Open LLM Leaderboard v1
Indexed results from Open LLM Leaderboard v1 · Archive. Each ranking retains its own metric and evaluation conditions.
Open LLM v1 ARC
openLLMLeaderboardV1 · Open LLM Leaderboard v1 · Accuracy · percent
- DopeorNope/COKAL-v1-70Bdopeornope87.457%
- freewheelin/free-evo-qwen72b-v0.8freewheelin79.863%
- freewheelin/free-evo-qwen72b-v0.8-refreewheelin79.863%
- SF-Foundation/Ein-70B-v2sf-foundation79.863%
- davidkim205/Rhea-72b-v0.5davidkim20579.778%
- 4season/alignment-model-test104season79.608%
- 4season/merge_model_test_v24season79.352%
- kimdeokgi/merge_model_test2kimdeokgi79.352%
- kimdeokgi/merge_model_test1kimdeokgi78.925%
- MTSAIR/MultiVerse_70Bmtsair78.669%
- MTSAIR/MultiVerse_70Bmtsair78.584%
- davidkim205/Rhea-72b-v0.4davidkim20578.498%
Open LLM v1 Average
openLLMLeaderboardV1 · Open LLM Leaderboard v1 · Six-task average · percent
- paloalma/Le_Triomphant-ECE-TW3paloalma81.305%
- SF-Foundation/Ein-70B-v2sf-foundation81.292%
- freewheelin/free-evo-qwen72b-v0.8freewheelin81.284%
- freewheelin/free-evo-qwen72b-v0.8-refreewheelin81.284%
- davidkim205/Rhea-72b-v0.5davidkim20581.224%
- Contamination/contaminated_proof_7b_v1.0contamination81.135%
- Contamination/contaminated_proof_7b_v1.0_safetensorcontamination81.135%
- davidkim205/Rhea-72b-v0.4davidkim20581.088%
- MTSAIR/MultiVerse_70Bmtsair81.004%
- binbi/Ein-72B-v0.1binbi80.99%
- MTSAIR/MultiVerse_70Bmtsair80.976%
- davidkim205/Rhea-72b-v0.2davidkim20580.948%
Open LLM v1 GSM8K
openLLMLeaderboardV1 · Open LLM Leaderboard v1 · Accuracy · percent
- MaziyarPanahi/Llama-3-70B-Instruct-DPO-v0.2maziyarpanahi88.249%
- mmnga/Llama-3-70B-japanese-suzume-vector-v0.1mmnga87.415%
- MaziyarPanahi/Llama-3-70B-Instruct-DPO-v0.4maziyarpanahi87.339%
- MaziyarPanahi/Llama-3-70B-Instruct-DPO-v0.3maziyarpanahi87.187%
- tenyx/Llama3-TenyxChat-70Btenyx86.277%
- MaziyarPanahi/Llama-3-70B-Instruct-DPO-v0.1maziyarpanahi86.05%
- abhishek/autotrain-llama3-70b-orpo-v1abhishek85.671%
- Meta-Llama-3-70B-Instructmeta-llama85.444%
- failspy/llama-3-70B-Instruct-abliteratedfailspy85.292%
- Qwen/Qwen2-72Bqwen85.292%
- failspy/llama-3-70B-Instruct-abliteratedfailspy85.216%
- abhishek/autotrain-llama3-70b-orpo-v2abhishek84.23%
Open LLM v1 HellaSwag
openLLMLeaderboardV1 · Open LLM Leaderboard v1 · Accuracy · percent
- swap-uniba/LLaMAntino-3-ANITA-8B-Inst-DPO-ITAswap-uniba92.75%
- saltlux/luxia-21.4b-alignment-v1.0saltlux91.884%
- saltlux/luxia-21.4b-alignment-v0.4saltlux91.834%
- saltlux/luxia-21.4b-alignment-v1.0saltlux91.824%
- fblgit/UNA-ThePitbull-21.4-v1fblgit91.814%
- fblgit/UNA-ThePitbull-21.4B-v2fblgit91.794%
- saltlux/luxia-21.4b-alignment-v0.1saltlux91.794%
- saltlux/luxia-21.4b-alignment-v0.2saltlux91.605%
- saltlux/luxia-21.4b-alignment-v0.3saltlux91.526%
- SF-Foundation/Ein-70B-v2sf-foundation91.486%
- freewheelin/free-evo-qwen72b-v0.8freewheelin91.336%
- freewheelin/free-evo-qwen72b-v0.8-refreewheelin91.336%
Open LLM v1 MMLU
openLLMLeaderboardV1 · Open LLM Leaderboard v1 · Accuracy · percent
- AA051611/O0201aa05161189.352%
- AA051611/V0201aa05161188.78%
- AA051615/A0204aa05161586.856%
- AA051612/A0125aa05161286.636%
- AA051611/V0202aa05161186.318%
- 8xqmff94/slm8xqmff9486.109%
- AA051612/B0121aa05161285.627%
- CausalLM/34b-betacausallm85.602%
- AA051610/A0127aa05161084.9%
- AA051615/A0304aa05161584.505%
- AA051615/A0221aa05161584.475%
- AA051615/A0308-Gaa05161584.066%
Open LLM v1 TruthfulQA
openLLMLeaderboardV1 · Open LLM Leaderboard v1 · Accuracy · percent
- Contamination/contaminated_proof_7b_v1.0contamination82.294%
- Contamination/contaminated_proof_7b_v1.0_safetensorcontamination82.294%
- cloudyu/Mixtral_7Bx2_MoE_DPOcloudyu81.498%
- saltlux/luxia-21.4b-alignment-v1.1saltlux80.909%
- 4season/alignment_model_test4season80.884%
- 4season/alignment-model-test34season80.884%
- saltlux/luxia-21.4b-alignment-v1.1saltlux80.884%
- x2bee/POLAR-14B-v0.2x2bee80.812%
- kihoonlee/stock-solar-10.7b-v1kihoonlee80.493%
- TwT-6/cr-model-v1twt-680.47%
- chihoonlee10/T3Q-ko-solar-dpo-v6.0chihoonlee1080.431%
- krevas/SOLAR-10.7Bkrevas80.325%
Open LLM v1 Winogrande
openLLMLeaderboardV1 · Open LLM Leaderboard v1 · Accuracy · percent
- udkai/Garrulusudkai91.476%
- zhengr/MixTAO-7Bx2-MoE-Instruct-v4.0zhengr90.923%
- zhengr/MixTAO-7Bx2-MoE-Instruct-v6.0zhengr89.266%
- RubielLabarta/LogoS-7Bx2-MoE-13B-v0.2rubiellabarta88.398%
- HanNayeoniee/LHK_DPO_v1hannayeoniee88.319%
- RubielLabarta/LogoS-7Bx2-MoE-13B-v0.1rubiellabarta88.319%
- yunconglong/Truthful_DPO_TomGrc_FusionNet_7Bx2_MoE_13Byunconglong88.24%
- Contamination/contaminated_proof_7b_v1.0contamination88.161%
- Contamination/contaminated_proof_7b_v1.0_safetensorcontamination88.161%
- HanNayeoniee/LHK_DPO_v1hannayeoniee88.161%
- TomGrc/FusionNet_7Bx2_MoE_14Btomgrc88.161%
- yunconglong/DARE_TIES_13Byunconglong88.082%
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.