NOUMENOpen app
NOUMEN

meganova · Efficient

Manta Pro 1.0

Added Sep 20, 2025

Compare models

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

Loading models…

Use in the app

Tailored for deep reasoning, long-form generation, and RAG workloads. 32K token context window.

Input
Text
Output
Text
Discovery tier
Efficient

Pricing

USD per 1M tokens
Input
$0.06
Output
$0.50

Reference prices as published by the model provider. API example

Specifications

Context window
65.5K
Max output
—
Average output (7 days)
198 tokens
Longer than 20% of 468 models

Side by side

Manta Pro 1.0 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…

Manta Pro 1.0meganovaThis modelTencent Hy3tencentRemove
Providermeganovatencent
Discovery tierEfficientEfficient
AddedSep 20, 2025Jul 6, 2026
Limits
Context window65.54K262.14KBest
Max output—128K
Average output198 tokens1.4K tokens
Pricing, USD per 1M tokens
Input$0.06Best$0.066
Output$0.50$0.26Best
Cache read—$0.029
Performance
Throughput—69.5 tok/s
Time to first token—3.8 s
Request success (24h)—99.8%
Benchmark indexes
Intelligence Index—25.3
Coding Index—58.8
Capabilities
ReasoningNoYes
ToolsNoYes
Structured outputNoYes
Reasoning effort—none, low, high

Public evaluations

Benchmarks

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

  • Manta Pro 1.0
  • Tencent Hy3

Intelligence Index

  • Manta Pro 1.0—
  • Tencent Hy325.3
3.8Catalog models by score55.1

Indexes

  • Coding Index

    Composite of the coding evaluations

    • Manta Pro 1.0: —
    • Tencent Hy3: 58.8

Agentic work

  • AutomationBench-AA

    Workflow automation, penalized for guardrail violations

    • Manta Pro 1.0: —
    • Tencent Hy3: 18.4%

  • AutomationBench-AA tasks completed

    Workflows finished end to end without a guardrail violation

    • Manta Pro 1.0: —
    • Tencent Hy3: 2.7%

  • AA-Briefcasev1.1

    Agentic knowledge work, rated head to head

    • Manta Pro 1.0: —
    • Tencent Hy3: 947 Elo

  • GDPval-AAv2.1

    Economically valuable occupational tasks, rated head to head

    • Manta Pro 1.0: —
    • Tencent Hy3: 1,063 Elo

Document reasoning

  • GDP.pdf

    Professional reasoning over PDF documents, all-pass rate

    • Manta Pro 1.0: —
    • Tencent Hy3: 11.2%

  • AA-LCRv1.1

    Reasoning across long documents

    • Manta Pro 1.0: —
    • Tencent Hy3: 79.0%

Reasoning and knowledge

  • Humanity’s Last Exam

    Expert-level questions across academic fields

    • Manta Pro 1.0: —
    • Tencent Hy3: 33.5%

  • GPQA Diamond

    Graduate-level science questions

    • Manta Pro 1.0: —
    • Tencent Hy3: 89.7%

Coding

  • Terminal-Benchv4.0

    Practical software engineering in a terminal

    • Manta Pro 1.0: —
    • Tencent Hy3: 0.5%

  • SciCode

    Scientific computing in Python

    • Manta Pro 1.0: —
    • Tencent Hy3: 48.6%

Legacy evaluations

  • AA-LCR (unversioned)

    Long-context reasoning, earlier grading

    • Manta Pro 1.0: —
    • Tencent Hy3: 79.0%

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": "meganova-ai/manta-pro-1.0",
    "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="meganova-ai/manta-pro-1.0",
    messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)

meganova

Other meganova models, starting with the same family.