Open Ko-LLM Leaderboard
Indexed results from Open Ko-LLM Leaderboard. Each ranking retains its own metric and evaluation conditions.
ko_ifeval · prompt_level_loose_acc,none
openKoLLM · Open Ko-LLM Leaderboard · ko_ifeval · prompt_level_loose_acc,none · percent · Higher is better
kornat_common · acc_norm,none
openKoLLM · Open Ko-LLM Leaderboard · kornat_common · acc_norm,none · percent · Higher is better
kornat_social · A-SVA,none
openKoLLM · Open Ko-LLM Leaderboard · kornat_social · A-SVA,none · percent · Higher is better
- VIRNECT/llama-3-Korean-8B-r-v-0.1virnect52.515%
- lightblue/suzume-llama-3-8B-japaneselightblue52.349%
- mlabonne/Daredevil-8B-abliteratedmlabonne52.247%
- chlee10/T3Q-Llama3-8B-sft1.0-dpo1.0chlee1052.235%
- chlee10/T3Q-Llama3-8B-Inst-sft1.0chlee1052.213%
- v000000/L3.1-Niitorm-8B-DPO-t0.0001v00000052.153%
- lightblue/suzume-llama-3-8B-multilinguallightblue52.117%
- lightblue/suzume-llama-3-8B-multilinguallightblue52.117%
- Magpie-Align/Llama-3-8B-Magpie-Align-SFT-v0.3magpie-align52.06%
- migtissera/Llama-3-8B-Synthia-v3.5migtissera51.993%
- AIDX-ktds/ktdsbaseLM-v0.15-onbased-llama3.1aidx-ktds51.982%
- AIDX-ktds/ktdsbaseLM-v0.16-onbased-llama3.1aidx-ktds51.982%
ko_winogrande · acc,none
openKoLLM · Open Ko-LLM Leaderboard · ko_winogrande · acc,none · percent · Higher is better
- tanitan2/SOLAR-10.7B-Instruct-STOCK_SOLAR-tiestanitan276.953%
- tanitan2/SOLAR-10.7B-Instruct-T3Q-ko-solar-dpo-tiestanitan276.875%
- chihoonlee10/T3Q-ko-solar-dpo-v7.0chihoonlee1076.085%
- MoaData/Myrrh_solar_10.7b_3.0moadata76.085%
- chihoonlee10/T3Q-ko-solar-dpo-v3.0chihoonlee1075.138%
- chihoonlee10/T3Q-ko-solar-dpo-v1.0chihoonlee1074.27%
- hkss/hk-SOLAR-10.7B-v1.4hkss74.191%
- hwkwon/S-SOLAR-10.7B-v1.4hwkwon74.112%
- davidkim205/nox-solar-10.7b-v4davidkim20573.875%
- davidkim205/nox-solar-10.7b-v4davidkim20573.875%
- freewheelin/free-solar-evo-v0.13freewheelin73.56%
- gwonny/nox-solar-10.7b-v4-kolon-ITD-5-v2.0gwonny73.086%
ko_ifeval · prompt_level_strict_acc,none
openKoLLM · Open Ko-LLM Leaderboard · ko_ifeval · prompt_level_strict_acc,none · percent · Higher is better
- ENERGY-DRINK-LOVE/rtzr_dpo-v4-hqenergy-drink-love60.324%
- Qwen: Qwen2.5 7B Instructqwen60.324%
- kayfour/T3Q-Qwen2.5-7B-it-KOR-Safekayfour60.121%
- Gunulhona/Gemma-Ko-Mergegunulhona50.81%
- vicgalle/Configurable-Llama-3.1-8B-Instructvicgalle50.202%
- lightblue/suzume-llama-3-8B-multilingual-orpo-borda-top25lightblue48.583%
- Eurdem/Defne-llama3.1-8Beurdem48.178%
- v000000/L3.1-Niitorm-8B-DPO-t0.0001v00000048.178%
- mlabonne/Daredevil-8B-abliteratedmlabonne47.976%
- lightblue/suzume-llama-3-8B-multilingual-orpo-borda-top75lightblue47.166%
- vicgalle/Configurable-Llama-3-8B-v0.3vicgalle45.951%
- 4yo1/llama3-eng-ko-8b-sl54yo145.749%
ko_ifeval · inst_level_strict_acc,none
openKoLLM · Open Ko-LLM Leaderboard · ko_ifeval · inst_level_strict_acc,none · percent · Higher is better
ko_gpqa_diamond_zeroshot · acc_norm,none
openKoLLM · Open Ko-LLM Leaderboard · ko_gpqa_diamond_zeroshot · acc_norm,none · percent · Higher is better
ko_gsm8k · exact_match,strict-match
openKoLLM · Open Ko-LLM Leaderboard · ko_gsm8k · exact_match,strict-match · percent · Higher is better
ko_eqbench · eqbench,none
openKoLLM · Open Ko-LLM Leaderboard · ko_eqbench · eqbench,none · score · Higher is better
- ENERGY-DRINK-LOVE/rtzr_dpo-v4-hqenergy-drink-love59.525
- T3Q-LLM/T3Q-LLM-sft1.0-dpo1.0t3q-llm55.307
- ai-human-lab/EEVE-Korean_Instruct-10.8B-expoai-human-lab53.588
- T3Q-LLM/T3Q-LLM1-CV-v2.0t3q-llm52.709
- algograp-Inc/algograpV4algograp-inc52.048
- T3Q-LLM/T3Q-LLM-solar10.8-sft-v1.0t3q-llm51.863
- T3Q-LLM/T3Q-LLM1-CV-v1.0t3q-llm51.756
- yanolja/EEVE-Korean-Instruct-10.8B-v1.0yanolja51.668
- kayfour/T3Q-gemma2-9B-it-Ko-safekayfour51.014
- sinjy1203/EEVE-Korean-Instruct-10.8B-v1.0-Grade-Retrievalsinjy120349.544
- cognitivecomputations/dolphin-2.9.3-mistral-nemo-12bcognitivecomputations48.53
- maywell/Mini_Synatra_SFTmaywell47.919
ko_winogrande · acc,none
openKoLLM · Open Ko-LLM Leaderboard · ko_winogrande · acc,none · percent · Higher is better
ko_eqbench · percent_parseable,none
openKoLLM · Open Ko-LLM Leaderboard · ko_eqbench · percent_parseable,none · percent · Higher is better
- Phi-3-medium-128k-instructmicrosoft90.058%
- AALF/gemma-2-27b-it-SimPO-37K-100stepsaalf89.474%
- Cran-May/T.E-8.1cran-may89.474%
- Lambent/qwen2.5-reinstruct-alternate-lumen-14Blambent89.474%
- migtissera/Tess-3-Mistral-Nemo-12Bmigtissera89.474%
- migtissera/Tess-v2.5-Gemma-2-27B-alphamigtissera89.474%
- migtissera/Trinity-2-Codestral-22Bmigtissera89.474%
- nbeerbower/gemma2-gutenberg-27Bnbeerbower89.474%
- princeton-nlp/Llama-3-Instruct-8B-IPOprinceton-nlp89.474%
- recoilme/Gemma-2-Ataraxy-Gemmasutra-9B-slerprecoilme89.474%
- rombodawg/rombos_Replete-Coder-Llama3-8Brombodawg89.474%
- VAGOsolutions/SauerkrautLM-Phi-3-mediumvagosolutions89.474%
ko_ifeval · prompt_level_loose_acc,none
openKoLLM · Open Ko-LLM Leaderboard · ko_ifeval · prompt_level_loose_acc,none · percent · Higher is better
- nbeerbower/gemma2-gutenberg-27Bnbeerbower72.874%
- byroneverson/gemma-2-27b-it-abliteratedbyroneverson71.66%
- recoilme/recoilme-gemma-2-9B-v0.2recoilme69.028%
- arcee-ai/SuperNova-Mediusarcee-ai68.826%
- v000000/Qwen2.5-Lumen-14Bv00000067.611%
- rombodawg/Rombos-LLM-V2.6-Qwen-14brombodawg67.409%
- v000000/Qwen2.5-14B-Gutenberg-1e-Deltav00000067.206%
- v000000/Qwen2.5-14B-Gutenberg-Instruct-Slerpenov00000067.206%
- tanliboy/lambda-qwen2.5-14b-dpo-testtanliboy67.004%
- Lambent/qwen2.5-reinstruct-alternate-lumen-14Blambent66.599%
- Qwen/Qwen2.5-14B-Instructqwen66.397%
- UCLA-AGI/Gemma-2-9B-It-SPPO-Iter1ucla-agi65.992%
Models
LoadingBenchmarks
Explore every benchmark
LoadingThese charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.