Codesota · Models · meta-llama/Llama-3.3-70B-Instructmeta-llama18 results · 4 benchmarks
Model card

meta-llama/Llama-3.3-70B-Instruct.

meta-llamaopen-weights70.6B params
§ 02 · Benchmarks

Every benchmark meta-llama/Llama-3.3-70B-Instruct has a recorded score for.

#BenchmarkArea · TaskMetricValueRankDateSource
01Open PL LLM LeaderboardNatural Language Processing · Polish LLM Generalbelebele92.6%#4/490—source ↗
02Open PL LLM LeaderboardNatural Language Processing · Polish LLM Generalklej-ner-generative60.9%#7/489—source ↗
03Open PL LLM LeaderboardNatural Language Processing · Polish LLM Generaldyk71.5%#8/489—source ↗
04Open PL LLM LeaderboardNatural Language Processing · Polish LLM Generalaverage66.4%#8/491—source ↗
05Open PL LLM LeaderboardNatural Language Processing · Polish LLM Generalpolemo2-in87.1%#12/490—source ↗
06CPTU-BenchNatural Language Processing · Polish Text Understandingsentiment4.3%#13/93—source ↗
07Open PL LLM LeaderboardNatural Language Processing · Polish LLM Generalklej-ner-mc59.4%#15/490—source ↗
08Open PL LLM LeaderboardNatural Language Processing · Polish LLM Generalpoquad-open-book72.0%#16/337—source ↗
09Polish EQ-BenchNatural Language Processing · Polish Emotional Intelligenceeq-score70.7%#18/101—source ↗
10Open PL LLM LeaderboardNatural Language Processing · Polish LLM Generalppc79.9%#19/490—source ↗
11Open PL LLM LeaderboardNatural Language Processing · Polish LLM Generaleq-bench61.8%#21/299—source ↗
12HumanEvalComputer Code · Code Generationpass@188.4%#22/422024-12-01source ↗
13CPTU-BenchNatural Language Processing · Polish Text Understandinglanguage-understanding3.9%#28/93—source ↗
14CPTU-BenchNatural Language Processing · Polish Text Understandingtricky-questions3.4%#30/93—source ↗
15CPTU-BenchNatural Language Processing · Polish Text Understandingaverage3.6%#31/93—source ↗
16Open PL LLM LeaderboardNatural Language Processing · Polish LLM Generalcbd36.7%#33/490—source ↗
17CPTU-BenchNatural Language Processing · Polish Text Understandingphraseology3.0%#62/93—source ↗
18Open PL LLM LeaderboardNatural Language Processing · Polish LLM Generalpolqa-open-book88.6%#92/489—source ↗
Rank column shows this model’s position vs all other models scored on the same benchmark + metric (competitors after the slash). #1 in red means current SOTA. Sorted by rank, then newest result.
§ 03 · Strengths by area

Where meta-llama/Llama-3.3-70B-Instruct actually performs.

Computer Code
1
benchmark
avg rank #22.0
Natural Language Processing
3
benchmarks
avg rank #24.5
§ 05 · Related models

Other meta-llama models scored on Codesota.

Llama-2-7b-chat-hf
0 results
Llama-2-7b-hf
0 results
Llama-3.2-1B
0 results
Llama-3.2-3B
0 results
Llama-4-Scout-17B-16E
0 results
Meta-Llama-3-70B
0 results
Meta-Llama-3-8B
0 results
Meta-Llama-3.1-405B-Instruct-FP8
0 results
§ 06 · Sources & freshness

Where these numbers come from.

speakleash/open_pl_llm_leaderboard
11
results
SpeakLeash/CPTU-Bench
5
results
SpeakLeash/Polish-EQ-Bench
1
result
shadow-page-humaneval
1
result
18 of 18 rows marked verified.