File tree Expand file tree Collapse file tree
Expand file tree Collapse file tree Original file line number Diff line number Diff line change @@ -1076,19 +1076,19 @@ <h1>SkillOpt</h1>
10761076
10771077 < aside class ="hero-ledger " aria-label ="Key numbers ">
10781078 < div class ="ledger-row ">
1079- < span class ="ledger-label "> Paper-reported avg gain </ span >
1080- < span class ="ledger-value "> +21.5 </ span >
1079+ < span class ="ledger-label "> Model x benchmark x harness cells </ span >
1080+ < span class ="ledger-value "> 52/52 </ span >
10811081 </ div >
10821082 < div class ="ledger-row ">
1083- < span class ="ledger-label "> Direct-chat benchmarks </ span >
1084- < span class ="ledger-value "> 6 </ span >
1083+ < span class ="ledger-label "> Frozen target models </ span >
1084+ < span class ="ledger-value "> 7 </ span >
10851085 </ div >
10861086 < div class ="ledger-row ">
1087- < span class ="ledger-label "> Best measured result </ span >
1088- < span class ="ledger-value "> 5/ 6</ span >
1087+ < span class ="ledger-label "> Benchmarks </ span >
1088+ < span class ="ledger-value "> 6</ span >
10891089 </ div >
10901090 < div class ="ledger-row ">
1091- < span class ="ledger-label "> Deployment artifact</ span >
1091+ < span class ="ledger-label "> Exported artifact</ span >
10921092 < span class ="ledger-value "> best_skill.md</ span >
10931093 </ div >
10941094 </ aside >
Original file line number Diff line number Diff line change @@ -1076,19 +1076,19 @@ <h1>SkillOpt</h1>
10761076
10771077 < aside class ="hero-ledger " aria-label ="Key numbers ">
10781078 < div class ="ledger-row ">
1079- < span class ="ledger-label "> Paper-reported avg gain </ span >
1080- < span class ="ledger-value "> +21.5 </ span >
1079+ < span class ="ledger-label "> Model x benchmark x harness cells </ span >
1080+ < span class ="ledger-value "> 52/52 </ span >
10811081 </ div >
10821082 < div class ="ledger-row ">
1083- < span class ="ledger-label "> Direct-chat benchmarks </ span >
1084- < span class ="ledger-value "> 6 </ span >
1083+ < span class ="ledger-label "> Frozen target models </ span >
1084+ < span class ="ledger-value "> 7 </ span >
10851085 </ div >
10861086 < div class ="ledger-row ">
1087- < span class ="ledger-label "> Best measured result </ span >
1088- < span class ="ledger-value "> 5/ 6</ span >
1087+ < span class ="ledger-label "> Benchmarks </ span >
1088+ < span class ="ledger-value "> 6</ span >
10891089 </ div >
10901090 < div class ="ledger-row ">
1091- < span class ="ledger-label "> Deployment artifact</ span >
1091+ < span class ="ledger-label "> Exported artifact</ span >
10921092 < span class ="ledger-value "> best_skill.md</ span >
10931093 </ div >
10941094 </ aside >
You can’t perform that action at this time.
0 commit comments