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 · SenseNova-U1-A3B-MoTSenseTime8 results · 7 benchmarks
Model card

SenseNova-U1-A3B-MoT.

SenseTimeLarge language model1 current SOTA

Added from Papers with Code MMLU-Pro refresh on 2026-05-19.

§ 02 · Benchmarks

Every benchmark SenseNova-U1-A3B-MoT has a recorded score for.

#BenchmarkArea · TaskMetricValueRankDateSource
01GenEvalMultimodal · Text-to-Image Generationgeneval-score0.9%#1/8source ↗
02MMBenchMultimodal · Visual Question Answeringaccuracy91.6%#1/20source ↗
03MMStarMultimodal · Image-Text-to-Textaccuracy80.9%#6/21source ↗
04MMMUMultimodal · Image-Text-to-Textaccuracy80.5%#9/36source ↗
05Tau2-BenchAgentic AI · Tool Useaccuracy75.4%#10/11source ↗
06MMMU-ProMultimodal · Visual Question Answeringaccuracy72.8%#16/31source ↗
07MMLU-ProReasoning · Commonsense Reasoningaccuracy84.0%#35/732026-05-12source ↗
08MMLU-ProReasoning · Commonsense Reasoningaccuracy84.0%#35/73source ↗
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 SenseNova-U1-A3B-MoT actually performs.

Multimodal
5
benchmarks
avg rank #6.6 · 1 SOTA
Agentic AI
1
benchmark
avg rank #10.0
Reasoning
1
benchmark
avg rank #35.0
§ 04 · Papers

1 paper with results for SenseNova-U1-A3B-MoT.

  1. 2026-05-12· 7 results

    SenseNova-U1: Unifying Multimodal Understanding and Generation with NEO-unify Architecture

§ 05 · Related models

Other SenseTime models scored on Codesota.

SenseTime Basemodel
1 result
§ 06 · Sources & freshness

Where these numbers come from.

pwc-dump
7
results
paperswithcode
1
result
0 of 8 rows marked verified.