NOUMENOpen app
NOUMEN

eva-unit-01 · Open weights

EVA Llama 3.33 70B

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 Llama-3.3-70B-Instruct 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
$2.01
Output
$2.01

Reference prices as published by the model provider. API example

Specifications

Context window
32.8K
Max output
—
Average output (7 days)
321 tokens
Longer than 35% of 468 models

Side by side

EVA Llama 3.33 70B 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 Llama 3.33 70Beva-unit-01This modelGPT-OSS 120B TEEOpenAIRemove
Providereva-unit-01OpenAI
Discovery tierOpen weightsOpen weights
AddedJul 26, 2025Jan 1, 2024
Limits
Context window32.77K131.07KBest
Max output—16.38K
Average output321 tokens174 tokens
Pricing, USD per 1M tokens
Input$2.01$2.00Best
Output$2.01$2.00Best
Cache read—$2.00
Performance
Request success (24h)50.0%—
Benchmark indexes
Intelligence Index—11.6
Coding Index—30.4
Math Index—93.4
Capabilities
Reasoning effort——

Public evaluations

Benchmarks

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

  • EVA Llama 3.33 70B
  • GPT-OSS 120B TEE

Intelligence Index

  • EVA Llama 3.33 70B—
  • GPT-OSS 120B TEE11.6
3.8Catalog models by score55.1

Indexes

  • Coding Index

    Composite of the coding evaluations

    • EVA Llama 3.33 70B: —
    • GPT-OSS 120B TEE: 30.4

  • Math Index

    Composite of the math evaluations

    • EVA Llama 3.33 70B: —
    • GPT-OSS 120B TEE: 93.4

Agentic work

  • AutomationBench-AA

    Workflow automation, penalized for guardrail violations

    • EVA Llama 3.33 70B: —
    • GPT-OSS 120B TEE: 0.2%

  • AutomationBench-AA tasks completed

    Workflows finished end to end without a guardrail violation

    • EVA Llama 3.33 70B: —
    • GPT-OSS 120B TEE: 0.0%

  • GDPval-AAv2.1

    Economically valuable occupational tasks, rated head to head

    • EVA Llama 3.33 70B: —
    • GPT-OSS 120B TEE: 608 Elo

Document reasoning

  • GDP.pdf

    Professional reasoning over PDF documents, all-pass rate

    • EVA Llama 3.33 70B: —
    • GPT-OSS 120B TEE: 4.0%

  • AA-LCRv1.1

    Reasoning across long documents

    • EVA Llama 3.33 70B: —
    • GPT-OSS 120B TEE: 52.0%

  • MLCR-AA

    Long-context reasoning over medical records

    • EVA Llama 3.33 70B: —
    • GPT-OSS 120B TEE: 1.7%

Reasoning and knowledge

  • Humanity’s Last Exam

    Expert-level questions across academic fields

    • EVA Llama 3.33 70B: —
    • GPT-OSS 120B TEE: 19.6%

  • GPQA Diamond

    Graduate-level science questions

    • EVA Llama 3.33 70B: —
    • GPT-OSS 120B TEE: 78.2%

  • MMLU-Pro

    Multi-subject knowledge and reasoning

    • EVA Llama 3.33 70B: —
    • GPT-OSS 120B TEE: 80.8%

  • IFBench

    Following precise output instructions

    • EVA Llama 3.33 70B: —
    • GPT-OSS 120B TEE: 69.0%

Coding

  • Terminal-Benchv4.0

    Practical software engineering in a terminal

    • EVA Llama 3.33 70B: —
    • GPT-OSS 120B TEE: 0.0%

  • SciCode

    Scientific computing in Python

    • EVA Llama 3.33 70B: —
    • GPT-OSS 120B TEE: 34.0%

  • LiveCodeBench

    Recent competitive programming problems

    • EVA Llama 3.33 70B: —
    • GPT-OSS 120B TEE: 87.8%

Math

  • AIME 2025

    Competition mathematics, 2025 problems

    • EVA Llama 3.33 70B: —
    • GPT-OSS 120B TEE: 93.4%

Legacy evaluations

  • Terminal-Bench Hard

    Earlier terminal task suite

    • EVA Llama 3.33 70B: —
    • GPT-OSS 120B TEE: 23.5%

  • τ²-Bench Telecom

    Tool use in a customer-support simulation

    • EVA Llama 3.33 70B: —
    • GPT-OSS 120B TEE: 65.8%

  • AA-LCR (unversioned)

    Long-context reasoning, earlier grading

    • EVA Llama 3.33 70B: —
    • GPT-OSS 120B TEE: 52.0%

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.

Prompt cache hits
0.0%
Request success (24h)
50.0%

Cache hits are the share of input tokens recently served from a prompt cache across all requests. They are not a forecast of your own hit rate.

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-LLaMA-3.33-70B-v0.0",
    "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="EVA-UNIT-01/EVA-LLaMA-3.33-70B-v0.0",
    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.