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 · HRM-Text-1B6 results · 6 benchmarks
Model card

HRM-Text-1B.

unknown
§ 02 · Benchmarks

Every benchmark HRM-Text-1B has a recorded score for.

#BenchmarkArea · TaskMetricValueRankDateSource
01DROPNatural Language Processing · Question Answeringf182.3%#2/5source ↗
02WinoGrandeReasoning · Commonsense Reasoningaccuracy72.4%#9/13source ↗
03HellaSwagReasoning · Commonsense Reasoningaccuracy63.4%#16/17source ↗
04GSM8KReasoning · Mathematical Reasoningaccuracy84.7%#38/48source ↗
05MATHReasoning · Mathematical Reasoningaccuracy56.5%#41/46source ↗
06MMLUReasoning · Commonsense Reasoningaccuracy60.7%#60/64source ↗
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 HRM-Text-1B actually performs.

Natural Language Processing
1
benchmark
avg rank #2.0
Reasoning
5
benchmarks
avg rank #32.8
§ 04 · Papers

1 paper with results for HRM-Text-1B.

  1. 2026-05-18· 6 results

    HRM-Text: Efficient Pretraining Beyond Scaling

§ 06 · Sources & freshness

Where these numbers come from.

pwc-dump
6
results
0 of 6 rows marked verified.