Recent studyBlind TTS Elo is live. Compare two anonymous voice samples, vote after listening, and help separate real preference signal from noise.Vote in the study ->
Codesota · Models · LongCat-Flash-Omni7 results · 7 benchmarks
Model card

LongCat-Flash-Omni.

unknown
§ 02 · Benchmarks

Every benchmark LongCat-Flash-Omni has a recorded score for.

#BenchmarkArea · TaskMetricValueRankDateSource
01LibriSpeechSpeech · Speech Recognitionwer1.6%#3/92source ↗
02MMAUMultimodal · Audio-Text-to-Textaccuracy75.9%#3/4source ↗
03MMBenchMultimodal · Visual Question Answeringaccuracy89.8%#4/20source ↗
04MVBenchMultimodal · Video Understandingaccuracy75.2%#6/20source ↗
05Video-MMEMultimodal · Video Understandingaccuracy78.2%#10/24source ↗
06RealWorldQAMultimodal · Visual Question Answeringaccuracy76.0%#11/23source ↗
07MMLUReasoning · Commonsense Reasoningaccuracy86.8%#35/64source ↗
Rank column shows this model’s position vs all other models scored on the same benchmark + metric (competitors after the slash). #1 in red means current SOTA. Sorted by rank, then newest result.
§ 03 · Strengths by area

Where LongCat-Flash-Omni actually performs.

Speech
1
benchmark
avg rank #3.0
Multimodal
5
benchmarks
avg rank #6.8
Reasoning
1
benchmark
avg rank #35.0
§ 04 · Papers

1 paper with results for LongCat-Flash-Omni.

  1. 2025-10-31· 7 results

    LongCat-Flash-Omni Technical Report

§ 06 · Sources & freshness

Where these numbers come from.

pwc-dump
7
results
0 of 7 rows marked verified.