blossom-v2-3B: benchmark results
A conversational instruction fine-tune released by Azure99 based on Bloom-3b, using Azure99/blossom-chat-v1, Azure99/blossom-math-v1, ehartford/dolphin, WizardLM/WizardLM_evol_instruct_V2_196k. Training uses two stages; dataset example counts and epochs are not token or compute disclosures. Provider: Azure99. Access: Open.
Aggregate Rating 1136 ± 36, rank #10207 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 43.11 | MC2 (%) (0-shot) | 22.5 |
| Open LLM Leaderboard v1 - ARC Challenge | 35.32 | Normalized accuracy (%) (25-shot) | 13 |
| Open LLM Leaderboard v1 - GSM8K | 0.53 | Accuracy (%) (5-shot) | 12.7 |
| Open LLM Leaderboard v1 - WinoGrande | 58.8 | Accuracy (%) (5-shot) | 11.9 |
| Open LLM Leaderboard v1 - HellaSwag | 54.1 | Normalized accuracy (%) (10-shot) | 11.7 |
| Open LLM Leaderboard v1 - MMLU | 23.99 | Accuracy (%) (5-shot) | 2.7 |
Interactive version: theaggregate.ai/model?slug=blossom-v2-3b · How It Works · Data refreshed daily, snapshot 2026-11-08.