Hugging Face Official Benchmarks Map: likes over time

quantid/huggingface-official-benchmark-leaderboards is a static Space on the Hugging Face Hub. It has 35 likes, 35 in the last 7 days and 35 in the last 30, and ranks #3,702 among Spaces by likes.

Live map of all HF official benchmark leaderboards

What it uses

• openai/gpt-oss-20b (model)
• openai/gpt-oss-120b (model)
• google/embeddinggemma-300m (model)
• Qwen/Qwen3.6-35B-A3B (model)
• Qwen/Qwen3.6-27B (model)
• Qwen/Qwen3.5-27B (model)
• Qwen/Qwen3.8-Flash-Next (model)
• moonshotai/Kimi-K3 (model)
• nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16 (model)
• deepseek-ai/DeepSeek-V4.1-Flash (model)
• zai-org/GLM-5.2 (model)
• moonshotai/Kimi-K2.6 (model)
• Qwen/Qwen3.5-397B-A17B (model)
• zai-org/GLM-5 (model)
• deepseek-ai/DeepSeek-V4-Pro (model)
• tencent/Hy3 (model)
• moonshotai/Kimi-K2.5 (model)
• zai-org/GLM-5.1 (model)
• ornith-ai/Ornith-1.5-397B (model)
• meta-models/Muse-Glimmer-30B (model)
• MiniMaxAI/MiniMax-M3 (model)
• zai-org/GLM-4.7 (model)
• XiaomiMiMo/MiMo-V2.6-Pro-RL (model)
• PaddlePaddle/PaddleOCR-VL-1.6 (model)
• lerobot/pi0_base (model)
• Qwen/Qwen3.8-2.4T-A95B (model)
• tencent/Hy4-preview (model)
• XiaomiMiMo/MiMo-V2.5-Pro (model)
• robbyant/lingbot-world-fast (model)
• infly/Infinity-Parser2-Pro (model)
• InternScience/Agents-A1 (model)
• KDLAI/KDL-Frontier-Parser-nano (model)
• Edge0/ARK-ASR-3B (model)
• dots-studio/dots3-note-prev (model)
• FINAL-Bench/Darwin-180B-RSI (model)
• mindlab-research/Macaron-V1-Venti (model)
• Tort-AI/GLM-5.3 (model)
• gnani/gnani (model)
• crosbylegal/claude-opus-5 (model)
• mteb/baseline-bm25s (model)
• openai/gsm8k (dataset)
• TIGER-Lab/MMLU-Pro (dataset)
• harborframework/terminal-bench-2.1 (dataset)
• harborframework/terminal-bench-3.0 (dataset)
• harborframework/terminal-bench (dataset)
• SWE-bench/SWE-bench_Verified (dataset)
• Idavidrein/gpqa (dataset)
• mercor/apex-agents (dataset)
• harborframework/terminal-bench-2.0 (dataset)
• harborframework/terminal-bench-science (dataset)
• SWE-bench/SWE-bench_Multilingual (dataset)
• ScaleAI/SWE-bench_Pro (dataset)
• InternScience/ResearchClawBench (dataset)
• MathArena/aime_2026 (dataset)
• allenai/olmOCR-bench (dataset)
• mteb/arguana (dataset)
• cais/hle (dataset)
• llamaindex/ParseBench (dataset)
• hf-audio/open-asr-leaderboard (dataset)
• MMMU/MMMU_Pro (dataset)
• MathArena/hmmt_feb_2026 (dataset)
• likaixin/ScreenSpot-Pro (dataset)
• llamaindex/ExtractBench (dataset)
• MME-Benchmarks/Video-MME-v2 (dataset)
• IntelligenceLab/Long-Horizon-Terminal-Bench (dataset)
• actava/chi-bench (dataset)
• internlm/WildClawBench (dataset)
• PaddlePaddle/Real5-OmniDocBench (dataset)
• benchflow/skillsbench (dataset)
• agents-last-exam/agents-last-exam (dataset)
• claw-eval/Claw-Eval (dataset)
• mteb/BRIGHT (dataset)
• VLABench/vlabench_primitive_ft_lerobot_video (dataset)
• meituan-longcat/WBench (dataset)
• crosbylegal/RedlineBench (dataset)
• LEXam-Benchmark/LEXam (dataset)
• Delores-Lin/MDPBench (dataset)
• mercor/APEX-v1-extended (dataset)
• tiiuae/PBench (dataset)
• datacurve/deep-swe (dataset)

Open quantid/huggingface-official-benchmark-leaderboards on Hugging Face

Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.