Skip to content
OpenTrain AIFor AI Companies

HFEPX · Eval paper review

EngGPT2: Sovereign, Efficient and Open Intelligence

G. Ciarfaglia, A. Rosanova, S. Cipolla, J. Bartoli +16 more

Published

Mar 17, 2026

Citations

0

Trust level

Low

Usefulness score

0/100 (Low)

Extraction confidence

25% (Low)

Derived from extracted protocol signals and abstract evidence.

Rater population

Domain Experts

Signals refreshed

Mar 30, 2026

Open arXiv Find implementation Shortlist (0) RSS feed

Should you rely on this paper?

This paper is adjacent to HFEPX scope and is best used for background context, not as a primary protocol reference.

Use this as background context only. Do not make protocol decisions from this page alone.

Best use

Background context only

Use if you need

Background context only.

What to verify

Validate the evaluation procedure and quality controls in the full paper before operational use.

Main weakness

This paper looks adjacent to evaluation work, but not like a strong protocol reference.

Human feedback signal
Not explicit
Not explicit in abstract metadata
Evaluation signal
Weak or implicit
Validate from full paper
Usefulness for eval research
0/100
Adjacent candidate

Treat as adjacent context, not a core eval-method reference.

If you are doing eval pipeline work, start here

Human Eval Papers LLM-as-Judge Papers Pairwise Preference Papers Tool-Use Evaluation Search

Abstract

EngGPT2-16B-A3B is the latest iteration of Engineering Group's Italian LLM and it's built to be a Sovereign, Efficient and Open model. EngGPT2 is trained on 2.5 trillion tokens - less than Qwen3's 36T or Llama3's 15T - and delivers performance on key benchmarks, including MMLU-Pro, GSM8K, IFEval and HumanEval, comparable to dense models in the 8B-16B range, while requiring one-fifth to half of the inference power, and between one-tenth to one-sixth of the training data and consequent needed training power. Designed as a trained-from-scratch Mixture-of-Experts (MoE) architecture, EngGPT2 features 16 billion parameters with 3 billion active per inference, with expert sizes positioned between those used in GPT-OSS and Qwen3. Approximately 25% of its training corpus consists of Italian-language data, to deliver strong capabilities for European and Italian NLP tasks among models of similar scale. This efficiency aims to position EngGPT2 as a key contributor to the growing portfolio of open-weight European models, combining performance and efficiency with full alignment to the EU AI Act. EngGPT2 is also a single model capable of multiple reasoning modes: non-reasoning, reasoning in Italian or English, and turbo-reasoning (a concise, bullet-point style reasoning available in both languages designed for real-time reasoning use cases). EngGPT2 aims to set a new standard for resource-conscious, high-performance LLMs tailored to European and Italian contexts.

What we could verify

These are the protocol signals we could actually recover from the available paper metadata. Use them to decide whether this paper is worth deeper reading.

Human Feedback Types

missing

None explicit

No explicit feedback protocol extracted.

"EngGPT2-16B-A3B is the latest iteration of Engineering Group's Italian LLM and it's built to be a Sovereign, Efficient and Open model."

Evaluation Modes

missing

None explicit

Validate eval design from full paper text.

"EngGPT2-16B-A3B is the latest iteration of Engineering Group's Italian LLM and it's built to be a Sovereign, Efficient and Open model."

Quality Controls

missing

Not reported

No explicit QC controls found.

"EngGPT2-16B-A3B is the latest iteration of Engineering Group's Italian LLM and it's built to be a Sovereign, Efficient and Open model."

Benchmarks / Datasets

partial

MMLU, MMLU Pro, GSM8K, HumanEval+, IFEval

Useful for quick benchmark comparison.

"EngGPT2 is trained on 2.5 trillion tokens - less than Qwen3's 36T or Llama3's 15T - and delivers performance on key benchmarks, including MMLU-Pro, GSM8K, IFEval and HumanEval, comparable to dense models in the 8B-16B range, while requiring one-fifth to half of the inference power, and between one-tenth to one-sixth of the training data and consequent needed training power."

Reported Metrics

missing

Not extracted

No metric anchors detected.

"EngGPT2-16B-A3B is the latest iteration of Engineering Group's Italian LLM and it's built to be a Sovereign, Efficient and Open model."

Rater Population

partial

Domain Experts

Helpful for staffing comparability.

"Designed as a trained-from-scratch Mixture-of-Experts (MoE) architecture, EngGPT2 features 16 billion parameters with 3 billion active per inference, with expert sizes positioned between those used in GPT-OSS and Qwen3."

Benchmarks and datasets

MMLUMMLU-ProGSM8KHumanEval+IFEval

Reported metrics

No metric terms were extracted from the available abstract.

Human feedback details
Uses human feedback
No
Feedback types
None
Rater population
Domain Experts
Expertise required
Math
Evaluation details
Evaluation modes
None
Agentic eval
None
Quality controls
Not reported
Evidence quality
Low
Use this page as
Background context only

Research brief

Metadata summary

EngGPT2-16B-A3B is the latest iteration of Engineering Group's Italian LLM and it's built to be a Sovereign, Efficient and Open model.

Based on abstract + metadata only. Check the source paper before making high-confidence protocol decisions.

Key takeaways

  • EngGPT2-16B-A3B is the latest iteration of Engineering Group's Italian LLM and it's built to be a Sovereign, Efficient and Open model.
  • EngGPT2 is trained on 2.5 trillion tokens - less than Qwen3's 36T or Llama3's 15T - and delivers performance on key benchmarks, including MMLU-Pro, GSM8K, IFEval and HumanEval, comparable to dense models in the 8B-16B range, while requiring one-fifth to half of the inference power, and between one-tenth to one-sixth of the training data and consequent needed training power.
  • Designed as a trained-from-scratch Mixture-of-Experts (MoE) architecture, EngGPT2 features 16 billion parameters with 3 billion active per inference, with expert sizes positioned between those used in GPT-OSS and Qwen3.

Researcher actions

  • Compare this paper against others mentioning MMLU and GSM8K.
  • Check the full text for explicit evaluation design choices (raters, protocol, and metrics).
  • Use related-paper links to find stronger protocol-specific references.

Caveats

  • Generated from abstract + metadata only; no PDF parsing.
  • Signals below are heuristic and may miss details reported outside the abstract.

Recommended queries

Expert verification evaluation MMLU GSM8K

Contribution summary

  • EngGPT2 is trained on 2.5 trillion tokens - less than Qwen3's 36T or Llama3's 15T - and delivers performance on key benchmarks, including MMLU-Pro, GSM8K, IFEval and HumanEval, comparable to dense models in the 8B-16B range, while requiring…
  • Approximately 25% of its training corpus consists of Italian-language data, to deliver strong capabilities for European and Italian NLP tasks among models of similar scale.

Why it matters for eval

  • EngGPT2 is trained on 2.5 trillion tokens - less than Qwen3's 36T or Llama3's 15T - and delivers performance on key benchmarks, including MMLU-Pro, GSM8K, IFEval and HumanEval, comparable to dense models in the 8B-16B range, while requiring…

Researcher checklist

  • Human feedback protocol is explicit

    No explicit human feedback protocol detected.

  • Evaluation mode is explicit

    No clear evaluation mode extracted.

  • Quality control reporting appears

    No calibration/adjudication/IAA control explicitly detected.

  • Benchmark or dataset anchors are present

    Detected: MMLU, MMLU-Pro, GSM8K, HumanEval+

  • Metric reporting is present

    No metric terms extracted.