Open LLM Leaderboard v1
Indexed results from Open LLM Leaderboard v1 · Archive. Each ranking retains its own metric and evaluation conditions.
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%
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.