LetTokenBurn
BenchHub
Benchmarks
Leaderboard
Graph
Run
Docs
Blog
Sign in
LetTokenBurn
Benchmarks
Leaderboard
Graph
Run
Docs
Blog
More
Recent runs
Agent API
AI Native test
Leaderboard
/
DeepSeek Flash
Model
DeepSeek Flash
DeepSeek · open weights
deepseek.com
Coding
Coding
Benchmark
Score
Metric
Harness
Source
Confidence
Link
Hob-VL
49.6
accuracy
N/A
Independent
medium
arxiv.org
↗
Multimodal
Multimodal
Benchmark
Score
Metric
Harness
Source
Confidence
Link
CREATE
34.2
accuracy
N/A
Independent
medium
arxiv.org
↗
MVGraph
17.4
accuracy
N/A
Independent
medium
arxiv.org
↗
Reproduced by the community
Loading community runs…