Codesota · Models · DreamerV3Google DeepMind2 results · 2 benchmarks
Model card

DreamerV3.

Google DeepMindopen-sourceWorld Model (Model-Based)

Scalable world model that masters Atari and Minecraft (MineDojo) with fixed hyperparameters.

§ 01 · Benchmarks

Every benchmark DreamerV3 has a recorded score for.

#BenchmarkArea · TaskMetricValueRankDateSource
01MuJoCoReinforcement Learning · Continuous Controlaverage-return897.00#6/9source ↗
02Atari 2600Reinforcement Learning · Atari Gameshuman-normalized-score840.00#8/12source ↗
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.
§ 02 · Strengths by area

Where DreamerV3 actually performs.

Reinforcement Learning
2
benchmarks
avg rank #7.0
§ 04 · Related models

Other Google DeepMind models scored on Codesota.

Gemma 3 12B IT
12B params · 2 results
Gemma 3 4B IT
4B params · 2 results
Disco57
1 result
Gemini Ultra
Unknown params · 1 result
MEME
1 result
SoViT-400m/14
400M params · 1 result
BBF (Bigger, Better, Faster)
Unknown params · 0 results
§ 05 · Sources & freshness

Where these numbers come from.

arxiv-paper
2
results
0 of 2 rows marked verified.