Inspect the measurement.

Download evidence

Example-level outputs

All 32 scored examples. Ground truth and model predictions are preserved in the downloadable JSONL.

{"id":"0","prediction":"assuredness . \" Bella Bella Marie \" ( Rarlophone ) , a lively song that changes tempo mid-way .","reference":"assuredness \" Bella Bella Marie \" ( Parlophone ) , a lively song that changes tempo mid-way .","score":0.03225806451612903}
{"id":"1","prediction":"I don't think he will storm the charts with this one , but it's a good start .","reference":"I don't think he will storm the charts with this one , but it 's a good start .","score":0.012658227848101266}
{"id":"2","prediction":"CHRISTS CHARLES , 39 , who lives in Stockton - on - Tees , is an accountant .","reference":"CHRIS CHARLES , 39 , who lives in Stockton-on-Tees , is an accountant .","score":0.08450704225352113}
{"id":"3","prediction":"become a success with a disc and key pesto ! You're a star . . Rolly sings with","reference":"Become a success with a disc and hey presto ! You 're a star ... . Rolly sings with","score":0.07228915662650602}
{"id":"4","prediction":"Idlch , as he is known in Tin Pan Alley , lives songs with a month in the title . He wrote","reference":"Tolch , as he is known in Tin Pan Alley , likes songs with a month in the title . He wrote","score":0.03333333333333333}
{"id":"5","prediction":"' My September Love , \" , the big David Whitfield hit of 1956","reference":"\" My September Love , \" the big David Whitfield hit of 1956 .","score":0.08196721311475409}
{"id":"6","prediction":"He is also a director of a couple of garages . And he finds time as well to be a lyric","reference":"He is also a director of a couple of garages . And he finds time as well to be a lyric","score":0.0}
{"id":"7","prediction":"writer . He writes with Tolchard Evans , composer of \" Lady of Spain \" and other big hits .","reference":"writer . He writes with Tolchard Evans , composer of \" Lady of Spain \" and other big hits .","score":0.0}
{"id":"8","prediction":"The numbers include \" Scotland the Brave , \" \" Men of Harkech , \"","reference":"The numbers include \" Scotland the Brave , \" \" Men of Harlech , \"","score":0.015384615384615385}
{"id":"9","prediction":"Gay Compton stars in \" No Hiding , Place \" LIT\", \" , 9. 35 p m.D.","reference":"Fay Compton stars in \" No Hiding Place \" (I T V , 9.35 p.m. ) .","score":0.20634920634920634}
{"id":"10","prediction":"She plays the possessive mother of a man whose hobby revolves","reference":"She plays the possessive mother of a man whose hobby revolves","score":0.0}
{"id":"11","prediction":"round a chalk's house .","reference":"round a doll's house .","score":0.18181818181818182}
{"id":"12","prediction":"THREE people will be hypnotised in tonight's \" Likeline \"","reference":"THREE people will be hypnotised in tonight's \" Lifeline \"","score":0.017543859649122806}
{"id":"13","prediction":"CBBE , 10. 15 ) .","reference":"( B B C , 10.15 ) .","score":0.3157894736842105}
{"id":"14","prediction":"\" Mr Nawara's band , \" \" Greens leaves \" and \" English base . \"","reference":"\" McNamara's Band , \" \" Greensleeves \" and \" English Rose . \"","score":0.13114754098360656}
{"id":"15","prediction":"of Rhodesia and Myrasahand ( 1030 p.d. ) .","reference":"of Rhodesia and Nyasaland ( 10.30 p.m. ) .","score":0.11904761904761904}
{"id":"16","prediction":"They will be asked to comment on the design of everyday articles","reference":"They will be asked to comment on the design of everyday articles","score":0.0}
{"id":"17","prediction":"playwright Arnold Wecker . \" Instead , Muggeridge's appointment","reference":"playwright Arnold Wesker . \" Instead , Muggeridge's appointment","score":0.015873015873015872}
{"id":"18","prediction":"such as a chair and a motor-car . The idea is to see what happens when","reference":"such as a chair and a motor-car . The idea is to see what happens when","score":0.0}
{"id":"19","prediction":"will be with Sir Roy Weleogsky the Premier at the F.der action","reference":"will be with Sir Roy Welensky the Premier of the Federation","score":0.11864406779661017}
{"id":"20","prediction":"parts of the mind not normally available without hypnosis are used .","reference":"parts of the mind not normally available without hypnosis are used .","score":0.0}
{"id":"21","prediction":"ITV have postponed Malcolm Muggeridge's \" Appointment with","reference":"I T V have postponed Malcolm Muggeridge's \" Appointment with","score":0.03333333333333333}
{"id":"22","prediction":"success last night in ITV's \" Private Potter , \" Luis","reference":"success last night in I T V's \" Private Potter , \" his","score":0.07407407407407407}
{"id":"23","prediction":"man could only be regarded as a machine .","reference":"man could only be regarded as a machine .","score":0.0}
{"id":"24","prediction":"taste . \" ACTOL Tom Courtency was an outstanding","reference":"date . \" ACTOR Tom Courtenay was an outstanding","score":0.0851063829787234}
{"id":"25","prediction":"the switch because of the topicality of African","reference":"the switch because of the topicality of African","score":0.0}
{"id":"26","prediction":"essay on soldiering which started that a frightening","reference":"essay on soldiering which stated that a fighting","score":0.08333333333333333}
{"id":"27","prediction":"Sony Granada TV , the producers ! \" We decided to make","reference":"Say Granada T V , the producers : \" We decided to make","score":0.07407407407407407}
{"id":"28","prediction":"first big TV part . The play was a brilliantly-witter","reference":"first big T V part . The play was a brilliantly-written","score":0.05454545454545454}
{"id":"29","prediction":"affairs . The Weskew Interview will be seen at a better-","reference":"affairs . The Wesker interview will be seen at a later","score":0.1111111111111111}
{"id":"30","prediction":"crazy face , and obstinate , he filled eyes . They stripped","reference":"craggy face , and obstinate , baffled eyes . They stripped","score":0.1206896551724138}
{"id":"31","prediction":"chaired Ireland seen a vision of God - only the pockre and his","reference":"claimed he had seen a vision of God - only the padre and his","score":0.16666666666666666}