Skip to content

R1 Distill Llama 70B

by DeepSeekRank #232Score 40.7

DeepSeek R1 Distill Llama 70B is a distilled large language model based on [Llama-3.3-70B-Instruct](/meta-llama/llama-3.3-70b-instruct), using outputs from [DeepSeek R1](/deepseek/deepseek-r1). The model combines advanced distillation techniques to achieve high performance across...

Performance Overview

Score
40.7
Rank
#232
24h Change
0
7d Change
-63
State
stable
Confidence
high

Signal Scores

SignalNormalizedWeightContributionFreshness
Capabilities
capability
33.320%6.72026-08-08T12:28:32.973Z
Benchmarks
benchmark
39.930%12.02026-08-08T12:28:32.973Z
Pricing
pricing_tier
99.215%14.92026-08-08T12:28:32.973Z
Context Window
context_window
62.110%6.22026-08-08T12:28:32.973Z
Recency
recency
30.615%4.62026-08-08T12:28:32.973Z
Output Capacity
output_capacity
65.010%6.52026-08-08T12:28:32.973Z

Top Drivers

positive
Pricing
$0.80/M output tokens
$0.80
negative
Benchmarks
negative
Capabilities
Supports reasoning, streaming
2/7
positive
Output Capacity
Up to 8K output tokens per request
8K

Capabilities

CapabilitySupported
VisionNo
ReasoningYes
JSON ModeNo
StreamingYes
Function CallingNo
Web SearchNo

Pricing

Input / 1M tokens
$0.80
Output / 1M tokens
$0.80
Context Window
8K
Max Output
8K

Related Models

Related

R1 Distill Llama 70B Tracker - Performance History | LM Market Cap