Commit History

Publish the arXiv-linked v1.3 leaderboard
f0c6805
Running
verified

josefchen commited on

Sync FlavourBench v1.2.0 source
6aec8cd
verified

josefchen commited on

Remove injected host chrome from the benchmark canvas
cce45fc
verified

josefchen commited on

Add task-family leaderboard views and research navigation
81e6eb1
verified

josefchen commited on

Remove decorative framing and table border leaks
3c3ecdd
verified

josefchen commited on

Align hosted Space chrome with launch design
2c640ad
verified

josefchen commited on

Polish benchmark discovery and statistical insights
2de538e
verified

josefchen commited on

Match Space to launch design
ad13bd6
verified

josefchen commited on

Sync launch asset to repository source
1d92e52
verified

josefchen commited on

Redesign Space and surface turnkey model evaluation
418bf00
verified

josefchen commited on

Add lab evaluator and training reward API
e38c605
verified

josefchen commited on

Update FlavourBench authorship and affiliation
854cc74
verified

josefchen commited on

Deploy final 27-model complete-core explorer
1c950b5
verified

josefchen commited on

Publish v43 OpenRouter Fable dashboard
170f6ba
verified

josefchen commited on

Clarify Fable refusal diagnostics
430599e
verified

josefchen commited on

Finish Fable 5 powered release
8507864
verified

josefchen commited on

Update 26-model FlavourBench explorer
5f69dee
verified

josefchen commited on

Add author affiliations
dba402e
verified

josefchen commited on

Add FlavourBench co-authors
a70a23e
verified

josefchen commited on

Publish the powered FlavourBench evidence explorer
91c562d
verified

josefchen commited on

Sharpen frontier benchmark positioning
158edce
verified

josefchen commited on

Make leaderboard score-first with statistical intervals
a5a9440
verified

josefchen commited on

Position FlavourBench as frontier culinary benchmark
b2aac0d
verified

josefchen commited on

Add release upload hygiene
fb3ab5d
verified

josefchen commited on

Remove generated bytecode cache
a973596
verified

josefchen commited on

Retitle FlavourBench around executable evaluation
ced4adf
verified

josefchen commited on

Publish private FlavourBench explorer candidate
f590e74
verified

josefchen commited on

initial commit
6d1c70d
verified

josefchen commited on