MetaLlama 3.1Open SourceArena #232Jul 23, 2024
Meta: Llama 3.1 8B Instruct
Meta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors. This 8B instruct-tuned version is fast and efficient.
It has demonstrated strong performance compared to leading closed-source models in human evaluations.
To read more about the model release, click here. Usage of this model is subject to Meta's Acceptable Use Policy.
Arena Rank
#232
of 305 models
Time to First Token
1.5s
TTFT
Supported Parameters
Frequency Penalty
Reduce repetition
Logit Bias
Adjust token weights
Log Probs
Token probabilities
Max Tokens
Output length limit
Presence Penalty
Encourage new topics
Repetition Penalty
Penalize repeated tokens
Response Format
JSON mode / structured output
Seed
Deterministic outputs
Stop Sequences
Custom stop tokens
Temperature
Controls randomness
Tool Choice
Control tool usage
Tool Calling
Function calling support
Pricing Comparison
| Router | Input / 1M | Output / 1M | Cached Input / 1M |
|---|
| OpenRouter | $0.02 | $0.05 | — |
| Vercel AI | $0.03 | $0.05 | — |
| Martian | $0.02 | $0.05 | — |
| DeepInfra | $0.02 | $0.05 | — |
Benchmarks
Open LLM Leaderboard
AverageOpen LLM Leaderboard
24.02/100IFEvalOpen LLM Leaderboard
50.58/100BBHOpen LLM Leaderboard
29.19/100MATH Lvl 5Open LLM Leaderboard
15.48/100GPQAOpen LLM Leaderboard
9.51/100MUSROpen LLM Leaderboard
8.51/100MMLU-PROOpen LLM Leaderboard
30.86/100Artificial Analysis
Intelligence IndexArtificial Analysis
51/100Coding IndexArtificial Analysis
46/100Math IndexArtificial Analysis
54/100MMLU-PROArtificial Analysis
0.682/1GPQA DiamondArtificial Analysis
0.488/1MATH-500Artificial Analysis
0.738/1AIME 2024Artificial Analysis
0.097/1LiveCodeBenchArtificial Analysis
0.398/1SciCodeArtificial Analysis
0.162/1Aider Code Editing
Aider EditingAider Code Editing
26.3/100Model IDs
OpenRoutermeta-llama/llama-3.1-8b-instruct
Similar Models
Ranked by provider, pricing, capabilities, and arena performance