Meta's Llama 3.1 8B model on an open permissionless network
Context Window
128.0K
Max Output
16.4K
Input Price (Auto)
$0.020/1M
Output Price (Auto)
$0.030/1M
Cache Read (Auto)
$0.010/1M
Benchmarks
Benchmarks
Performance metrics and benchmarks
Sourced from Artificial Analysis.
Intelligence Index
6.9
Coding Index
5.4
Agentic work
T²-Bench Telecom (legacy)
Legacy fallback · Conversational AI agents in dual-control scenarios
16.4%
Better than 15% of models compared
GDPval-AA v2
Economically valuable tasks (Elo)
-151 Elo
Better than 2% of models compared
Document reasoning
AA-LCR v1.1
Long context reasoning with updated grading
18.0%
Better than 22% of models compared
Reasoning
HLE
Humanity's Last Exam
5.3%
Better than 34% of models compared
IFBench
Instruction-following benchmark
28.6%
Better than 12% of models compared
CritPt
Research-level physics reasoning
0.0%
Coding
Terminal-Bench Hard (legacy)
Legacy fallback · Agentic coding and terminal use
0.8%
Better than 13% of models compared
LiveCodeBench
Contamination-free coding benchmark
11.6%
Better than 11% of models compared
Math
AIME 2025
American Invitational Mathematics Examination 2025
4.3%
Better than 7% of models compared
AIME
American Invitational Mathematics Examination
7.7%
Better than 25% of models compared
Math-500
Diverse mathematical problem solving benchmark
51.9%
Better than 15% of models compared
Knowledge
MMLU-Pro
Professional and academic subject knowledge
47.6%
Better than 13% of models compared
AA-Omniscience Accuracy
Proportion of correctly answered questions
8.5%
AA-Omniscience Hallucination Rate
Rate of incorrect answers among non-correct responses
43.0%
Legacy benchmarks
GPQA Diamond (legacy)
Graduate-level scientific reasoning
25.9%
Better than 3% of models compared
AA-LCR (unversioned / legacy)
Long context reasoning evaluation
18.0%
Better than 22% of models compared
GDPval-AA (unversioned / legacy)
Economically valuable tasks
0.0%
Last updated Sep 13, 2026
Artificial AnalysisProviders
Auto routing is available for this model. Explicit provider selection is not available.
Loading provider options…
Related text models
Compare Llama 3.1 8B (decentralized) with similar models from the same provider or model family.
Llama 3.1 405B
meta-llama/llama-3.1-405b-instructLlama 3.1 405B hosted by IONOS in Berlin, Germany. Zero data retention.
Llama 3 70B abliterated
failspy/Meta-Llama-3-70B-Instruct-abliterated-v3.5An abliterated (removed restrictions and censorship) version of Llama 3.1 70b.
Llama 3.3 70b Instruct
meta-llama/llama-3.3-70b-instructLlama 3.3 is optimized for multilingual dialogue use cases and outperforms many of the available open source and closed chat models on common industry benchmarks.
Llama 3.1 8b Instruct
meta-llama/llama-3.1-8b-instructFast and efficient for simple purposes.
Llama 3.2 3b Instruct
meta-llama/llama-3.2-3b-instructSmall model optimized for advanced natural language processing tasks like dialogue generation, reasoning, and summarization
Llama 4 Maverick
meta-llama/llama-4-maverickLlama 4 Maverick, a 17 billion active parameter model with 128 experts, is the best multimodal model in its class, beating GPT-4o and Gemini 2.0 Flash across a broad range of widely reported benchmarks, while achieving comparable results to the new DeepSeek v3 on reasoning and coding—at less than half the active parameters. Llama 4 Maverick offers a best-in-class performance to cost ratio with an experimental chat version scoring ELO of 1417 on LMArena.