NOUMENOpen app
NOUMEN

baidu · Balanced

ERNIE 5.1

Added May 10, 2026

Compare models

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

Loading models…

Use in the app

ERNIE 5.1 is the latest Wenxin model, with broad upgrades to agentic workflows, knowledge, reasoning, and deep search. ⚠️ Note: privacy and logging guarantees may be limited.

Input
Text
Output
Text
Discovery tier
Balanced

Pricing

USD per 1M tokens
Input
$0.75
Output
$3.00
Cache read
$0.75

Reference prices as published by the model provider. API example

Specifications

Context window
119K
Max output
64K
Average output (7 days)
1.9K tokens
Longer than 90% of 468 models

Side by side

ERNIE 5.1 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…

ERNIE 5.1baiduThis modelAmazon Nova Pro 1.0amazonRemove
Providerbaiduamazon
Discovery tierBalancedBalanced
AddedMay 10, 2026Dec 3, 2024
Limits
Context window119K300KBest
Max output64KBest32K
Average output1.9K tokens56 tokens
Pricing, USD per 1M tokens
Input$0.75Best$0.80
Output$3.00Best$3.20
Cache read$0.75—
Benchmark indexes
Intelligence Index—7.0
Math Index—7.0
Capabilities
Reasoning effort——

Public evaluations

Benchmarks

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

  • ERNIE 5.1
  • Amazon Nova Pro 1.0

Intelligence Index

  • ERNIE 5.1—
  • Amazon Nova Pro 1.07.0
3.8Catalog models by score55.1

Indexes

  • Math Index

    Composite of the math evaluations

    • ERNIE 5.1: —
    • Amazon Nova Pro 1.0: 7.0

Document reasoning

  • AA-LCRv1.1

    Reasoning across long documents

    • ERNIE 5.1: —
    • Amazon Nova Pro 1.0: 21.0%

Reasoning and knowledge

  • Humanity’s Last Exam

    Expert-level questions across academic fields

    • ERNIE 5.1: —
    • Amazon Nova Pro 1.0: 3.2%

  • GPQA Diamond

    Graduate-level science questions

    • ERNIE 5.1: —
    • Amazon Nova Pro 1.0: 49.9%

  • MMLU-Pro

    Multi-subject knowledge and reasoning

    • ERNIE 5.1: —
    • Amazon Nova Pro 1.0: 69.1%

  • IFBench

    Following precise output instructions

    • ERNIE 5.1: —
    • Amazon Nova Pro 1.0: 38.1%

Coding

  • LiveCodeBench

    Recent competitive programming problems

    • ERNIE 5.1: —
    • Amazon Nova Pro 1.0: 23.3%

Math

  • AIME 2025

    Competition mathematics, 2025 problems

    • ERNIE 5.1: —
    • Amazon Nova Pro 1.0: 7.0%

  • AIME

    Competition mathematics

    • ERNIE 5.1: —
    • Amazon Nova Pro 1.0: 10.7%

  • MATH-500

    Competition math problems

    • ERNIE 5.1: —
    • Amazon Nova Pro 1.0: 78.6%

Legacy evaluations

  • Terminal-Bench Hard

    Earlier terminal task suite

    • ERNIE 5.1: —
    • Amazon Nova Pro 1.0: 6.1%

  • τ²-Bench Telecom

    Tool use in a customer-support simulation

    • ERNIE 5.1: —
    • Amazon Nova Pro 1.0: 14.0%

  • AA-LCR (unversioned)

    Long-context reasoning, earlier grading

    • ERNIE 5.1: —
    • Amazon Nova Pro 1.0: 21.0%

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": "ernie-5.1",
    "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="ernie-5.1",
    messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)

baidu

Other baidu models, starting with the same family.