Open Ko-LLM Leaderboard
Indexed results from Open Ko-LLM Leaderboard. Each ranking retains its own metric and evaluation conditions.
kornat_harmless · acc_norm,none
openKoLLM · Open Ko-LLM Leaderboard · kornat_harmless · acc_norm,none · percent · Higher is better
- F24/llama-2-koen-orca-mini-platypus2-math-13bf24100%
- MoaData/Myrrh_solar_10.7b_3.0moadata88.803%
- tanitan2/SOLAR-10.7B-Instruct-T3Q-ko-solar-dpo-tiestanitan288.043%
- tanitan2/SOLAR-10.7B-Instruct-STOCK_SOLAR-tiestanitan288.033%
- chihoonlee10/T3Q-ko-solar-dpo-v7.0chihoonlee1086.627%
- freewheelin/free-solar-evo-v0.13freewheelin85.08%
- freewheelin/free-solar-evo-v0.11freewheelin83.853%
- freewheelin/free-solar-evo-v0.1freewheelin83.833%
- chihoonlee10/T3Q-ko-solar-dpo-v3.0chihoonlee1081.863%
- Edentns/DataVortexS-10.7B-dpo-v1.6edentns80.09%
- mlabonne/NeuralMonarch-7Bmlabonne79.697%
- chihoonlee10/T3Q-ko-solar-dpo-v1.0chihoonlee1079.68%
ko_gpqa_diamond_zeroshot · acc_norm,none
openKoLLM · Open Ko-LLM Leaderboard · ko_gpqa_diamond_zeroshot · acc_norm,none · percent · Higher is better
- BAAI/Infinity-Instruct-7M-Gen-Llama3_1-8Bbaai28.788%
- BAAI/Infinity-Instruct-7M-Gen-Llama3_1-8Bbaai28.788%
- chujiezheng/Mistral7B-PairRM-SPPO-ExPOchujiezheng28.788%
- princeton-nlp/gemma-2-9b-it-SimPOprinceton-nlp28.788%
- princeton-nlp/Mistral-7B-Base-SFT-RDPOprinceton-nlp28.788%
- v000000/Qwen2.5-14B-Gutenberg-1e-Deltav00000028.788%
- Magpie-Align/MagpieLM-8B-Chat-v0.1magpie-align28.283%
- anthracite-org/magnum-v3-27b-ktoanthracite-org27.778%
- cognitivecomputations/dolphin-2.9.3-mistral-nemo-12bcognitivecomputations27.778%
- princeton-nlp/Llama-3-Base-8B-SFT-DPOprinceton-nlp27.778%
- princeton-nlp/Llama-3-Instruct-8B-DPO-v0.2princeton-nlp27.778%
- v000000/Qwen2.5-14B-Gutenberg-Instruct-Slerpenov00000027.778%
ko_ifeval · prompt_level_strict_acc,none
openKoLLM · Open Ko-LLM Leaderboard · ko_ifeval · prompt_level_strict_acc,none · percent · Higher is better
- nbeerbower/gemma2-gutenberg-27Bnbeerbower72.065%
- byroneverson/gemma-2-27b-it-abliteratedbyroneverson69.636%
- recoilme/recoilme-gemma-2-9B-v0.2recoilme65.992%
- v000000/Qwen2.5-14B-Gutenberg-Instruct-Slerpenov00000065.182%
- v000000/Qwen2.5-14B-Gutenberg-1e-Deltav00000064.777%
- v000000/Qwen2.5-Lumen-14Bv00000064.777%
- rombodawg/Rombos-LLM-V2.6-Qwen-14brombodawg64.575%
- UCLA-AGI/Gemma-2-9B-It-SPPO-Iter1ucla-agi64.17%
- arcee-ai/SuperNova-Mediusarcee-ai63.968%
- UCLA-AGI/Gemma-2-9B-It-SPPO-Iter3ucla-agi63.563%
- Lambent/qwen2.5-reinstruct-alternate-lumen-14Blambent63.36%
- Qwen/Qwen2.5-14B-Instructqwen63.36%
kornat_common · acc_norm,none
openKoLLM · Open Ko-LLM Leaderboard · kornat_common · acc_norm,none · percent · Higher is better
- tanliboy/lambda-qwen2.5-14b-dpo-testtanliboy46.255%
- v000000/Qwen2.5-Lumen-14Bv00000040.097%
- v000000/Qwen2.5-14B-Gutenberg-Instruct-Slerpenov00000039.847%
- v000000/Qwen2.5-14B-Gutenberg-1e-Deltav00000039.68%
- Lambent/qwen2.5-reinstruct-alternate-lumen-14Blambent39.664%
- Qwen/Qwen2.5-14B-Instructqwen39.564%
- recoilme/recoilme-gemma-2-9B-v0.4recoilme39.314%
- rombodawg/Rombos-LLM-V2.6-Qwen-14brombodawg39.214%
- byroneverson/gemma-2-27b-it-abliteratedbyroneverson38.748%
- nbeerbower/gemma2-gutenberg-27Bnbeerbower38.049%
- arcee-ai/SuperNova-Mediusarcee-ai37.8%
- AALF/gemma-2-27b-it-SimPO-37K-100stepsaalf36.634%
ko_eqbench · eqbench,none
openKoLLM · Open Ko-LLM Leaderboard · ko_eqbench · eqbench,none · score · Higher is better
- recoilme/Gemma-2-Ataraxy-Gemmasutra-9B-slerprecoilme62.532
- UCLA-AGI/Gemma-2-9B-It-SPPO-Iter3ucla-agi62.403
- recoilme/recoilme-gemma-2-9B-v0.4recoilme61.433
- UCLA-AGI/Gemma-2-9B-It-SPPO-Iter2ucla-agi61.399
- UCLA-AGI/Gemma-2-9B-It-SPPO-Iter1ucla-agi61.391
- TheDrummer/Gemmasutra-9B-v1thedrummer60.302
- Saxo/Linkbricks-Horizon-AI-Korean-Superb-22Bsaxo59.769
- Lambent/qwen2.5-reinstruct-alternate-lumen-14Blambent59.258
- v000000/Qwen2.5-14B-Gutenberg-1e-Deltav00000059.251
- v000000/Qwen2.5-Lumen-14Bv00000059.227
- arcee-ai/SuperNova-Mediusarcee-ai59.129
- spow12/MK_Nemo_12Bspow1259.104
kornat_common · acc_norm,none
openKoLLM · Open Ko-LLM Leaderboard · kornat_common · acc_norm,none · percent · Higher is better
- chihoonlee10/T3Q-ko-solar-dpo-v7.0chihoonlee1050.766%
- MoaData/Myrrh_solar_10.7b_3.0moadata48.569%
- tanitan2/SOLAR-10.7B-Instruct-T3Q-ko-solar-dpo-tiestanitan244.391%
- tanitan2/SOLAR-10.7B-Instruct-STOCK_SOLAR-tiestanitan244.125%
- DopeorNope/Dear_My_best_Friends-13Bdopeornope40.446%
- Edentns/DataVortexS-10.7B-dpo-v1.10edentns39.947%
- freewheelin/free-solar-evo-v0.13freewheelin39.814%
- lemon-mint/gemma-ko-7b-instruct-v0.50lemon-mint39.547%
- Kukedlc/NeuralSynthesis-7B-v0.1kukedlc38.898%
- Gunulhona/Gemma-Ko-Mergegunulhona38.665%
- freewheelin/free-solar-evo-v0.11freewheelin38.465%
- Edentns/DataVortexS-10.7B-dpo-v1.7edentns38.199%
kornat_helpful · acc_norm,none
openKoLLM · Open Ko-LLM Leaderboard · kornat_helpful · acc_norm,none · percent · Higher is better
- tanliboy/lambda-qwen2.5-14b-dpo-testtanliboy66.4%
- v000000/Qwen2.5-Lumen-14Bv00000060.9%
- Qwen/Qwen2.5-14B-Instructqwen60.65%
- Lambent/qwen2.5-reinstruct-alternate-lumen-14Blambent60.475%
- v000000/Qwen2.5-14B-Gutenberg-1e-Deltav00000060.2%
- v000000/Qwen2.5-14B-Gutenberg-Instruct-Slerpenov00000060.05%
- rombodawg/Rombos-LLM-V2.6-Qwen-14brombodawg59.2%
- arcee-ai/SuperNova-Mediusarcee-ai58.625%
- huihui-ai/Qwen2.5-7B-Instruct-abliteratedhuihui-ai56.275%
- princeton-nlp/Llama-3-Base-8B-SFT-RDPOprinceton-nlp56.225%
- princeton-nlp/Llama-3-Instruct-8B-SimPO-v0.2princeton-nlp55.95%
- Magpie-Align/Llama-3.1-8B-Magpie-Align-v0.1magpie-align55.625%
kornat_social · A-SVA,none
openKoLLM · Open Ko-LLM Leaderboard · kornat_social · A-SVA,none · percent · Higher is better
- princeton-nlp/Llama-3-Instruct-8B-RDPO-v0.2princeton-nlp52.779%
- princeton-nlp/Llama-3-8B-ProLong-64k-Instructprinceton-nlp52.768%
- princeton-nlp/Llama-3-8B-ProLong-512k-Instructprinceton-nlp52.714%
- princeton-nlp/Llama-3-Instruct-8B-DPO-v0.2princeton-nlp52.672%
- princeton-nlp/Llama-3-8B-ProLong-64k-Baseprinceton-nlp52.384%
- princeton-nlp/Llama-3-Instruct-8B-SimPOprinceton-nlp52.242%
- princeton-nlp/Llama-3-8B-ProLong-512k-Baseprinceton-nlp52.233%
- arcee-ai/Llama-3.1-SuperNova-Litearcee-ai52.12%
- princeton-nlp/Llama-3-Instruct-8B-DPOprinceton-nlp52.113%
- Magpie-Align/Llama-3-8B-Magpie-Align-SFT-v0.3magpie-align52.088%
- Joseph717171/Llama-3.1-SuperNova-8B-Lite_TIES_with_Basejoseph71717152.078%
- hyemijo/omed-llama3.1-8bhyemijo52.034%
ko_ifeval · inst_level_strict_acc,none
openKoLLM · Open Ko-LLM Leaderboard · ko_ifeval · inst_level_strict_acc,none · percent · Higher is better
- ENERGY-DRINK-LOVE/rtzr_dpo-v4-hqenergy-drink-love67.953%
- Qwen: Qwen2.5 7B Instructqwen67.656%
- kayfour/T3Q-Qwen2.5-7B-it-KOR-Safekayfour67.507%
- Gunulhona/Gemma-Ko-Mergegunulhona59.644%
- vicgalle/Configurable-Llama-3.1-8B-Instructvicgalle59.644%
- v000000/L3.1-Niitorm-8B-DPO-t0.0001v00000057.567%
- lightblue/suzume-llama-3-8B-multilingual-orpo-borda-top25lightblue56.973%
- mlabonne/Daredevil-8B-abliteratedmlabonne56.528%
- Eurdem/Defne-llama3.1-8Beurdem55.638%
- lightblue/suzume-llama-3-8B-multilingual-orpo-borda-top75lightblue55.341%
- EpistemeAI/Fireball-Alpaca-Llama3.1.07-8B-Philos-Math-KTO-betaepistemeai55.193%
- vicgalle/Configurable-Llama-3-8B-v0.3vicgalle55.193%
kornat_helpful · acc_norm,none
openKoLLM · Open Ko-LLM Leaderboard · kornat_helpful · acc_norm,none · percent · Higher is better
- F24/llama-2-koen-orca-mini-platypus2-math-13bf24100%
- chihoonlee10/T3Q-ko-solar-dpo-v7.0chihoonlee1082.2%
- MoaData/Myrrh_solar_10.7b_3.0moadata82.125%
- tanitan2/SOLAR-10.7B-Instruct-T3Q-ko-solar-dpo-tiestanitan279.475%
- tanitan2/SOLAR-10.7B-Instruct-STOCK_SOLAR-tiestanitan279.4%
- freewheelin/free-solar-evo-v0.1freewheelin77.525%
- freewheelin/free-solar-evo-v0.13freewheelin76.8%
- freewheelin/free-solar-evo-v0.11freewheelin75.375%
- chihoonlee10/T3Q-ko-solar-dpo-v3.0chihoonlee1072.05%
- chihoonlee10/T3Q-ko-solar-dpo-v1.0chihoonlee1069.875%
- hwkwon/S-SOLAR-10.7B-v1.4hwkwon69.6%
- hkss/hk-SOLAR-10.7B-v1.4hkss69.45%
ko_eqbench · percent_parseable,none
openKoLLM · Open Ko-LLM Leaderboard · ko_eqbench · percent_parseable,none · percent · Higher is better
- 12thD/ko-Llama-3-8B-sft-v0.112thd89.474%
- 12thD/ko-Llama-3-8B-sft-v0.312thd89.474%
- AIdenU/SOLAR-10.7b-ko-Y24_v1.0aidenu89.474%
- lcw99/llama-3-8b-it-kor-extented-changlcw9989.474%
- OpenBuddy/openbuddy-llama3-8b-v21.1-8kopenbuddy89.474%
- PathFinderKR/Waktaverse-Llama-3-KO-8B-Instructpathfinderkr89.474%
- richard-park/llama3-deepspeed-v1.0richard-park89.474%
- SeaLLMs/SeaLLM-7B-v2.5seallms89.474%
- sinjy1203/EEVE-Korean-Instruct-10.8B-v1.0-Grade-Retrievalsinjy120389.474%
- T3Q-LLM/T3Q-LLM-sft1.0-dpo1.0t3q-llm89.474%
- T3Q-LLM/T3Q-LLM-solar10.8-sft-v1.0t3q-llm89.474%
- yanolja/Bookworm-10.7B-v0.4-DPOyanolja89.474%
ko_gpqa_diamond_zeroshot · acc_norm,none
openKoLLM · Open Ko-LLM Leaderboard · ko_gpqa_diamond_zeroshot · acc_norm,none · percent · Higher is better
- T3Q-LLM/T3Q-LLM1-sft1.0-dpo1.0t3q-llm31.313%
- ai-human-lab/EEVE-Korean-10.8B-DPO-v1.0ai-human-lab30.303%
- gwonny/nox-solar-10.7b-v4-kolon-all-10gwonny29.798%
- jungyuko/DAVinCI-42dot_LLM-PLM-1.3B-v1.5.3jungyuko29.798%
- MoaData/Myrrh_solar_10.7b_3.0moadata29.798%
- Alphacode-AI/Alphallama3-8B_v2alphacode-ai29.293%
- DopeorNope/SOLAR_C-v1-10.7Bdopeornope29.293%
- freewheelin/free-solar-evo-v0.13freewheelin29.293%
- metterian/llama-2-ko-7b-ptmetterian29.293%
- tanitan2/SOLAR-10.7B-Instruct-T3Q-ko-solar-dpo-tiestanitan229.293%
- v000000/L3.1-Niitorm-8B-DPO-t0.0001v00000029.293%
- Alphacode-AI/Alphacode-MALI-11Balphacode-ai28.788%
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.