Nexa-AI-4B-Instruct
A collaborative open-source large language model developed by Neura Tech AI and Lumina AI.
Overview
Nexa-AI-4B-Instruct is an instruction-tuned large language model built on top of Qwen/Qwen3-4B-Instruct-2507.
This project is jointly developed by:
- Neura Tech AI
- Lumina AI
Nexa AI focuses on delivering a capable multilingual AI assistant with strong performance in:
- General conversation
- Instruction following
- Coding
- Mathematics
- Logical reasoning
- Tool calling & AI agents
- Multilingual understanding (including English, Hindi, Chinese, and more)
Base Model
Base Model: Qwen/Qwen3-4B-Instruct-2507
We sincerely thank the Qwen Team for releasing the Qwen3 model family under the Apache 2.0 License, which made this project possible.
Developers
Project: Nexa AI
Developed by:
- Neura Tech AI
- Lumina AI
Model Details
- Model Name: Nexa-AI-4B-Instruct
- Base Model: Qwen/Qwen3-4B-Instruct-2507
- Architecture: Transformer Decoder
- Parameters: ~4 Billion
- Context Length: 262,144 Tokens (Inherited from the base model)
- License: Apache-2.0 (Base model license)
Features
- High-quality instruction following
- Coding assistance
- Mathematical reasoning
- Agent & tool calling support
- Multilingual capabilities
- Long-context understanding
- Fine-tuned alignment for helpful responses
Performance
| GPT-4.1-nano-2025-04-14 | Qwen3-30B-A3B Non-Thinking | Qwen3-4B Non-Thinking | Nexa-AI-4B-Instruct | |
|---|---|---|---|---|
| Knowledge | ||||
| MMLU-Pro | 62.8 | 69.1 | 58.0 | 69.6 |
| MMLU-Redux | 80.2 | 84.1 | 77.3 | 84.2 |
| GPQA | 50.3 | 54.8 | 41.7 | 62.0 |
| SuperGPQA | 32.2 | 42.2 | 32.0 | 42.8 |
| Reasoning | ||||
| AIME25 | 22.7 | 21.6 | 19.1 | 47.4 |
| HMMT25 | 9.7 | 12.0 | 12.1 | 31.0 |
| ZebraLogic | 14.8 | 33.2 | 35.2 | 80.2 |
| LiveBench 20241125 | 41.5 | 59.4 | 48.4 | 63.0 |
| Coding | ||||
| LiveCodeBench v6 (25.02-25.05) | 31.5 | 29.0 | 26.4 | 35.1 |
| MultiPL-E | 76.3 | 74.6 | 66.6 | 76.8 |
| Aider-Polyglot | 9.8 | 24.4 | 13.8 | 12.9 |
| Alignment | ||||
| IFEval | 74.5 | 83.7 | 81.2 | 83.4 |
| Arena-Hard v2* | 15.9 | 24.8 | 9.5 | 43.4 |
| Creative Writing v3 | 72.7 | 68.1 | 53.6 | 83.5 |
| WritingBench | 66.9 | 72.2 | 68.5 | 83.4 |
| Agent | ||||
| BFCL-v3 | 53.0 | 58.6 | 57.6 | 61.9 |
| TAU1-Retail | 23.5 | 38.3 | 24.3 | 48.7 |
| TAU1-Airline | 14.0 | 18.0 | 16.0 | 32.0 |
| TAU2-Retail | - | 31.6 | 28.1 | 40.4 |
| TAU2-Airline | - | 18.0 | 12.0 | 24.0 |
| TAU2-Telecom | - | 18.4 | 17.5 | 13.2 |
| Multilingualism | ||||
| MultiIF | 60.7 | 70.8 | 61.3 | 69.0 |
| MMLU-ProX | 56.2 | 65.1 | 49.6 | 61.6 |
| INCLUDE | 58.6 | 67.8 | 53.8 | 60.1 |
| PolyMATH | 15.6 | 23.3 | 16.6 | 31.1 |
*: For reproducibility, we report the win rates evaluated by GPT-4.1.