemini-3 Pro	Qwen3-Max-Thinking	K2.5-1T-A32B	Qwen3.5-397B-A17B
HLE w/ tool	45.5	43.4	45.8	49.8	50.2	48.3
BrowseComp	65.8	67.8	59.2	53.9	--/74.9	69.0/78.6
BrowseComp-zh	76.1	62.4	66.8	60.9	--	70.3
WideSearch	76.8	76.4	68.0	57.9	72.7	74.0
Seal-0	45.0	47.7	45.5	46.9	57.4	46.9

Multilingualism

Benchmark	GPT5.2	Claude 4.5 Opus	Gemini-3 Pro	Qwen3-Max-Thinking	K2.5-1T-A32B	Qwen3.5-397B-A17B
MMMLU	89.5	90.1	90.6	84.4	86.0	88.5
MMLU-ProX	83.7	85.7	87.7	78.5	82.3	84.7
NOVA-63	54.6	56.7	56.7	54.2	56.0	59.1
INCLUDE	87.5	86.2	90.5	82.3	83.3	85.6
Global PIQA	90.9	91.6	93.2	86.0	89.3	89.8
PolyMATH	62.5	79.0	81.6	64.7	43.1	73.3
WMT24++	78.8	79.7	80.7	77.6	77.6	78.9
MAXIFE	88.4	79.2	87.5	84.0	72.8	88.2

Coding Agent

Benchmark	GPT5.2	Claude 4.5 Opus	Gemini-3 Pro	Qwen3-Max-Thinking	K2.5-1T-A32B	Qwen3.5-397B-A17B
SWE-bench Verified	80.0	80.9	76.2	75.3	76.8	76.4
SWE-bench Multilingual	72.0	77.5	65.0	66.7	73.0	72.0
SecCodeBench	68.7	68.6	62.4	57.5	61.3	68.3
Terminal Bench 2	54.0	59.3	54.2	22.5	50.8	52.5

Notes

• HLE-Verified: a verified and revised version of Humanity’s Last Exam (HLE), accompanied by a transparent, component-wise verification protocol and a fine-grained error taxonomy. We open-source the dataset at https://huggingface.co/datasets/skylenage/HLE-Verified.

• TAU2-Bench：we follow the official setup except for the airline domain, where all models are evaluated by applying the fixes proposed in the Claude Opus 4.5 system card.

• MCPMark: GitHub MCP server uses v0.30.3 from api.githubcopilot.com; Playwright tool responses are truncated at 32k tokens.

• Seach Agent: most Search Agents built on our model adopt a simple context-folding strategy(256k): once the cumulative Tool Response length reaches a preset threshold, earlier Tool Responses are pruned from the history to keep the context within limits.

• BrowseComp: we tested two strategies, simple context-folding achieved a score of 69.0, while using the same discard-all strategy as DeepSeek-V3.2 and Kimi K2.5 achieved 78.6.

• WideSearch: we use a 256k context window without any context management.

• MMLU-ProX: we report the averaged accuracy on 29 languages.

• WMT24++: a harder subset of WMT24 after difficulty labeling and rebalancing; we report the averaged scores on 55 languages using XCOMET-XXL.

• MAXIFE: we report the accuracy on English + multilingual original prompts (totally 23 settings).

• Empty cells (--) indicate scores not yet available or not applicable.

Vision Language Benchmarks

STEM and Puzzle

Benchmark	GPT5.2	Claude 4.5 Opus	Gemini-3 Pro	Qwen3-VL-235B-A22B	K2.5-1T-A32B	Qwen3.5-397B-A17B
MMMU	86.7	80.7	87.2	80.6	84.3	85.0
MMMU-Pro	79.5	70.6	81.0	69.3	78.5	79.0
MathVision	83.0	74.3	86.6	74.6	84.2	88.6
Mathvista(mini)	83.1	80.0	87.9	85.8	90.1	90.3
We-Math	79.0	70.0	86.9	74.8	84.7	87.9
DynaMath	86.8	79.7	85.1	82.8	84.4	86.3
ZEROBench	9	3	10	4	9	12
ZEROBench_sub	33.2	28.4	39.0	28.4	33.5	41.0
BabyVision	34.4	14.2	49.7	22.2	36.5	52.3/43.3

General VQA

Benchmark	GPT5.2	Claude 4.5 Opus	Gemini-3 Pro	Qwen3-VL-235B-A22B	K2.5-1T-A32B	Qwen3.5-397B-A17B
RealWorldQA	83.3	77.0	83.3	81.3	81.0	83.9
MMStar	77.1	73.2	83.1	78.7	80.5	83.8
HallusionBench	65.2	64.1	68.6	66.7	69.8	71.4
MMBench (EN-DEV-v1.1)	88.2	89.2	93.7	89.7	94.2	93.7
SimpleVQA	55.8	65.7	73.2	61.3	71.2	67.1

Text Recognition and Document Understanding

Benchmark	GPT5.2	Claude 4.5 Opus	Gemini-3 Pro	Qwen3-VL-235B-A22B	K2.5-1T-A32B	Qwen3.5-397B-A17B
OmniDocBench1.5	85.7	87.7	88.5	84.5	88.8	90.8
CharXiv(RQ)	82.1	68.5	81.4	66.1	77.5	80.8
MMLongBench-Doc	--	61.9	60.5	56.2	58.5	61.5
CC-OCR	70.3	76.9	79.0	81.5	79.7	82.0
AI2D_TEST	92.2	87.7	94.1	89.2	90.8	93.9
OCRBench	80.7	85.8	90.4	87.5	92.3	93.1

Spatial Intelligence

Benchmark	GPT5.2	Claude 4.5 Opus	Gemini-3 Pro	Qwen3-VL-235B-A22B	K2.5-1T-A32B	Qwen3.5-397B-A17B
ERQA	59.8	46.8	70.5	52.5	--	67.5
CountBench	91.9	90.6	97.3	93.7	94.1	97.2
RefCOCO(avg)	--	--	84.1	91.1	87.8	92.3
ODInW13	--	--	46.3	43.2	--	47.0
EmbSpatialBench	81.3	75.7	61.2	84.3	77.4	84.5
RefSpatialBench	--	--	65.5	69.9	--	73.6
LingoQA	68.8	78.8	72.8	66.8	68.2	81.6
V*	75.9	67.0	88.0	85.9	77.0	95.8/91.1
Hypersim	--	--	--	11.0	--	12.5
SUNRGBD	--	--	--	34.9	--	38.3
Nuscene	--	--	--	13.9	--	16.0

Video Understanding

Benchmark	GPT5.2	Claude 4.5 Opus	Gemini-3 Pro	Qwen3-VL-235B-A22B	K2.5-1T-A32B	Qwen3.5-397B-A17B
VideoMME (w sub.)	86	77.6	88.4	83.8	87.4	87.5
VideoMME (w/o sub.)	85.8	81.4	87.7	79.0	83.2	83.7
VideoMMMU	85.9	84.4	87.6	80.0	86.6	84.7
MLVU (M-Avg)	85.6	81.7	83.0	83.8	85.0	86.7
MVBench	78.1	67.2	74.1	75.2	73.5	77.6
LVBench	73.7	57.3	76.2	63.6	75.9	75.5
MMVU	80.8	77.3	77.5	71.1	80.4	75.4

Visual Agent

Benchmark	GPT5.2	Claude 4.5 Opus	Gemini-3 Pro	Qwen3-VL-235B-A22B	K2.5-1T-A32B	Qwen3.5-397B-A17B
ScreenSpot Pro	--	45.7	72.7	62.0	--	65.6
OSWorld-Verified	38.2	66.3	--	38.1	63.3	62.2
AndroidWorld	--	--	--	63.7	--	66.8

Medical

Benchmark	GPT5.2	Claude 4.5 Opus	Gemini-3 Pro	Qwen3-VL-235B-A22B	K2.5-1T-A32B	Qwen3.5-397B-A17B
VQA-RAD	69.8	65.6	74.5	65.4	79.9	76.3
SLAKE	76.9	76.4	81.3	54.7	81.6	79.9
OM-VQA	72.9	75.5	80.3	65.4	87.4	85.1
PMC-VQA	58.9	59.9	62.3	41.2	63.3	64.2
MedXpertQA-MM	73.3	63.6	76.0	47.6	65.3	70.0

Notes

• MathVision：our model’s score is evaluated using a fixed prompt, e.g., “Please reason step by step, and put your final answer within \boxed{}.” For other models, we report the higher score between runs with and without the \boxed{} formatting.

• BabyVision: our model’s score is reported with CI (Code Interpreter) enabled; without CI, the result is 43.3.

• V*: our model’s score is reported with CI (Code Interpreter) enabled; without CI, the result is 91.1.

• Empty cells (--) indicate scores not yet available or not applicable.