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 · Helium4 results · 4 benchmarks
Model card

Helium.

unknown
§ 02 · Benchmarks

Every benchmark Helium has a recorded score for.

#BenchmarkArea · TaskMetricValueRankDateSource
01Natural QuestionsNatural Language Processing · Question Answeringaccuracy23.3%#4/5source ↗
02WinoGrandeReasoning · Commonsense Reasoningaccuracy70.0%#11/13source ↗
03HellaSwagReasoning · Commonsense Reasoningaccuracy76.3%#12/17source ↗
04MMLUReasoning · Commonsense Reasoningaccuracy54.3%#62/64source ↗
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 Helium actually performs.

Natural Language Processing
1
benchmark
avg rank #4.0
Reasoning
3
benchmarks
avg rank #28.3
§ 04 · Papers

1 paper with results for Helium.

  1. 2024-09-17· 4 results

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

§ 06 · Sources & freshness

Where these numbers come from.

pwc-dump
4
results
0 of 4 rows marked verified.