blossom-v5-llama3-8B: benchmark results
A conversational instruction fine-tune released by Azure99 based on Meta-Llama-3-8B, using Azure99/blossom-chat-v3, Azure99/blossom-math-v4, Azure99/blossom-wizard-v3, Azure99/blossom-orca-v3. Training uses two stages; dataset example counts and epochs are not token or compute disclosures. The card says its training data was distilled from gpt-4-0125-preview. Provider: Azure99. Access: Open.
Aggregate Rating 1391 ± 33, rank #6498 of 10916 rated models, from 12 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - MMLU | 65.48 | Accuracy (%) (5-shot) | 84.6 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 57.12 | MC2 (%) (0-shot) | 69.4 |
| Open LLM Leaderboard v1 - WinoGrande | 78.37 | Accuracy (%) (5-shot) | 62.7 |
| Open LLM Leaderboard v1 - GSM8K | 44.43 | Accuracy (%) (5-shot) | 58.5 |
| Open LLM Leaderboard v1 - HellaSwag | 83.05 | Normalized accuracy (%) (10-shot) | 55.7 |
| Open LLM Leaderboard - IFEval | 43.43 | Score | 45.9 |
| Open LLM Leaderboard v1 - ARC Challenge | 56.83 | Normalized accuracy (%) (25-shot) | 36.2 |
| Open LLM Leaderboard - MATH Level 5 | 5.14 | Score | 28.6 |
| Open LLM Leaderboard - BBH | 41.85 | Score | 27.3 |
| Open LLM Leaderboard - MMLU-Pro | 22.06 | Score | 22.9 |
| Open LLM Leaderboard - MuSR | 36.7 | Score | 22 |
| Open LLM Leaderboard - GPQA | 26.51 | Score | 19.3 |
Interactive version: theaggregate.ai/model?slug=blossom-v5-llama3-8b · How It Works · Data refreshed daily, snapshot 2026-11-08.