Codesota · Models · THUDM/glm-4-9b-chatTHUDM17 results · 3 benchmarks
Model card

THUDM/glm-4-9b-chat.

THUDMopen-weights9.4B params
§ 02 · Benchmarks

Every benchmark THUDM/glm-4-9b-chat has a recorded score for.

#BenchmarkArea · TaskMetricValueRankDateSource
01Polish EQ-BenchNatural Language Processing · Polish Emotional Intelligenceeq-score61.8%#29/101—source ↗
02CPTU-BenchNatural Language Processing · Polish Text Understandinglanguage-understanding3.5%#53/93—source ↗
03Open PL LLM LeaderboardNatural Language Processing · Polish LLM Generaleq-bench53.8%#55/299—source ↗
04CPTU-BenchNatural Language Processing · Polish Text Understandingsentiment3.6%#56/93—source ↗
05Open PL LLM LeaderboardNatural Language Processing · Polish LLM Generaldyk67.0%#59/489—source ↗
06CPTU-BenchNatural Language Processing · Polish Text Understandingaverage3.0%#65/93—source ↗
07CPTU-BenchNatural Language Processing · Polish Text Understandingtricky-questions2.0%#65/93—source ↗
08CPTU-BenchNatural Language Processing · Polish Text Understandingphraseology2.8%#68/93—source ↗
09Open PL LLM LeaderboardNatural Language Processing · Polish LLM Generalpoquad-open-book68.2%#73/337—source ↗
10Open PL LLM LeaderboardNatural Language Processing · Polish LLM Generalpolemo2-in81.6%#86/490—source ↗
11Open PL LLM LeaderboardNatural Language Processing · Polish LLM Generalaverage56.6%#88/491—source ↗
12Open PL LLM LeaderboardNatural Language Processing · Polish LLM Generalbelebele86.6%#89/490—source ↗
13Open PL LLM LeaderboardNatural Language Processing · Polish LLM Generalklej-ner-generative51.4%#100/489—source ↗
14Open PL LLM LeaderboardNatural Language Processing · Polish LLM Generalklej-ner-mc49.6%#118/490—source ↗
15Open PL LLM LeaderboardNatural Language Processing · Polish LLM Generalppc73.6%#147/490—source ↗
16Open PL LLM LeaderboardNatural Language Processing · Polish LLM Generalcbd27.9%#177/490—source ↗
17Open PL LLM LeaderboardNatural Language Processing · Polish LLM Generalpolqa-open-book82.7%#250/489—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 THUDM/glm-4-9b-chat actually performs.

Natural Language Processing
3
benchmarks
avg rank #92.8
§ 05 · Related models

Other THUDM models scored on Codesota.

chatglm3-6b
0 results
chatglm3-6b-base
0 results
glm-4-9b
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
17 of 17 rows marked verified.