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 · BitNet b1.58 2B4T6 results · 6 benchmarks
Model card

BitNet b1.58 2B4T.

unknown
§ 02 · Benchmarks

Every benchmark BitNet b1.58 2B4T has a recorded score for.

#BenchmarkArea · TaskMetricValueRankDateSource
01CommonsenseQAReasoning · Commonsense Reasoningaccuracy71.6%#4/5source ↗
02TriviaQANatural Language Processing · Question Answeringaccuracy33.6%#4/4source ↗
03WinoGrandeReasoning · Commonsense Reasoningaccuracy71.9%#10/13source ↗
04HellaSwagReasoning · Commonsense Reasoningaccuracy68.4%#14/17source ↗
05GSM8KReasoning · Mathematical Reasoningaccuracy58.4%#43/48source ↗
06MMLUReasoning · Commonsense Reasoningaccuracy53.2%#63/64source ↗
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 BitNet b1.58 2B4T actually performs.

Natural Language Processing
1
benchmark
avg rank #4.0
Reasoning
5
benchmarks
avg rank #26.8
§ 04 · Papers

1 paper with results for BitNet b1.58 2B4T.

  1. 2025-04-16· 6 results

    BitNet b1.58 2B4T Technical Report

§ 06 · Sources & freshness

Where these numbers come from.

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