NOUMENOpen app
NOUMEN

aisingapore · Open weights

Qwen SEA-LION v4 32B

Added Oct 15, 2026Open weights

Compare models

Choose up to 3 models to compare.1 of 3 chosen

Loading models…

Use in the app

AI Singapore’s Qwen-based multilingual model, adapted for Southeast Asian languages and cultural contexts. Supports text chat and tool calling with a 128K context window.

  • Tools
Input
Text
Output
Text
Discovery tier
Open weights

Pricing

USD per 1M tokens
Input
$0.30
Output
$0.60

Reference prices as published by the model provider. API example

Specifications

Context window
131.1K
Max output
—

Side by side

Qwen SEA-LION v4 32B compared

Specifications, prices, speed and benchmark scores next to each other. Benchmarks below show every compared model too.

Compare models

Choose up to 3 models to compare.1 of 3 chosen

Loading models…

Qwen SEA-LION v4 32BaisingaporeThis modelGLM 4.6VZ.aiRemove
ProvideraisingaporeZ.ai
Discovery tierOpen weightsOpen weights
AddedOct 15, 2026Dec 11, 2025
Limits
Context window131.07KBest128K
Max output—24K
Average output—139 tokens
Pricing, USD per 1M tokens
Input$0.30$0.30
Output$0.60Best$0.90
Performance
Request success (24h)—99.7%
Benchmark indexes
Intelligence Index—8.4
Math Index—26.3
Capabilities
ToolsYesNo
VisionNoYes
Video inputNoYes
Reasoning effort——

Public evaluations

Benchmarks

Independent evaluation results, with how each score ranks among the models in the Noumen catalog.

  • Qwen SEA-LION v4 32B
  • GLM 4.6V

Intelligence Index

  • Qwen SEA-LION v4 32B—
  • GLM 4.6V8.4
3.8Catalog models by score55.1

Indexes

  • Math Index

    Composite of the math evaluations

    • Qwen SEA-LION v4 32B: —
    • GLM 4.6V: 26.3

Document reasoning

  • AA-LCRv1.1

    Reasoning across long documents

    • Qwen SEA-LION v4 32B: —
    • GLM 4.6V: 17.0%

Reasoning and knowledge

  • Humanity’s Last Exam

    Expert-level questions across academic fields

    • Qwen SEA-LION v4 32B: —
    • GLM 4.6V: 3.7%

  • GPQA Diamond

    Graduate-level science questions

    • Qwen SEA-LION v4 32B: —
    • GLM 4.6V: 56.6%

  • MMLU-Pro

    Multi-subject knowledge and reasoning

    • Qwen SEA-LION v4 32B: —
    • GLM 4.6V: 75.2%

  • IFBench

    Following precise output instructions

    • Qwen SEA-LION v4 32B: —
    • GLM 4.6V: 27.9%

Coding

  • LiveCodeBench

    Recent competitive programming problems

    • Qwen SEA-LION v4 32B: —
    • GLM 4.6V: 41.1%

Math

  • AIME 2025

    Competition mathematics, 2025 problems

    • Qwen SEA-LION v4 32B: —
    • GLM 4.6V: 26.3%

Legacy evaluations

  • Terminal-Bench Hard

    Earlier terminal task suite

    • Qwen SEA-LION v4 32B: —
    • GLM 4.6V: 3.0%

  • τ²-Bench Telecom

    Tool use in a customer-support simulation

    • Qwen SEA-LION v4 32B: —
    • GLM 4.6V: 30.7%

  • AA-LCR (unversioned)

    Long-context reasoning, earlier grading

    • Qwen SEA-LION v4 32B: —
    • GLM 4.6V: 17.0%

Scores from Artificial Analysis, updated Oct 26, 2026. Artificial Analysis

Developers

Use it through the API

Noumen’s API is OpenAI-compatible: any Chat Completions client works with a base URL and a key.

Read the quickstart
curl https://www.noumen.xyz/api/v1/chat/completions \
  -H "Authorization: Bearer $NOUMEN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "aisingapore/qwen-sea-lion-v4-32b-it",
    "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="aisingapore/qwen-sea-lion-v4-32b-it",
    messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)

aisingapore

Other aisingapore models, starting with the same family.