Codesota · Models · MoshiKyutai1 results · 1 benchmarks
Model card

Moshi.

Kyutaiopen-source
§ 02 · Benchmarks

Every benchmark Moshi has a recorded score for.

#BenchmarkArea · TaskMetricValueRankDateSource
01MMLUReasoning · Commonsense Reasoningaccuracy49.7%#64/64—source ↗
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 Moshi actually performs.

Reasoning
1
benchmark
avg rank #64.0
§ 04 · Papers

1 paper with results for Moshi.

  1. 2024-09-17· 1 result

    Moshi: a speech-text foundation model for real-time dialogue

§ 05 · Related models

Other Kyutai models scored on Codesota.

Kyutai STT 2.6B (EN)
2.6B params · 0 results
§ 06 · Sources & freshness

Where these numbers come from.

pwc-dump
1
result
0 of 1 rows marked verified.