Official benchmarks map / All boards

Every official benchmark and its current #1

52 Hugging Face official benchmark leaderboards, grouped by field. Each board has its own page with the full top 10.

Read from the Hugging Face API on November 8, 2026 and refreshed daily.

Agents & terminal

BenchmarkCurrent #1Entries
WildClawBenchQwen/Qwen3.8-2.4T-A95B52
terminal-bench-2.0mindlab-research/Macaron-V1-Venti44
terminal-bench-2.1deepseek-ai/DeepSeek-V4.1-Flash44
Claw-Evalornith-ai/Ornith-1.5-397B22
ToolathlonXiaomiMiMo/MiMo-V2.6-Pro-RL18
terminal-benchmoonshotai/Kimi-K3.1-Pro16
apex-agentsmoonshotai/Kimi-K3.1-Pro14
skillsbenchinclusionAI/Ling-3.1-flash12
agents-last-exammoonshotai/Kimi-K3.1-Pro10
yc-benchMiniMaxAI/MiniMax-M310
typed-decisionsFINAL-Bench/Darwin-27B-ZTC-v59
terminal-bench-sciencemoonshotai/Kimi-K3.1-Pro9
Long-Horizon-Terminal-Benchmoonshotai/Kimi-K39
physical-engineerings-last-examzai-org/GLM-5.27
ifstruct-v1.0FINAL-Bench/Darwin-180B-RSI6
cwe-benchdeepseek-ai/DeepSeek-V4.1-Flash-10174
chi-benchzai-org/GLM-5.13
safeagents-judge-benchvllm-sr/d3-ultra2
APEX-v1-extendedzai-org/GLM-4.72
decision-index-leaderboardFINAL-Bench/Darwin-27B-ZTC1

Vision & video

BenchmarkCurrent #1Entries
ScreenSpot-Probeipo-ai/NorthCUA-Pro31
OmniCompassmoonshotai/Kimi-K3.1-Pro26
VDEBenchsensenova/SenseNova-U1.5-8B-MoT16
MMMU_Promoonshotai/Kimi-K3.1-Pro14
WBenchrobbyant/lingbot-world-fast8
Video-MME-v2MiniMaxAI/MiniMax-M37
mmimeta-models/Muse-Spark-Open-816B-A42B5

Documents & OCR

BenchmarkCurrent #1Entries
ParseBenchKDLAI/KDL-Frontier-Parser-nano-v234
olmOCR-benchSoMarkAI/OXR-1.024
Real5-OmniDocBenchPaddlePaddle/PaddleOCR-VL-1.618
MDPBenchFINAL-Bench/Darwin-180B-RSI16
ExtractBenchFINAL-Bench/Darwin-180B-RSI-R312

Science & knowledge

BenchmarkCurrent #1Entries
MMLU-Prointernlm/Intern-S2-Preview-397B163
gpqaFINAL-Bench/Darwin-180B-RSI123
hlemoonshotai/Kimi-K3.1-Pro103
ResearchClawBenchzai-org/GLM-5.27

Coding

BenchmarkCurrent #1Entries
SWE-bench_Verifiedornith-ai/Ornith-1.5-397B78
SWE-bench_ProPCL-RSI-lab/Seshat-agent55
SWE-bench_MultilingualinclusionAI/Ling-3.1-flash34
deep-swePCL-RSI-lab/Seshat-agent33

Law & finance

BenchmarkCurrent #1Entries
RedlineBenchcrosbylegal/gemini-4-argon15
LEXam-hardFINAL-Bench/Darwin-180B-RSI12
LEXamFINAL-Bench/Darwin-180B-RSI10
EvasionBenchzai-org/GLM-4.75

Math

BenchmarkCurrent #1Entries
aime_2026deepseek-ai/DeepSeek-V4.1-Flash39
gsm8kXiaomiMiMo/MiMo-V2.5-Pro28
hmmt_feb_2026FINAL-Bench/Darwin-180B-RSI25

Speech

BenchmarkCurrent #1Entries
open-asr-leaderboardEdge0/ARK-ASR-3B65
Vaani-Benchmark-V1.0gnani/gnani11

Retrieval

BenchmarkCurrent #1Entries
arguanaFINAL-Bench/Darwin-180B-RSI-R34
BRIGHTFINAL-Bench/Darwin-BRIGHT-Retriever2

Robotics

BenchmarkCurrent #1Entries
vlabench_primitive_ft_lerobot_videonvidia/GR00T-N1-2B1