Meta · model passport
Llama 2 70b Chat
llama-2-70b-chat- Open weights
- Llama 2 Community licence
- Released 2023-07-18(curated)
- Overall · LMArena
- 1,171#347 of 396
- Best percentile
- 12.6Overall
- Cohort standing
- 27.9median 26.0
What the data says
Benchmarked on 4 of 27 tracked axes. Every figure below is the model's own published result on that board.
Weakest axes
- 9.7 pct — Coding (1,179)
- 11.4 pct — Hard prompts (1,161)
- 11.6 pct — Instruction following (1,135)
Uneven: 2.9 percentile points between its best and worst axis — 12.6 pct on Overall versus 9.7 pct on Coding.
- Overall12.6 pct1,171Verify →
- Instruction following11.6 pct1,135Verify →
- Hard prompts11.4 pct1,161Verify →
- Coding9.7 pct1,179Verify →
- WebDev ArenaNot benchmarked
- Vision ArenaNot benchmarked
- Factuality ArenaNot benchmarked
- Search ArenaNot benchmarked
- Document ArenaNot benchmarked
- Agent ArenaNot benchmarked
- GPQA DiamondNot benchmarked
- AIME (math)Not benchmarked
- FrontierMathNot benchmarked
- SimpleQA VerifiedNot benchmarked
- ARC-AGI-2Not benchmarked
- Humanity's Last ExamNot benchmarked
- SimpleBenchNot benchmarked
- LiveBenchNot benchmarked
- BFCL v4 (function calling)Not benchmarked
- SWE-bench Verified (live board)Not benchmarked
- Terminal-Bench 4.0Not benchmarked
- MMLU-Pro (Artificial Analysis)Not benchmarked
- LiveCodeBench (Artificial Analysis)Not benchmarked
- IFBench (Artificial Analysis)Not benchmarked
- HHEM Hallucination (Vectara)Not benchmarked
- SWE-bench VerifiedNot benchmarked
- Terminal-BenchNot benchmarked
Percentiles are the model's standing within each board's own population. Axes marked "not benchmarked" have no published result for this model — that is an absence of data, not a low score.
How to run it
Run it yourself
Transformers
from transformers import AutoModelForCausalLM, AutoTokenizer
model_id = "meta-llama/Llama-2-70b-chat"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id)Ollama
We don't sync Ollama tags, so we won't print a command we can't verify — a wrong one would pull the wrong model. Search the Ollama library →
Unsloth fine-tuning recipes are model-specific and we don't derive them here. Unsloth docs →
Identifiers, limits and prices are synced from the upstream source shown above. Any field we haven't synced is left out entirely rather than guessed.
llama-2-70b-chat stands at 27.9 (raw mean 11.3) — measured on 4 of 27 axes.
llama-2-70b-chat stands at 27.9 versus a cohort median of 26 across 49 models released within 180 days — above the peer median.
llama-2-70b-chat scores at percentile 9.7 on Coding.
llama-2-70b-chat scores at percentile 11.4 on Hard prompts.
llama-2-70b-chat ranks between #363 and #753 across 5 built-in weightings — best under "Conversation-first", worst under "All sources".
Every claim is a computed fact from the current board data, phrased by a low-temperature model call and rejected by a validation gate if any number is not in the source row. How the leaderboards work →