Magnum v4 72B

Text input Text output
Author's Description

This is a series of models designed to replicate the prose quality of the Claude 3 models, specifically Sonnet(https://openrouter.ai/anthropic/claude-3.5-sonnet) and Opus(https://openrouter.ai/anthropic/claude-3-opus). The model is fine-tuned on top of [Qwen2.5 72B](https://openrouter.ai/qwen/qwen-2.5-72b-instruct).

Key Specifications
Cost
$$$$$
Context
16K
Parameters
72B
Released
Oct 21, 2024
Speed
Ability
Reliability
Supported Parameters

This model supports the following parameters:

Stop Presence Penalty Logit Bias Top P Temperature Min P Seed Frequency Penalty Max Tokens
Performance Summary

Magnum v4 72B, a model from anthracite-org created on October 21, 2024, aims to replicate the prose quality of Claude 3 models and is fine-tuned on Qwen2.5 72B. It exhibits moderate speed performance, ranking in the 27th percentile across benchmarks, and offers moderate pricing, also in the 27th percentile. A standout feature is its exceptional reliability, achieving a perfect 100th percentile, indicating consistent and usable responses with minimal technical failures. In terms of specific performance, Magnum v4 72B demonstrates strong capabilities across various domains. It achieved 97.0% accuracy in Email Classification, performing solidly within the 48th percentile. Its Reasoning abilities are commendable with 72.0% accuracy, placing it in the 69th percentile. The model truly excels in Ethics, achieving a perfect 100.0% accuracy, making it the most accurate model at its price point and among models of similar speed. For General Knowledge, it scored 98.5% accuracy, ranking in the 67th percentile. While its accuracy is high across the board, its duration for General Knowledge was notably longer, placing it in the 15th percentile for speed on that specific benchmark. Overall, Magnum v4 72B's key strengths lie in its high accuracy, particularly in ethical reasoning, and its robust reliability, making it a dependable choice for critical applications despite its moderate speed and pricing.

Model Pricing

Current Pricing

Feature Price (per 1M tokens)
Prompt $1.25
Completion $1.5

Price History

Available Endpoints
Provider Endpoint Name Context Length Pricing (Input) Pricing (Output)
Mancer 2
Mancer 2 | anthracite-org/magnum-v4-72b 16K $1.25 / 1M tokens $1.5 / 1M tokens
Featherless
Featherless | anthracite-org/magnum-v4-72b 16K $1.25 / 1M tokens $1.5 / 1M tokens
Benchmark Results
Benchmark Category Reasoning Free Executions Accuracy Cost Duration
Other Models by anthracite-org