Qwen · Open weights
Qwen 3.8 27B Kimiko
Qwen 3.8 27B Kimiko is a creative finetune served by Aoru in NVFP4 with a 262,144-token context window. It supports image understanding, tool calling, and optional reasoning.
- Reasoning
- Tools
- Vision
- Input
- Text, Images
- Output
- Text
- Discovery tier
- Open weights
Pricing
USD per 1M tokens- Input
- $0.10
- Output
- $0.60
- Cache read
- $0.05
Reference prices as published by the model provider. API example
Specifications
- Context window
- 262.1K
- Max output
- 32.8K
- Average output (7 days)
- 210 tokens
- Longer than 22% of 465 models
Side by side
Qwen 3.8 27B Kimiko compared
Specifications, prices, speed and benchmark scores next to each other. Benchmarks below show every compared model too.
| Qwen 3.8 27B KimikoQwenThis model | GLM 5.3 FlashZ.aiRemove | |
|---|---|---|
| Provider | Qwen | Z.ai |
| Discovery tier | Open weights | Open weights |
| Added | Oct 5, 2026 | Aug 26, 2026 |
| Limits | ||
| Context window | 262.14K | 1.05MBest |
| Max output | 32.77K | 131.07KBest |
| Average output | 210 tokens | 1.3K tokens |
| Pricing, USD per 1M tokens | ||
| Input | $0.10 | $0.10 |
| Output | $0.60 | $0.30Best |
| Cache read | $0.05 | $0.025Best |
| Performance | ||
| Throughput | — | 105.3 tok/s |
| Time to first token | — | 3.3 s |
| Request success (24h) | 100.0%Best | 99.6% |
| Benchmark indexes | ||
| Intelligence Index | — | 41.8 |
| Coding Index | — | 71.5 |
| Capabilities | ||
| Reasoning | Yes | Yes |
| Tools | Yes | Yes |
| Vision | Yes | Yes |
| Structured output | No | Yes |
| Video input | No | Yes |
| Reasoning effort | — | low, high, max |
Public evaluations
Benchmarks
Independent evaluation results, with how each score ranks among the models in the Noumen catalog.
- Qwen 3.8 27B Kimiko
- GLM 5.3 Flash
Intelligence Index
- Qwen 3.8 27B Kimiko—
- GLM 5.3 Flash41.8
Indexes
Coding Index
Composite of the coding evaluations
- Qwen 3.8 27B Kimiko: —
- GLM 5.3 Flash: 71.5
Agentic work
AutomationBench-AA
Workflow automation, penalized for guardrail violations
- Qwen 3.8 27B Kimiko: —
- GLM 5.3 Flash: 60.4%
AutomationBench-AA tasks completed
Workflows finished end to end without a guardrail violation
- Qwen 3.8 27B Kimiko: —
- GLM 5.3 Flash: 25.4%
Harvey LAB-AAv1.1
Legal tasks passed in full, with no material hallucination
- Qwen 3.8 27B Kimiko: —
- GLM 5.3 Flash: 0.8%
AA-Briefcasev1.1
Agentic knowledge work, rated head to head
- Qwen 3.8 27B Kimiko: —
- GLM 5.3 Flash: 1,452 Elo
GDPval-AAv2.1
Economically valuable occupational tasks, rated head to head
- Qwen 3.8 27B Kimiko: —
- GLM 5.3 Flash: 1,642 Elo
Document reasoning
GDP.pdf
Professional reasoning over PDF documents, all-pass rate
- Qwen 3.8 27B Kimiko: —
- GLM 5.3 Flash: 15.4%
AA-LCRv1.1
Reasoning across long documents
- Qwen 3.8 27B Kimiko: —
- GLM 5.3 Flash: 80.0%
MLCR-AA
Long-context reasoning over medical records
- Qwen 3.8 27B Kimiko: —
- GLM 5.3 Flash: 11.7%
Reasoning and knowledge
Humanity’s Last Exam
Expert-level questions across academic fields
- Qwen 3.8 27B Kimiko: —
- GLM 5.3 Flash: 39.9%
GPQA Diamond
Graduate-level science questions
- Qwen 3.8 27B Kimiko: —
- GLM 5.3 Flash: 91.2%
Coding
Terminal-Benchv4.0
Practical software engineering in a terminal
- Qwen 3.8 27B Kimiko: —
- GLM 5.3 Flash: 32.8%
SciCode
Scientific computing in Python
- Qwen 3.8 27B Kimiko: —
- GLM 5.3 Flash: 51.6%
Legacy evaluations
AA-LCR (unversioned)
Long-context reasoning, earlier grading
- Qwen 3.8 27B Kimiko: —
- GLM 5.3 Flash: 80.0%
Scores from Artificial Analysis, updated Oct 26, 2026. Artificial Analysis
- Qwen 3.8 27B Kimiko
- GLM 5.3 Flash
| Leaderboard | Qwen 3.8 27B Kimiko | GLM 5.3 Flash |
|---|---|---|
| Roleplay | Not in top 20 | #20 · 14.9% |
| Creative writing | Not in top 20 | #16 · 19.8% |
| Math | Not in top 20 | #13 · 10.6% |
Ranks among Noumen catalog models on Use cases leaderboards. Only top-20 placements are listed.
- Qwen 3.8 27B Kimiko
- GLM 5.3 Flash
| Leaderboard | Qwen 3.8 27B Kimiko | GLM 5.3 Flash |
|---|---|---|
| Math | Not in top 20 | #13 · 1503.6 |
| Chinese | Not in top 20 | #15 · 1532.0 |
| Vision Style Control · Chinese | Not in top 20 | #12 · 1337.8 |
Ranks among Noumen catalog models on LMArena leaderboards. Only top-20 placements are listed.LMArena
- Qwen 3.8 27B Kimiko
- GLM 5.3 Flash
| Leaderboard | Qwen 3.8 27B Kimiko | GLM 5.3 Flash |
|---|---|---|
| Creative Writing v3 | Not in top 20 | #10 · 1974 |
| Longform Writing | Not in top 20 | #17 · 79.9 |
Ranks among Noumen catalog models on EQ-Bench leaderboards. Only top-20 placements are listed.EQ-Bench
Live routing data
Performance and reliability
Recent averages across requests routed for this model. Your own speed depends on prompt length, reasoning effort and load.
- Prompt cache hits
- 79.7%
- About $0.0602 per 1M input tokens with caching
- Request success (24h)
- 100.0%
- Reliable
Cache hits are the share of input tokens recently served from a prompt cache across all requests. They are not a forecast of your own hit rate.
- Healthy (98% or more)
- Degraded (90–98%)
- Down (under 90%)
- No requests
Developers
Use it through the API
Noumen’s API is OpenAI-compatible: any Chat Completions client works with a base URL and a key.
curl https://www.noumen.xyz/api/v1/chat/completions \
-H "Authorization: Bearer $NOUMEN_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "qwen/qwen3.8-27b-kimiko",
"messages": [{ "role": "user", "content": "Explain this stack trace." }]
}'import os
from openai import OpenAI
client = OpenAI(base_url="https://www.noumen.xyz/api/v1", api_key=os.environ["NOUMEN_API_KEY"])
reply = client.chat.completions.create(
model="qwen/qwen3.8-27b-kimiko",
messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)Qwen
Related models
Other Qwen models, starting with the same family.