Codesota · Models · SmolLM2-1.7B-InstructHuggingFaceTB12 results · 2 benchmarks
Model card

SmolLM2-1.7B-Instruct.

HuggingFaceTBopen-source1.71B params
§ 01 · Benchmarks

Every benchmark SmolLM2-1.7B-Instruct has a recorded score for.

#BenchmarkArea · TaskMetricValueRankDateSource
01CPTU-BenchNatural Language Processing · Polish Text Understandingphraseology2.4%#83/93—source ↗
02CPTU-BenchNatural Language Processing · Polish Text Understandingsentiment2.3%#90/93—source ↗
03CPTU-BenchNatural Language Processing · Polish Text Understandingtricky-questions0.3%#90/93—source ↗
04CPTU-BenchNatural Language Processing · Polish Text Understandingaverage1.5%#92/93—source ↗
05CPTU-BenchNatural Language Processing · Polish Text Understandinglanguage-understanding1.1%#92/93—source ↗
06Open PL LLM LeaderboardNatural Language Processing · Polish LLM Generaldyk29.8%#420/489—source ↗
07Open PL LLM LeaderboardNatural Language Processing · Polish LLM Generalcbd15.8%#432/490—source ↗
08Open PL LLM LeaderboardNatural Language Processing · Polish LLM Generalbelebele33.0%#444/490—source ↗
09Open PL LLM LeaderboardNatural Language Processing · Polish LLM Generalpolemo2-in49.2%#449/490—source ↗
10Open PL LLM LeaderboardNatural Language Processing · Polish LLM Generalpolqa-open-book46.3%#477/489—source ↗
11Open PL LLM LeaderboardNatural Language Processing · Polish LLM Generalaverage3.0%#480/491—source ↗
12Open PL LLM LeaderboardNatural Language Processing · Polish LLM Generalppc22.4%#484/490—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.
§ 02 · Strengths by area

Where SmolLM2-1.7B-Instruct actually performs.

Natural Language Processing
2
benchmarks
avg rank #302.8
§ 05 · Sources & freshness

Where these numbers come from.

speakleash/open_pl_llm_leaderboard
7
results
SpeakLeash/CPTU-Bench
5
results
12 of 12 rows marked verified.