Note: Overall leaderboard rankings may not reflect true model quality — individual benchmarks give a clearer picture. ARC-Challenge MMLU GPQA GSM8K Artificial Analysis Intelligence Index v4.1
← Back to leaderboard

LibriSpeech (test-clean) (-)

8 models

Top 5 Models Performance

AI at Meta: wav2vec2-base-960h ######################## -3.4
NVIDIA Corporation: stt_en_citrinet_256_ls ########################### -3.8
cactus-compute: whistle ############################### -4.31
moonshine-ai: moonshine-tiny ################################# -4.58
OpenAI: whisper-tiny.en ######################################## -5.6
– 970 – 1.1T
– 2019 – 2026
Rank Model Score
❓ 1 AI at Meta: wav2vec2-base-960h -3.4
🇺🇸 2 NVIDIA Corporation: stt_en_citrinet_256_ls -3.8
❓ 3 cactus-compute: whistle -4.31
❓ 4 moonshine-ai: moonshine-tiny -4.58
🇺🇸 5 OpenAI: whisper-tiny.en -5.6
🇺🇸 6 OpenAI: whisper-tiny -7.6
❓ 7 igorktech: femto-asr -10.95
❓ 8 auroraai-research: auroraasr-1m -11.43