blossom-v4-mistral-7B: benchmark results
A conversational instruction fine-tune released by Azure99 based on Mistral-7B-v0.1, 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 1402 ± 32, rank #5985 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 53.84 | MC2 (%) (0-shot) | 60.9 |
| Open LLM Leaderboard v1 - GSM8K | 43.14 | Accuracy (%) (5-shot) | 57.4 |
| Open LLM Leaderboard v1 - ARC Challenge | 62.03 | Normalized accuracy (%) (25-shot) | 55.6 |
| Open LLM Leaderboard v1 - MMLU | 62.48 | Accuracy (%) (5-shot) | 55.4 |
| Open LLM Leaderboard v1 - WinoGrande | 77.27 | Accuracy (%) (5-shot) | 54.6 |
| Open LLM Leaderboard v1 - HellaSwag | 82.9 | Normalized accuracy (%) (10-shot) | 54.5 |
Interactive version: theaggregate.ai/model?slug=blossom-v4-mistral-7b · How It Works · Data refreshed daily, snapshot 2026-11-08.