blossom-v4-qwen1.5-4B: benchmark results
A conversational instruction fine-tune released by Azure99 based on Qwen1.5-4B, using Azure99/blossom-chat-v2, Azure99/blossom-math-v3, Azure99/blossom-wizard-v2, Azure99/blossom-orca-v2. Training uses two stages; dataset example counts and epochs are not token or compute disclosures. Provider: Azure99. Access: Open.
Aggregate Rating 1328 ± 39, rank #8197 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - GSM8K | 51.1 | Accuracy (%) (5-shot) | 63.3 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 47.29 | MC2 (%) (0-shot) | 37.3 |
| Open LLM Leaderboard v1 - MMLU | 55.11 | Accuracy (%) (5-shot) | 35.4 |
| Open LLM Leaderboard v1 - WinoGrande | 67.64 | Accuracy (%) (5-shot) | 21.6 |
| Open LLM Leaderboard v1 - ARC Challenge | 46.08 | Normalized accuracy (%) (25-shot) | 21.3 |
| Open LLM Leaderboard v1 - HellaSwag | 70.8 | Normalized accuracy (%) (10-shot) | 21 |
Interactive version: theaggregate.ai/model?slug=blossom-v4-qwen1-5-4b · How It Works · Data refreshed daily, snapshot 2026-11-08.