NOUMENOpen app
NOUMEN

aisingapore · Efficient

Gemma SEA-LION v4 27B

Added Oct 15, 2026

Compare models

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

Loading models…

Use in the app

AI Singapore’s Gemma-based model for text chat in Southeast Asian languages, with a 128K context window. Open weights under the Gemma license; this route supports text input only.

Input
Text
Output
Text
Discovery tier
Efficient

Pricing

USD per 1M tokens
Input
$0.24
Output
$0.48

Reference prices as published by the model provider. API example

Specifications

Context window
131.1K
Max output
—

Side by side

Gemma SEA-LION v4 27B 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…

Gemma SEA-LION v4 27BaisingaporeThis modelGemini 3.1 Flash LiteGoogleRemove
ProvideraisingaporeGoogle
Discovery tierEfficientEfficient
AddedOct 15, 2026Mar 3, 2026
Limits
Context window131.07K1.05MBest
Max output—65.54K
Average output—669 tokens
Pricing, USD per 1M tokens
Input$0.24Best$0.25
Output$0.48Best$1.50
Cache read—$0.025
Cache write—$0.0833
Performance
Throughput—434.7 tok/s
Time to first token—2.3 s
Request success (24h)—100.0%
Benchmark indexes
Intelligence Index—15.6
Coding Index—34.7
Capabilities
ReasoningNoYes
ToolsNoYes
VisionNoYes
Structured outputNoYes
PDF inputNoYes
Audio inputNoYes
Video inputNoYes
Reasoning effort—minimal, low, medium, high

Public evaluations

Benchmarks

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

  • Gemma SEA-LION v4 27B
  • Gemini 3.1 Flash Lite

Intelligence Index

  • Gemma SEA-LION v4 27B—
  • Gemini 3.1 Flash Lite15.6
3.8Catalog models by score55.1

Indexes

  • Coding Index

    Composite of the coding evaluations

    • Gemma SEA-LION v4 27B: —
    • Gemini 3.1 Flash Lite: 34.7

Agentic work

  • AutomationBench-AA

    Workflow automation, penalized for guardrail violations

    • Gemma SEA-LION v4 27B: —
    • Gemini 3.1 Flash Lite: 6.8%

  • AutomationBench-AA tasks completed

    Workflows finished end to end without a guardrail violation

    • Gemma SEA-LION v4 27B: —
    • Gemini 3.1 Flash Lite: 0.5%

  • AA-Briefcasev1.1

    Agentic knowledge work, rated head to head

    • Gemma SEA-LION v4 27B: —
    • Gemini 3.1 Flash Lite: 207 Elo

  • GDPval-AAv2.1

    Economically valuable occupational tasks, rated head to head

    • Gemma SEA-LION v4 27B: —
    • Gemini 3.1 Flash Lite: 430 Elo

Document reasoning

  • GDP.pdf

    Professional reasoning over PDF documents, all-pass rate

    • Gemma SEA-LION v4 27B: —
    • Gemini 3.1 Flash Lite: 7.8%

  • AA-LCRv1.1

    Reasoning across long documents

    • Gemma SEA-LION v4 27B: —
    • Gemini 3.1 Flash Lite: 74.3%

  • MLCR-AA

    Long-context reasoning over medical records

    • Gemma SEA-LION v4 27B: —
    • Gemini 3.1 Flash Lite: 5.0%

Reasoning and knowledge

  • Humanity’s Last Exam

    Expert-level questions across academic fields

    • Gemma SEA-LION v4 27B: —
    • Gemini 3.1 Flash Lite: 17.2%

  • GPQA Diamond

    Graduate-level science questions

    • Gemma SEA-LION v4 27B: —
    • Gemini 3.1 Flash Lite: 82.2%

  • IFBench

    Following precise output instructions

    • Gemma SEA-LION v4 27B: —
    • Gemini 3.1 Flash Lite: 77.2%

Coding

  • Terminal-Benchv4.0

    Practical software engineering in a terminal

    • Gemma SEA-LION v4 27B: —
    • Gemini 3.1 Flash Lite: 0.5%

  • SciCode

    Scientific computing in Python

    • Gemma SEA-LION v4 27B: —
    • Gemini 3.1 Flash Lite: 43.4%

Legacy evaluations

  • Terminal-Bench Hard

    Earlier terminal task suite

    • Gemma SEA-LION v4 27B: —
    • Gemini 3.1 Flash Lite: 24.2%

  • τ²-Bench Telecom

    Tool use in a customer-support simulation

    • Gemma SEA-LION v4 27B: —
    • Gemini 3.1 Flash Lite: 31.3%

  • AA-LCR (unversioned)

    Long-context reasoning, earlier grading

    • Gemma SEA-LION v4 27B: —
    • Gemini 3.1 Flash Lite: 74.3%

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/gemma-sea-lion-v4-27b-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/gemma-sea-lion-v4-27b-it",
    messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)

aisingapore

Other aisingapore models, starting with the same family.