Spaces:

evalstate
/

tb21-annotated

Running

App Files Files Community

tb21-annotated

399 MB

Ctrl+K

1 contributor

History: 34 commits

evalstate HF Staff

Gemini CLI: thought summaries filed as messages by Harbor's old converter, counted as reasoning (summary only)

05c21f3 verified about 3 hours ago

data
Gemini CLI: thought summaries filed as messages by Harbor's old converter, counted as reasoning (summary only) about 3 hours ago
rows
Our estimate (leads + fallback discounted), output/hidden reasoning bar, cost estimate, regrouped gaps, waffle flags, Harbor Hub trial links (part 5) about 19 hours ago
.gitattributes

2.21 kB
TB2.1 annotated: 22 leaderboard rows, atif-scan v0.8.17 highlights and trajectories 1 day ago
README.md

1.18 kB
Data holes & accounting; leaderboard rows scored as listed (atif-scan v0.8.17-2-g4fbd8b8) 1 day ago
annot-nav.css

742 Bytes
Our estimate (leads + fallback discounted), output/hidden reasoning bar, cost estimate, regrouped gaps, waffle flags, Harbor Hub trial links about 19 hours ago
common.js

10.1 kB
Trace completeness: share of output tokens in the trace; why not (withheld by provider, not kept by harness, lost in conversion, summary only); counted/inferred basis; undercounted about 4 hours ago
home.js

16.6 kB
Trace completeness: share of output tokens in the trace; why not (withheld by provider, not kept by harness, lost in conversion, summary only); counted/inferred basis; undercounted about 4 hours ago
hub-link.js

929 Bytes
Our estimate (leads + fallback discounted), output/hidden reasoning bar, cost estimate, regrouped gaps, waffle flags, Harbor Hub trial links about 19 hours ago
index.html

7.98 kB
Trace completeness: share of output tokens in the trace; why not (withheld by provider, not kept by harness, lost in conversion, summary only); counted/inferred basis; undercounted about 4 hours ago
row.html

1.72 kB
Link the submissions Space 1 day ago
row.js

12.1 kB
Trace completeness: share of output tokens in the trace; why not (withheld by provider, not kept by harness, lost in conversion, summary only); counted/inferred basis; undercounted about 4 hours ago
style.css

17.4 kB
Trace completeness: share of output tokens in the trace; why not (withheld by provider, not kept by harness, lost in conversion, summary only); counted/inferred basis; undercounted about 4 hours ago
tokens.css

2.17 kB
TB2.1 annotated: 22 leaderboard rows, atif-scan v0.8.17 highlights and trajectories 1 day ago