Meta AIopen-weight
Released: 2024-12-06Llama 3.3 70B
Meta highly efficient 70B parameter open-weight model matching earlier 405B capabilities across general benchmarks.
Intelligence Index
80.9/ 100
Calibrated multi-domain compositeThroughput Speed
72tok/sec
Output streaming throughputTime To First Token
350ms
Initial chunk server latencyLiveBench Contam-Free
65.2%
September 2026 suite scoreLiveBench Multi-Domain Evaluation Breakdown
Monthly refreshed contamination-free test setsLogical Reasoning79.5%
Coding & Repo Repair65.1%
Mathematics (AIME)76.2%
Data Analysis & Tables73.0%
Language & Comprehension79.0%
Instruction Following86.2%
Sourced Benchmark Evaluations (3)
Verified performance across authoritative benchmarks with provenance tracking.Local Hardware Execution (Ollama)Hardware Compatible
# 1. Pull and execute model locally with Ollama
ollama run llama-3-3-70b
# 2. Or invoke via local OpenAI-compatible endpoint
curl http://localhost:11434/v1/chat/completions \
-H "Content-Type: application/json" \
-d '{
"model": "llama-3-3-70b",
"messages": [{"role": "user", "content": "Analyze reasoning chains on AIME 2026"}]
}'Evaluation & Sourcing Notes
Scores listed for Llama 3.3 70B represent verified evaluations extracted from official research papers, independent evaluation suites (HELM, LMSYS, OpenCompass, LiveBench), and verified audit reports.
All benchmarks marked as saturated or deprecated reflect historical performance where the benchmark no longer provides active discriminative power.