QwenReleased Aug 2026Apache 2.0
Qwen3.8 27B scores 69.5% overall (4 of 5 tasks) on Roboflow's Vision Evals (November 12, 2026 snapshot), #28 of 69 models (Gemini 4 Carbon leads at 89.4%).
Its best task is object detection (65.7%, #18 of 69) and its weakest is counting (64.9%, #37 of 69). It is an open-weight model from Qwen under the Apache 2.0 license, and free for commercial use.
Qwen3.8 27BField median
Ranks out of 69 models
Drag and drop an image here, or click to browse
Model settings
Thinking level
Max output tokens
Default 65,536 · max 65,536
Sign in to adjust thinking and output length per run.
Results appear here. Add an image or pick an example to run Qwen3.8 27B.
Vision Evals is Roboflow's ground-truth benchmark: every model runs the same real-world samples across five vision tasks, and answers are scored against ground truth.
Evals updated November 12, 2026Pricing updated November 13, 2026
Best showing
Weak spot
Below the field median.
Qwen3.8 27BField median
Ranks out of 69 models
| Task | Score | Field (0 to 100) | Rank | Cost / sample | Speed |
|---|---|---|---|---|---|
| Object Detection (low) | 65.7% ±1.0, Mean of 3 runs, range 64.6 to 66.5 | #18 of 69 | $0 | 33.43s | |
| Object Detection (high) | 66.1% ±1.4, Mean of 3 runs, range 64.9 to 67.8 | #20 of 37 | $0 | 39.37s | |
| Counting (low) | 64.9% ±4.1, Mean of 3 runs, range 60.8 to 68.9 | #37 of 69 | $0 | 9.16s | |
| Counting (high) | 68.0% ±2.0, Mean of 3 runs, range 66.2 to 70.3 | #27 of 37 | $0 | 32.28s | |
| Identification (low) | 85.4% ±4.7, Mean of 3 runs, range 81.3 to 90.6 | #34 of 69 | $0 | 2.95s | |
| Identification (high) | 87.5% ±3.1, Mean of 3 runs, range 84.4 to 90.6 | #22 of 37 | $0 | 7.53s | |
| Reasoning (low) | 62.0% ±2.0, Mean of 3 runs, range 60.3 to 64.2 | #32 of 69 | $0 | 10.75s | |
| Reasoning (high) | 66.0% ±0.7, Mean of 3 runs, range 65.6 to 66.9 | #35 of 56 | $0 | 42.86s |
Overall benchmark score against estimated cost per sample, on a log scale. Upper-left is the sweet spot: high quality at low cost.
68 of 69 models plotted (the rest have no measured figure for this axis) · scores and efficiency pooled across all five tasks at low effort · Qwen3.8 27B highlighted
Qwen3.8 27B scores are the mean of 3 runs per task at both low and high effort · Methodology
View all Vision Evals →3 quantizations of Qwen3.8 27B, served with vLLM from the published weights and scored on the same tasks as the hosted models. Expand a row for the GPUs it was measured on.
Rows are ordered by overall score. Every score is the mean of three runs per task under the benchmark protocol (a row marked single run has one), and the gap between quantizations is usually inside the run-to-run range, so read the order as a guide rather than a verdict. Self-hosted rows run with thinking on, the same setting as the hosted frontier models; some hosted open-weight rows still run without thinking, so a self-hosted quant can score above its own hosted API. Quantization still costs a little precision.
Qwen3.8-27B is a dense vision-language model of roughly 27.78 billion parameters from Alibaba's Qwen team, built on the architectural foundation established by the Qwen3.5 generation. It takes interleaved text, image, and video input through an integrated vision encoder and produces text, covering document and chart understanding, visual question answering, front-end code generation from visual references, and agentic computer-use workflows. The decoder is a hybrid stack of 64 layers that repeats a pattern of three Gated DeltaNet linear-attention blocks, each followed by a feed-forward block, then one grouped-query full-attention block, so only a quarter of the layers maintain a conventional key-value cache. Native context length is 262,144 tokens.
Qwen3.8 27B costs $0.150 per 1M input tokens and $1.88 per 1M output tokens.
Pricing updated Nov 13, 2026
Qwen3.8 27B runs as a hosted REST endpoint through Roboflow Workflows. Pick a task, then hand the prompt to your coding agent or copy the code. Deploying the workflow into a free Roboflow workspace replaces the your-workspace and YOUR_API_KEY placeholders with your own.
Add the Roboflow MCP server
claude mcp add --transport http roboflow https://mcp.roboflow.com/mcp
Run /mcp and authorize Roboflow in your browser when the OAuth flow opens.
Start a new Claude Code session so the MCP loads, then paste the prompt below (it works the same in any agent).
Deploy this workflow to your Roboflow workspace to use it.
Integrate the Roboflow "Qwen3.8 27B" workflow into my app.
- Endpoint: POST https://serverless.roboflow.com/<your-workspace>/workflows/qwen3-8-27b-captioning
- Auth: send my Roboflow API key as `api_key` in the request body, read from the ROBOFLOW_API_KEY env var (never hardcode).
- Body: { "api_key": ..., "inputs": { `image`: { type: "url" | "base64", value } } }.
- Billing: this workflow needs no provider API key — inference runs on my Roboflow credits. A BYO provider key can be added to the model step in the Roboflow workflow editor later.
With the Roboflow MCP connected, call `workflows_get` on "qwen3-8-27b-captioning" to read the exact input schema (the source of truth), then `workflows_run` on a sample image to confirm the output shape before writing code (the MCP is authenticated, so this needs no key). Without the MCP, use the contract above.
Before running the app, set up these keys so it does not error at runtime:
- `ROBOFLOW_API_KEY` (sent as `api_key`) from https://app.roboflow.com/settings/api
Create a .gitignore'd .env with these variables, using placeholder values for any I haven't given you. Then pause and tell me directly, in your reply: the full path to the .env file, exactly which keys I need to paste in, and the link to get each one. Wait for me to confirm I've added them before you run anything. Do not run the app until I confirm.
Then add the integration to my codebase: match my project's language, framework, and conventions; read every key from environment variables (never hardcode); add basic error handling; and include a small runnable example. If you can't tell what language my project uses, ask me.pip install inference-sdkDeploy this workflow to your Roboflow workspace to use it.
# Inference runs on your Roboflow credits — no provider API key needed. To bill your own provider account instead, add an api_key to the model step in the Roboflow workflow editor.
# 1. Import the library
from inference_sdk import InferenceHTTPClient
# 2. Connect to your workflow
client = InferenceHTTPClient(
api_url="https://serverless.roboflow.com",
api_key="YOUR_API_KEY"
)
# 3. Run your workflow on an image
result = client.run_workflow(
workspace_name="your-workspace",
workflow_id="qwen3-8-27b-captioning",
images={
"image": "YOUR_IMAGE.jpg" # Path to your image file
},
use_cache=True # cache workflow definition for 15 minutes
)
# 4. Get your results
print(result)Deploy this workflow to your Roboflow workspace to use it.
// Inference runs on your Roboflow credits — no provider API key needed. To bill your own provider account instead, add an api_key to the model step in the Roboflow workflow editor.
const response = await fetch('https://serverless.roboflow.com/your-workspace/workflows/qwen3-8-27b-captioning', {
method: 'POST',
headers: {
'Content-Type': 'application/json'
},
body: JSON.stringify({
api_key: 'YOUR_API_KEY',
inputs: {
"image": {"type": "url", "value": "IMAGE_URL"}
}
})
});
const result = await response.json();
console.log(result);Deploy this workflow to your Roboflow workspace to use it.
# Inference runs on your Roboflow credits — no provider API key needed. To bill your own provider account instead, add an api_key to the model step in the Roboflow workflow editor.
curl --location 'https://serverless.roboflow.com/your-workspace/workflows/qwen3-8-27b-captioning' \
--header 'Content-Type: application/json' \
--data '{
"api_key": "YOUR_API_KEY",
"inputs": {
"image": {"type": "url", "value": "IMAGE_URL"}
}
}'Add the Roboflow MCP server
claude mcp add --transport http roboflow https://mcp.roboflow.com/mcp
Run /mcp and authorize Roboflow in your browser when the OAuth flow opens.
Start a new Claude Code session so the MCP loads, then paste the prompt below (it works the same in any agent).
Deploy this workflow to your Roboflow workspace to use it.
Integrate the Roboflow "Qwen3.8 27B" workflow into my app.
- Endpoint: POST https://serverless.roboflow.com/<your-workspace>/workflows/qwen3-8-27b-open-prompt
- Auth: send my Roboflow API key as `api_key` in the request body, read from the ROBOFLOW_API_KEY env var (never hardcode).
- Body: { "api_key": ..., "inputs": { `image`: { type: "url" | "base64", value }, `prompt`: text } }.
- Billing: this workflow needs no provider API key — inference runs on my Roboflow credits. A BYO provider key can be added to the model step in the Roboflow workflow editor later.
With the Roboflow MCP connected, call `workflows_get` on "qwen3-8-27b-open-prompt" to read the exact input schema (the source of truth), then `workflows_run` on a sample image to confirm the output shape before writing code (the MCP is authenticated, so this needs no key). Without the MCP, use the contract above.
Before running the app, set up these keys so it does not error at runtime:
- `ROBOFLOW_API_KEY` (sent as `api_key`) from https://app.roboflow.com/settings/api
Create a .gitignore'd .env with these variables, using placeholder values for any I haven't given you. Then pause and tell me directly, in your reply: the full path to the .env file, exactly which keys I need to paste in, and the link to get each one. Wait for me to confirm I've added them before you run anything. Do not run the app until I confirm.
Then add the integration to my codebase: match my project's language, framework, and conventions; read every key from environment variables (never hardcode); add basic error handling; and include a small runnable example. If you can't tell what language my project uses, ask me.pip install inference-sdkDeploy this workflow to your Roboflow workspace to use it.
# Inference runs on your Roboflow credits — no provider API key needed. To bill your own provider account instead, add an api_key to the model step in the Roboflow workflow editor.
# 1. Import the library
from inference_sdk import InferenceHTTPClient
# 2. Connect to your workflow
client = InferenceHTTPClient(
api_url="https://serverless.roboflow.com",
api_key="YOUR_API_KEY"
)
# 3. Run your workflow on an image
result = client.run_workflow(
workspace_name="your-workspace",
workflow_id="qwen3-8-27b-open-prompt",
images={
"image": "YOUR_IMAGE.jpg" # Path to your image file
},
parameters={
"prompt": "Describe what you see in the image"
},
use_cache=True # cache workflow definition for 15 minutes
)
# 4. Get your results
print(result)Deploy this workflow to your Roboflow workspace to use it.
// Inference runs on your Roboflow credits — no provider API key needed. To bill your own provider account instead, add an api_key to the model step in the Roboflow workflow editor.
const response = await fetch('https://serverless.roboflow.com/your-workspace/workflows/qwen3-8-27b-open-prompt', {
method: 'POST',
headers: {
'Content-Type': 'application/json'
},
body: JSON.stringify({
api_key: 'YOUR_API_KEY',
inputs: {
"image": {"type": "url", "value": "IMAGE_URL"},
"prompt": "Describe what you see in the image"
}
})
});
const result = await response.json();
console.log(result);Deploy this workflow to your Roboflow workspace to use it.
# Inference runs on your Roboflow credits — no provider API key needed. To bill your own provider account instead, add an api_key to the model step in the Roboflow workflow editor.
curl --location 'https://serverless.roboflow.com/your-workspace/workflows/qwen3-8-27b-open-prompt' \
--header 'Content-Type: application/json' \
--data '{
"api_key": "YOUR_API_KEY",
"inputs": {
"image": {"type": "url", "value": "IMAGE_URL"},
"prompt": "Describe what you see in the image"
}
}'Add the Roboflow MCP server
claude mcp add --transport http roboflow https://mcp.roboflow.com/mcp
Run /mcp and authorize Roboflow in your browser when the OAuth flow opens.
Start a new Claude Code session so the MCP loads, then paste the prompt below (it works the same in any agent).
Deploy this workflow to your Roboflow workspace to use it.
Integrate the Roboflow "Qwen3.8 27B" workflow into my app.
- Endpoint: POST https://serverless.roboflow.com/<your-workspace>/workflows/qwen3-8-27b-classification
- Auth: send my Roboflow API key as `api_key` in the request body, read from the ROBOFLOW_API_KEY env var (never hardcode).
- Body: { "api_key": ..., "inputs": { `image`: { type: "url" | "base64", value }, `classes`: string array } }.
- Billing: this workflow needs no provider API key — inference runs on my Roboflow credits. A BYO provider key can be added to the model step in the Roboflow workflow editor later.
With the Roboflow MCP connected, call `workflows_get` on "qwen3-8-27b-classification" to read the exact input schema (the source of truth), then `workflows_run` on a sample image to confirm the output shape before writing code (the MCP is authenticated, so this needs no key). Without the MCP, use the contract above.
Before running the app, set up these keys so it does not error at runtime:
- `ROBOFLOW_API_KEY` (sent as `api_key`) from https://app.roboflow.com/settings/api
Create a .gitignore'd .env with these variables, using placeholder values for any I haven't given you. Then pause and tell me directly, in your reply: the full path to the .env file, exactly which keys I need to paste in, and the link to get each one. Wait for me to confirm I've added them before you run anything. Do not run the app until I confirm.
Then add the integration to my codebase: match my project's language, framework, and conventions; read every key from environment variables (never hardcode); add basic error handling; and include a small runnable example. If you can't tell what language my project uses, ask me.pip install inference-sdkDeploy this workflow to your Roboflow workspace to use it.
# Inference runs on your Roboflow credits — no provider API key needed. To bill your own provider account instead, add an api_key to the model step in the Roboflow workflow editor.
# 1. Import the library
from inference_sdk import InferenceHTTPClient
# 2. Connect to your workflow
client = InferenceHTTPClient(
api_url="https://serverless.roboflow.com",
api_key="YOUR_API_KEY"
)
# 3. Run your workflow on an image
result = client.run_workflow(
workspace_name="your-workspace",
workflow_id="qwen3-8-27b-classification",
images={
"image": "YOUR_IMAGE.jpg" # Path to your image file
},
parameters={
"classes": ["class1", "class2", "class3"]
},
use_cache=True # cache workflow definition for 15 minutes
)
# 4. Get your results
print(result)Deploy this workflow to your Roboflow workspace to use it.
// Inference runs on your Roboflow credits — no provider API key needed. To bill your own provider account instead, add an api_key to the model step in the Roboflow workflow editor.
const response = await fetch('https://serverless.roboflow.com/your-workspace/workflows/qwen3-8-27b-classification', {
method: 'POST',
headers: {
'Content-Type': 'application/json'
},
body: JSON.stringify({
api_key: 'YOUR_API_KEY',
inputs: {
"image": {"type": "url", "value": "IMAGE_URL"},
"classes": ["class1", "class2", "class3"]
}
})
});
const result = await response.json();
console.log(result);Deploy this workflow to your Roboflow workspace to use it.
# Inference runs on your Roboflow credits — no provider API key needed. To bill your own provider account instead, add an api_key to the model step in the Roboflow workflow editor.
curl --location 'https://serverless.roboflow.com/your-workspace/workflows/qwen3-8-27b-classification' \
--header 'Content-Type: application/json' \
--data '{
"api_key": "YOUR_API_KEY",
"inputs": {
"image": {"type": "url", "value": "IMAGE_URL"},
"classes": ["class1", "class2", "class3"]
}
}'Add the Roboflow MCP server
claude mcp add --transport http roboflow https://mcp.roboflow.com/mcp
Run /mcp and authorize Roboflow in your browser when the OAuth flow opens.
Start a new Claude Code session so the MCP loads, then paste the prompt below (it works the same in any agent).
Deploy this workflow to your Roboflow workspace to use it.
Integrate the Roboflow "Qwen3.8 27B" workflow into my app.
- Endpoint: POST https://serverless.roboflow.com/<your-workspace>/workflows/qwen3-8-27b-object-detection
- Auth: send my Roboflow API key as `api_key` in the request body, read from the ROBOFLOW_API_KEY env var (never hardcode).
- Body: { "api_key": ..., "inputs": { `image`: { type: "url" | "base64", value }, `classes`: string array } }.
- Billing: this workflow needs no provider API key — inference runs on my Roboflow credits. A BYO provider key can be added to the model step in the Roboflow workflow editor later.
With the Roboflow MCP connected, call `workflows_get` on "qwen3-8-27b-object-detection" to read the exact input schema (the source of truth), then `workflows_run` on a sample image to confirm the output shape before writing code (the MCP is authenticated, so this needs no key). Without the MCP, use the contract above.
Before running the app, set up these keys so it does not error at runtime:
- `ROBOFLOW_API_KEY` (sent as `api_key`) from https://app.roboflow.com/settings/api
Create a .gitignore'd .env with these variables, using placeholder values for any I haven't given you. Then pause and tell me directly, in your reply: the full path to the .env file, exactly which keys I need to paste in, and the link to get each one. Wait for me to confirm I've added them before you run anything. Do not run the app until I confirm.
Then add the integration to my codebase: match my project's language, framework, and conventions; read every key from environment variables (never hardcode); add basic error handling; and include a small runnable example. If you can't tell what language my project uses, ask me.pip install inference-sdkDeploy this workflow to your Roboflow workspace to use it.
# Inference runs on your Roboflow credits — no provider API key needed. To bill your own provider account instead, add an api_key to the model step in the Roboflow workflow editor.
# 1. Import the library
from inference_sdk import InferenceHTTPClient
# 2. Connect to your workflow
client = InferenceHTTPClient(
api_url="https://serverless.roboflow.com",
api_key="YOUR_API_KEY"
)
# 3. Run your workflow on an image
result = client.run_workflow(
workspace_name="your-workspace",
workflow_id="qwen3-8-27b-object-detection",
images={
"image": "YOUR_IMAGE.jpg" # Path to your image file
},
parameters={
"classes": ["class1", "class2", "class3"]
},
use_cache=True # cache workflow definition for 15 minutes
)
# 4. Get your results
print(result)Deploy this workflow to your Roboflow workspace to use it.
// Inference runs on your Roboflow credits — no provider API key needed. To bill your own provider account instead, add an api_key to the model step in the Roboflow workflow editor.
const response = await fetch('https://serverless.roboflow.com/your-workspace/workflows/qwen3-8-27b-object-detection', {
method: 'POST',
headers: {
'Content-Type': 'application/json'
},
body: JSON.stringify({
api_key: 'YOUR_API_KEY',
inputs: {
"image": {"type": "url", "value": "IMAGE_URL"},
"classes": ["class1", "class2", "class3"]
}
})
});
const result = await response.json();
console.log(result);Deploy this workflow to your Roboflow workspace to use it.
# Inference runs on your Roboflow credits — no provider API key needed. To bill your own provider account instead, add an api_key to the model step in the Roboflow workflow editor.
curl --location 'https://serverless.roboflow.com/your-workspace/workflows/qwen3-8-27b-object-detection' \
--header 'Content-Type: application/json' \
--data '{
"api_key": "YOUR_API_KEY",
"inputs": {
"image": {"type": "url", "value": "IMAGE_URL"},
"classes": ["class1", "class2", "class3"]
}
}'Add the Roboflow MCP server
claude mcp add --transport http roboflow https://mcp.roboflow.com/mcp
Run /mcp and authorize Roboflow in your browser when the OAuth flow opens.
Start a new Claude Code session so the MCP loads, then paste the prompt below (it works the same in any agent).
Deploy this workflow to your Roboflow workspace to use it.
Integrate the Roboflow "Qwen3.8 27B" workflow into my app.
- Endpoint: POST https://serverless.roboflow.com/<your-workspace>/workflows/qwen3-8-27b-ocr
- Auth: send my Roboflow API key as `api_key` in the request body, read from the ROBOFLOW_API_KEY env var (never hardcode).
- Body: { "api_key": ..., "inputs": { `image`: { type: "url" | "base64", value } } }.
- Billing: this workflow needs no provider API key — inference runs on my Roboflow credits. A BYO provider key can be added to the model step in the Roboflow workflow editor later.
With the Roboflow MCP connected, call `workflows_get` on "qwen3-8-27b-ocr" to read the exact input schema (the source of truth), then `workflows_run` on a sample image to confirm the output shape before writing code (the MCP is authenticated, so this needs no key). Without the MCP, use the contract above.
Before running the app, set up these keys so it does not error at runtime:
- `ROBOFLOW_API_KEY` (sent as `api_key`) from https://app.roboflow.com/settings/api
Create a .gitignore'd .env with these variables, using placeholder values for any I haven't given you. Then pause and tell me directly, in your reply: the full path to the .env file, exactly which keys I need to paste in, and the link to get each one. Wait for me to confirm I've added them before you run anything. Do not run the app until I confirm.
Then add the integration to my codebase: match my project's language, framework, and conventions; read every key from environment variables (never hardcode); add basic error handling; and include a small runnable example. If you can't tell what language my project uses, ask me.pip install inference-sdkDeploy this workflow to your Roboflow workspace to use it.
# Inference runs on your Roboflow credits — no provider API key needed. To bill your own provider account instead, add an api_key to the model step in the Roboflow workflow editor.
# 1. Import the library
from inference_sdk import InferenceHTTPClient
# 2. Connect to your workflow
client = InferenceHTTPClient(
api_url="https://serverless.roboflow.com",
api_key="YOUR_API_KEY"
)
# 3. Run your workflow on an image
result = client.run_workflow(
workspace_name="your-workspace",
workflow_id="qwen3-8-27b-ocr",
images={
"image": "YOUR_IMAGE.jpg" # Path to your image file
},
use_cache=True # cache workflow definition for 15 minutes
)
# 4. Get your results
print(result)Deploy this workflow to your Roboflow workspace to use it.
// Inference runs on your Roboflow credits — no provider API key needed. To bill your own provider account instead, add an api_key to the model step in the Roboflow workflow editor.
const response = await fetch('https://serverless.roboflow.com/your-workspace/workflows/qwen3-8-27b-ocr', {
method: 'POST',
headers: {
'Content-Type': 'application/json'
},
body: JSON.stringify({
api_key: 'YOUR_API_KEY',
inputs: {
"image": {"type": "url", "value": "IMAGE_URL"}
}
})
});
const result = await response.json();
console.log(result);Deploy this workflow to your Roboflow workspace to use it.
# Inference runs on your Roboflow credits — no provider API key needed. To bill your own provider account instead, add an api_key to the model step in the Roboflow workflow editor.
curl --location 'https://serverless.roboflow.com/your-workspace/workflows/qwen3-8-27b-ocr' \
--header 'Content-Type: application/json' \
--data '{
"api_key": "YOUR_API_KEY",
"inputs": {
"image": {"type": "url", "value": "IMAGE_URL"}
}
}'Qwen3.8 27B is released under the Apache 2.0 license, so it's commercially usable out of the box: you can ship it in closed-source, commercial products, including self-hosted deployments, without paying a license fee or open-sourcing your code. The Qwen3.8 27B license is permissive, so no separate commercial license is required.
Apache-2.0 grants an express patent license that terminates if you bring a patent claim over the work, and it disclaims warranties. Validate Qwen3.8 27B on your own data before you depend on it in production.
Read the full Apache 2.0 license ↗This is the straightforward case: a permissive license is the best technical solution and you are free to deploy Qwen3.8 27B commercially without open-sourcing your own code.
Do not hesitate to reach out with questions for your commercial project. Our team will help you start solving business problems on the first call. See Roboflow commercial licensing for the models included in each plan.
Talk to salesThis model is released under the Apache License 2.0, a permissive open-source license that allows commercial use, modification, distribution, and patent use.
Yes. Under the terms of the Apache 2.0 license, you can freely use this model for commercial purposes, including in proprietary products. You must retain the copyright notice and disclaimers when redistributing.
License information is provided as a guide and is not legal advice.
Usage
Past 30 DaysOther models worth comparing for similar use cases.
Yes. Qwen3.8 27B accepts image input and handles OCR, object counting, identification, visual reasoning, and object detection. On Roboflow's Vision Evals its strongest task is Object Detection at 65.7% (#18 of 69 at low effort). You can test it on your own image in the demo above.
Not its strength. On Vision Evals, Qwen3.8 27B scores 65.7% mAP@50 on object detection (#18 of 69 at low effort) and 64.9% judge-graded accuracy on object counting. For production counting or precise localization, pairing it with a specialized detector like RF-DETR or your own trained model in a Roboflow Workflow is usually more reliable: detect the objects, then count the detections.
On our benchmark's task mix, Qwen3.8 27B averages $0.0020 per sample at $0.15 per 1M input and $1.88 per 1M output tokens (#14 of 69 on cost), with an average speed of 18.0s per sample across the benchmark. Actual cost depends on your images and prompts.
On the overall Vision Evals ranking, Qwen3.8 27B sits #28 of 69 at 69.5%, just behind Claude Haiku 5.5 (69.6%) and just ahead of Muse Spark Open (69.4%). See the full side-by-side: Qwen3.8 27B vs Claude Haiku 5.5.