blossom-v5-32B: benchmark results
A conversational instruction fine-tune released by Azure99 based on Qwen1.5-32B, 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. Multiple evaluator revisions retain this release identity; their weights are not assumed identical. Provider: Azure99. Access: Open.
Aggregate Rating 1485 ± 32, rank #2596 of 10916 rated models, from 12 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - MMLU | 74.27 | Accuracy (%) (5-shot) | 95.9 |
| Open LLM Leaderboard v1 - GSM8K | 70.66 | Accuracy (%) (5-shot) | 93.8 |
| Open LLM Leaderboard - BBH | 59.55 | Score | 81.2 |
| Open LLM Leaderboard v1 - WinoGrande | 81.69 | Accuracy (%) (5-shot) | 80.5 |
| Open LLM Leaderboard - MMLU-Pro | 42.35 | Score | 76.9 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 58.24 | MC2 (%) (0-shot) | 71.9 |
| Open LLM Leaderboard - MATH Level 5 | 18.66 | Score | 68.6 |
| Open LLM Leaderboard - GPQA | 31.12 | Score | 68.5 |
| Open LLM Leaderboard v1 - ARC Challenge | 63.82 | Normalized accuracy (%) (25-shot) | 64.4 |
| Open LLM Leaderboard - IFEval | 52.35 | Score | 62.3 |
| Open LLM Leaderboard v1 - HellaSwag | 83.54 | Normalized accuracy (%) (10-shot) | 59.5 |
| Open LLM Leaderboard - MuSR | 40.2 | Score | 43.7 |
Interactive version: theaggregate.ai/model?slug=blossom-v5-32b · How It Works · Data refreshed daily, snapshot 2026-11-08.