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
+2
7d Change
-7
State
stableConfidence
highSignal Scores
| Signal | Normalized | Weight | Contribution | Freshness |
|---|---|---|---|---|
Capabilities capability | 33.3 | 20% | 6.7 | 2026-09-22T14:24:56.053Z |
Benchmarks benchmark | 39.9 | 30% | 12.0 | 2026-09-22T14:24:56.053Z |
Pricing pricing_tier | 99.2 | 15% | 14.9 | 2026-09-22T14:24:56.053Z |
Context Window context_window | 62.1 | 10% | 6.2 | 2026-09-22T14:24:56.053Z |
Recency recency | 22.4 | 15% | 3.4 | 2026-09-22T14:24:56.053Z |
Output Capacity output_capacity | 61.8 | 10% | 6.2 | 2026-09-22T14:24:56.053Z |
Top Drivers
positive
Pricing
$0.80/M output tokens
$0.80
negative
Benchmarks
negative
Capabilities
Supports reasoning, streaming
2/7
positive
Context Window
8K token context window
8K
Capabilities
| Capability | Supported |
|---|---|
| Vision | No |
| Reasoning | Yes |
| JSON Mode | No |
| Streaming | Yes |
| Function Calling | No |
| Web Search | No |
Pricing
Input / 1M tokens
$0.80
Output / 1M tokens
$0.80
Context Window
8K
Max Output
7K