Clémentine
POC, v0
84b5dfa
raw
history blame
3.56 kB
"""
Default leaderboards with which we initialize the space.
"""
leaderboard_to_tags = {
"HuggingFaceH4/open_llm_leaderboard": ["submission:automatic", "judge:auto", "test:public", "modality:text", "eval:math"],
"bigcode/bigcode-models-leaderboard": ["submission:semiautomatic", "judge:auto", "test:public", "eval:code"],
"optimum/llm-perf-leaderboard": ["submission:manual", "judge:auto", "eval:performance"],
"lmsys/chatbot-arena-leaderboard": ["judge:humans", "modality:text", "eval:generation"],
"llmonitor/benchmarks": ["submission:manual", "judge:humans", "modality:text", "judge:vibe_check"],
"mteb/leaderboard": ["submission:semiautomatic", "modality:text", "Embeddings", "modality:artefacts"],
"gaia-benchmark/leaderboard": ["submission:automatic", "test:private", "judge:auto", "modality:text", "modality:tools", "modality:text", "modality:image", "modality:video"],
"opencompass/opencompass-llm-leaderboard": ["submission:manual", "modality:text", "language:chinese"],
"upstage/open-ko-llm-leaderboard": ["submission:automatic", "judge:auto", "test:mix", "modality:text", "language:korean"],
"BramVanroy/open_dutch_llm_leaderboard": ["submission:manual", "judge:auto", "modality:text", "language:dutch"],
"vectara/leaderboard": ["submission:semiautomatic", "judge:model", "modality:text", "Hallucinations"],
"facebook/CyberSecEval": ["submission:closed", "eval:code", "eval:safety"],
"mlabonne/Yet_Another_LLM_Leaderboard": ["submission:manual", "modality:text", "judge:auto"],
"AI-Secure/llm-trustworthy-leaderboard": ["submission:automatic", "eval:safety", "modality:text"],
"AILab-CVC/EvalCrafter": ["submission:closed", "modality:video", "eval:generation"],
"mike-ravkine/can-ai-code-results": ["submission:closed", "eval:code"],
"echo840/ocrbench-leaderboard": ["submission:closed", "modality:image", "OCR"],
"NPHardEval/NPHardEval-leaderboard": ["submission:closed", "modality:text", "eval:math", "test:rolling"],
"HaizeLabs/red-teaming-resistance-benchmark": ["submission:manual", "eval:safety", "modality:text"],
"devingulliver/subquadratic-llm-leaderboard": ["submission:semiautomatic", "modality:text", "eval:math"],
"WildVision/vision-arena": ["modality:image", "modality:text", "judge:humans"],
"Vchitect/VBench_Leaderboard": ["submission:semiautomatic", "modality:video", "eval:generation"],
"eduagarcia/open_pt_llm_leaderboard": ["modality:text", "language:portuguese"],
"FinancialSupport/open_ita_llm_leaderboard": ["modality:text", "language:italian"],
"mesolitica/malay-llm-leaderboard": ["modality:text", "language:malay"],
"TIGER-Lab/GenAI-Arena": ["modality:image", "eval:generation", "judge:humans", ],
"q-future/Q-Bench-Leaderboard": ["modality:image", "judge:auto", "submission:closed"],
"OpenGenAI/parti-prompts-leaderboard": ["modality:image", "eval:generation", "judge:humans"],
"speakleash/open_pl_llm_leaderboard": ["modality:text", "language:polish"],
"malhajar/OpenLLMTurkishLeaderboard": ["modality:text", "language:turkish"],
"allenai/WildBench": ["judge:humans", "judge:model", "modality:text", "eval:generation"],
"hf-audio/open_asr_leaderboard": ["judge:auto", "modality:audio"],
"opencompass/open_vlm_leaderboard": ["judge:auto", "eval:generation", "modality:image"],
"livecodebench/benchmarks": ["judge:auto", "eval:code"],
"allenai/reward-bench": ["judge:auto", "modality:artefacts", "Models", "modality:text"],
"TTS-AGI/TTS-Arena": ["judge:humans", "modality:audio"]
}