NOUMENOpen app
NOUMEN

eva-unit-01 · Open weights

EVA-Qwen2.5-32B-v0.2

Added Jul 26, 2025Open weights

Compare models

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

Loading models…

Use in the app

A RP/storywriting specialist model, full-parameter finetune of Qwen2.5-32B on mixture of synthetic and natural data. It uses Celeste 70B 0.1 data mixture, greatly expanding it to improve versatility, creativity and flavor of the resulting model.

Input
Text
Output
Text
Discovery tier
Open weights

Pricing

USD per 1M tokens
Input
$0.80
Output
$0.80

Reference prices as published by the model provider. API example

Specifications

Context window
16.4K
Max output
8.2K
Average output (7 days)
238 tokens
Longer than 25% of 468 models

Side by side

EVA-Qwen2.5-32B-v0.2 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…

EVA-Qwen2.5-32B-v0.2eva-unit-01This modelLongCat 2.0 ThinkinglongcatRemove
Providereva-unit-01longcat
Discovery tierOpen weightsOpen weights
AddedJul 26, 2025Jul 21, 2026
Limits
Context window16.38K1MBest
Max output8.19K131.07KBest
Average output238 tokens1.1K tokens
Pricing, USD per 1M tokens
Input$0.80$0.75Best
Output$0.80Best$3.00
Cache read—$0.015
Performance
Throughput—57.2 tok/s
Time to first token—4.0 s
Request success (24h)41.3%100.0%Best
Benchmark indexes
Intelligence Index—19.1
Coding Index—45.3
Capabilities
ReasoningNoYes
ToolsNoYes
Reasoning effort——

Public evaluations

Benchmarks

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

  • EVA-Qwen2.5-32B-v0.2
  • LongCat 2.0 Thinking

Intelligence Index

  • EVA-Qwen2.5-32B-v0.2—
  • LongCat 2.0 Thinking19.1
3.8Catalog models by score55.1

Indexes

  • Coding Index

    Composite of the coding evaluations

    • EVA-Qwen2.5-32B-v0.2: —
    • LongCat 2.0 Thinking: 45.3

Agentic work

  • AutomationBench-AA

    Workflow automation, penalized for guardrail violations

    • EVA-Qwen2.5-32B-v0.2: —
    • LongCat 2.0 Thinking: 4.5%

  • AutomationBench-AA tasks completed

    Workflows finished end to end without a guardrail violation

    • EVA-Qwen2.5-32B-v0.2: —
    • LongCat 2.0 Thinking: 0.5%

  • AA-Briefcasev1.1

    Agentic knowledge work, rated head to head

    • EVA-Qwen2.5-32B-v0.2: —
    • LongCat 2.0 Thinking: 739 Elo

  • GDPval-AAv2.1

    Economically valuable occupational tasks, rated head to head

    • EVA-Qwen2.5-32B-v0.2: —
    • LongCat 2.0 Thinking: 869 Elo

Document reasoning

  • GDP.pdf

    Professional reasoning over PDF documents, all-pass rate

    • EVA-Qwen2.5-32B-v0.2: —
    • LongCat 2.0 Thinking: 6.4%

  • AA-LCRv1.1

    Reasoning across long documents

    • EVA-Qwen2.5-32B-v0.2: —
    • LongCat 2.0 Thinking: 65.0%

Reasoning and knowledge

  • Humanity’s Last Exam

    Expert-level questions across academic fields

    • EVA-Qwen2.5-32B-v0.2: —
    • LongCat 2.0 Thinking: 33.7%

  • GPQA Diamond

    Graduate-level science questions

    • EVA-Qwen2.5-32B-v0.2: —
    • LongCat 2.0 Thinking: 78.0%

Coding

  • Terminal-Benchv4.0

    Practical software engineering in a terminal

    • EVA-Qwen2.5-32B-v0.2: —
    • LongCat 2.0 Thinking: 0.0%

  • SciCode

    Scientific computing in Python

    • EVA-Qwen2.5-32B-v0.2: —
    • LongCat 2.0 Thinking: 36.3%

Legacy evaluations

  • AA-LCR (unversioned)

    Long-context reasoning, earlier grading

    • EVA-Qwen2.5-32B-v0.2: —
    • LongCat 2.0 Thinking: 65.0%

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

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.

Request success (24h)
41.3%

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": "EVA-UNIT-01/EVA-Qwen2.5-32B-v0.2",
    "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="EVA-UNIT-01/EVA-Qwen2.5-32B-v0.2",
    messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)

eva-unit-01

Other eva-unit-01 models, starting with the same family.