Skip to content
Arena
Leaderboard

llama3-70b-instruct

Metaopen weightsinactiveThis model is no longer in battles and gets no new votes.

Licence
Llama 3 Community License
ID
meta/llama3-70b-instruct

llama3-70b-instruct no longer takes part in new comparisons. Its rating of 749 (±174) was set by the 20 votes cast while it took part. The rating's 95% interval is 575–923: it shows how precisely the votes have pinned the rating down so far. It won 15.8% of its decided comparisons (3 wins, 16 losses, 1 tie). The median length of its answers is 168 words. It is developed by Meta. Its weights are open (licence: Llama 3 Community License).

At a glance

Rating
749±174
95% interval 575–923
Answer length
168words
median, typically 9–305
Votes
20
15.8% of decided votes won

Model information

Note: The model is made available in the arena via the NVIDIA NIM API.

More about the model (opens in a new tab)

Statistics

Rating with 95% confidence interval

  1. gpt-oss-20b
  2. Mistral-Small-24B-Instruct-2501inactive
  3. bielik-11b-v2.3-instructinactive
  4. llama3-70b-instructinactive
  5. nemotron-3.5-lightning-30b-a3binactive

The models just above and below it on the leaderboard, on one axis. The upright mark is the rating, the line its 95% interval.

Vote outcomes

  • Wins3
  • Ties1
  • Losses16
Total queries
41

Answer length among models

Median words per answer for every model on the leaderboard, on one axis.

Longer answers than 17 of 30 other models.

All models in numbers
ModelMedian words
gpt-oss-120b463
Ministral-3-14B-Instruct-2512348
deepseek-r1336
gemini-2.5-pro330
Qwen3-Next-80B-A3B-Instruct312
gpt-oss-20b285
gemini-3-pro-preview260
gemini-2.5-flash242
GaMS-9B-Instruct-Nemotron236
GaMS-27B-Instruct-Nemotron226
Mistral-Large-3-675B-Instruct-2512224
deepseek-r1-0528216
GaMS3-12B-Instruct200
llama3-70b-instruct168
gpt-5-mini162
kimi-k2-instruct142
Mistral-Small-24B-Instruct-2501110
gpt-5107
gemma-3-12b-it107
bielik-11b-v2.3-instruct104
gemma-3-27b-it101
gemini-1.5-pro100
llama-4-scout-17b-16e-instruct91
llama-3.3-70b-instruct90
EuroLLM-9B-Instruct83
gemini-2.0-flash78
llama-4-maverick-17b-128e-instruct78
gpt-4o68
Zlatorog-12B-Instruct-Beta47
GaMS-9B-Instruct13
GaMS-27B-Instruct10