Skip to content

Test Report

This test has the following configuration:

data provider model dataclass temperature prompt_file active

Test Results

fuzzy cost_summary 

Detailed Results

Result for 638948506246463270_1_u_003

Average Fuzzy Score: 0.400 (higher is better)
Total Fields: 5
View raw result from qwen/qwen3-vl-8b-thinking

638948506246463270_1_u_003

Field Model Response Ground Truth Fuzzy Score Match
b_id.transcription (empty) B.51.322.GB.266 0.000 ❌
company.transcription (empty) Abegg & Cie. 0.000 ❌
date (empty) (empty) 1.000 ✅
information (empty) (empty) 1.000 ✅
location.transcription (empty) Zürich 0.000 ❌

Result for 638948506246463270_1_u_079

Average Fuzzy Score: 0.000 (higher is better)
Total Fields: 6
View raw result from qwen/qwen3-vl-8b-thinking

638948506246463270_1_u_079

Field Model Response Ground Truth Fuzzy Score Match
b_id.transcription (empty) B.51.322.GB.638 0.000 ❌
company.transcription (empty) ARIA, Automobil-Reifen-Import A.G. 0.000 ❌
date (empty) 1942-08-06 0.000 ❌
information[0].transcription (empty) Britische schwarze Liste
Amendment 12, Juli 1942.		 0.000 ❌
information[1].transcription (empty) gestrichen:
Amendment 13, 23. November 1945.		 0.000 ❌
location.transcription (empty) Zürich 0.000 ❌

Result for 638948507035339442_4_u_043

Average Fuzzy Score: 0.167 (higher is better)
Total Fields: 6
View raw result from qwen/qwen3-vl-8b-thinking

638948507035339442_4_u_043

Field Model Response Ground Truth Fuzzy Score Match
b_id.transcription (empty) B.51.322.GB.608 0.000 ❌
company.transcription (empty) Beatus A.G. 0.000 ❌
date (empty) (empty) 1.000 ✅
information[0].transcription (empty) Britische schwarze Liste
10. Amendment vom Juli 1942.		 0.000 ❌
information[1].transcription (empty) gestrichen:
Amendment 13, 23. November 1945.		 0.000 ❌
location.transcription (empty) Basel 0.000 ❌

Result for 638948507035339442_4_u_135

Average Fuzzy Score: 0.143 (higher is better)
Total Fields: 7
View raw result from qwen/qwen3-vl-8b-thinking

638948507035339442_4_u_135

Field Model Response Ground Truth Fuzzy Score Match
b_id.transcription (empty) B.51.322.GB.913. 0.000 ❌
company.transcription (empty) Brocca Bruno 0.000 ❌
date (empty) (empty) 1.000 ✅
information[0].transcription (empty) Britische schwarze Liste,
Amendment 4, März 1943.		 0.000 ❌
information[1].transcription (empty) gestrichen:
Amendment 5, April 1944		 0.000 ❌
information[2].transcription (empty) Via Ciani 1. 0.000 ❌
location.transcription (empty) Lugano 0.000 ❌

Result for 638948508323810801_7_u_025

Average Fuzzy Score: 0.143 (higher is better)
Total Fields: 7
View raw result from qwen/qwen3-vl-8b-thinking

638948508323810801_7_u_025

Field Model Response Ground Truth Fuzzy Score Match
b_id.transcription (empty) B.51.322.GB.1051. 0.000 ❌
company.transcription (empty) Caviglia Pietro 0.000 ❌
date (empty) (empty) 1.000 ✅
information[0].transcription (empty) Britische schwarze Liste,
Amendment 10, Juli 1943.		 0.000 ❌
information[1].transcription (empty) gestrichen:
Amendment 7, 18. Juni 1945.		 0.000 ❌
information[2].transcription (empty) fig. noch auf franz. Liste Suppl. 6, 31.8.45. 0.000 ❌
location.transcription (empty) Zürich 1 0.000 ❌

Result for 638948508323810801_7_u_107

Average Fuzzy Score: 0.143 (higher is better)
Total Fields: 7
View raw result from qwen/qwen3-vl-8b-thinking

638948508323810801_7_u_107

Field Model Response Ground Truth Fuzzy Score Match
b_id.transcription (empty) B.51.322.GB.1200 0.000 ❌
company.transcription (empty) Cusin Alexander, Hotel Seidenhof 0.000 ❌
date (empty) (empty) 1.000 ✅
information[0].transcription (empty) Britische schwarze Liste,
Amendment 16, November 1943.		 0.000 ❌
information[1].transcription (empty) gestrichen:
Amendment 7, 18. Juni 1945.		 0.000 ❌
information[2].transcription (empty) fig. noch auf franz. liste Suppl. 6, 31.8.45. 0.000 ❌
location.transcription (empty) Zürich / Genève 0.000 ❌

Result for 638948509529371336_13_u_019

Average Fuzzy Score: 0.167 (higher is better)
Total Fields: 6
View raw result from qwen/qwen3-vl-8b-thinking

638948509529371336_13_u_019

Field Model Response Ground Truth Fuzzy Score Match
b_id.transcription (empty) B.51.322.GB.590. 0.000 ❌
company.transcription (empty) Egli Jean Martin 0.000 ❌
date (empty) (empty) 1.000 ✅
information[0].transcription (empty) Britische schwarze Liste
8.Amendment vom 23. Mai 1942.		 0.000 ❌
information[1].transcription (empty) gestrichen:
Amendment 13, 23.11.1945.		 0.000 ❌
location.transcription (empty) Wil 0.000 ❌

Result for 638948510008849475_16_u_033

Average Fuzzy Score: 0.000 (higher is better)
Total Fields: 6
View raw result from qwen/qwen3-vl-8b-thinking

638948510008849475_16_u_033

Field Model Response Ground Truth Fuzzy Score Match
b_id.transcription (empty) B.51.322.GB.1392 0.000 ❌
company.transcription (empty) Florentin Max & Adrienne, Marie Gabrielle 0.000 ❌
date (empty) 1944-12-20 0.000 ❌
information[0].transcription (empty) Britische schwarze Liste.
Amendment 11, September 1944.		 0.000 ❌
information[1].transcription (empty) gestrichen:
Amendment 10, 18. September 1945.		 0.000 ❌
location.transcription (empty) GENEVE 0.000 ❌

Result for 638948510550116959_19_u_053

Average Fuzzy Score: 0.000 (higher is better)
Total Fields: 7
View raw result from qwen/qwen3-vl-8b-thinking

638948510550116959_19_u_053

Field Model Response Ground Truth Fuzzy Score Match
b_id.transcription (empty) B.51.322.GB.759 0.000 ❌
company.transcription (empty) Gittard Léon 0.000 ❌
date (empty) 1942-12-02 0.000 ❌
information[0].transcription (empty) Figuriert auf Amendment 18, Nov.1942,
zur britischen schwarzen Liste.		 0.000 ❌
information[1].transcription (empty) Gestrichen !
Amendment 13, 24. Oktober 1944.		 0.000 ❌
information[2].transcription (empty) fig. auch auf franz. Liste Suppl. 6, 31.8.45 0.000 ❌
location.transcription (empty) Genève 0.000 ❌

Result for 638948511454726998_22_u_011

Average Fuzzy Score: 0.167 (higher is better)
Total Fields: 6
View raw result from qwen/qwen3-vl-8b-thinking

638948511454726998_22_u_011

Field Model Response Ground Truth Fuzzy Score Match
b_id.transcription (empty) B.51.322.GB.384. 0.000 ❌
company.transcription (empty) Häuselmann Carlos 0.000 ❌
date (empty) (empty) 1.000 ✅
information[0].transcription (empty) Britische schwarze Liste
Amendment 9, 1940.		 0.000 ❌
information[1].transcription (empty) gestrichen:
Amendment 14, vom 23.Nov.1944.(Venezuela)		 0.000 ❌
location.transcription (empty) CARACAS 0.000 ❌

Result for 638948511454726998_22_u_093

Average Fuzzy Score: 0.167 (higher is better)
Total Fields: 6
View raw result from qwen/qwen3-vl-8b-thinking

638948511454726998_22_u_093

Field Model Response Ground Truth Fuzzy Score Match
b_id.transcription (empty) B.51.322.GB.178. 0.000 ❌
company.transcription (empty) Hochstrasser & Cie. 0.000 ❌
date (empty) (empty) 1.000 ✅
information[0].transcription (empty) Britische schwarze Liste,
12. Nachtrag vom 29. Oktober 1940.		 0.000 ❌
information[1].transcription (empty) gestrichen:
Amendment 2, Februar 1944.		 0.000 ❌
location.transcription (empty) Küsnacht-Zch 0.000 ❌

Result for 638948512454392347_25_u_039

Average Fuzzy Score: 0.167 (higher is better)
Total Fields: 6
View raw result from qwen/qwen3-vl-8b-thinking

638948512454392347_25_u_039

Field Model Response Ground Truth Fuzzy Score Match
b_id.transcription (empty) B.51.322.GB.87. 0.000 ❌
company.transcription (empty) "ITALELVETICA" S.A. di partecipazione finanziarie ed industriali 0.000 ❌
date (empty) (empty) 1.000 ✅
information[0].transcription (empty) Britische schwarze Liste
13. Amendment vom 16.12.1940		 0.000 ❌
information[1].transcription (empty) gestrichen:
Amendment 11, 30.10.45.		 0.000 ❌
location.transcription (empty) Chur 0.000 ❌

Result for 638948512920532967_31_u_051

Average Fuzzy Score: 0.143 (higher is better)
Total Fields: 7
View raw result from qwen/qwen3-vl-8b-thinking

638948512920532967_31_u_051

Field Model Response Ground Truth Fuzzy Score Match
b_id.transcription (empty) B.51.322.GB.1176. 0.000 ❌
company.transcription (empty) Kolter G.m.b.H. 0.000 ❌
date (empty) (empty) 1.000 ✅
information[0].transcription (empty) Britische schwarze Liste,
Amendment 15, Oktober 1943.		 0.000 ❌
information[1].transcription (empty) gestrichen:
Amendment 15, Januar 1945.		 0.000 ❌
information[2].transcription (empty) fig. auch auf franz. Liste Suppl. 6, 31.8.45. 0.000 ❌
location.transcription (empty) Zürich 0.000 ❌

Result for 638948513657936804_34_u_033

Average Fuzzy Score: 0.000 (higher is better)
Total Fields: 6
View raw result from qwen/qwen3-vl-8b-thinking

638948513657936804_34_u_033

Field Model Response Ground Truth Fuzzy Score Match
b_id.transcription (empty) B.51.322.GB.1411. 0.000 ❌
company.transcription (empty) Libella A.-G. 0.000 ❌
date (empty) 1944-10-19 0.000 ❌
information[0].transcription (empty) Britische schwarze Liste.
Amendment 12, Oktober 1944.		 0.000 ❌
information[1].transcription (empty) gestrichen:
Amendment 13,23.11.1945.		 0.000 ❌
location.transcription (empty) BASEL 0.000 ❌

Result for 638948514122960907_37_u_033

Average Fuzzy Score: 0.143 (higher is better)
Total Fields: 7
View raw result from qwen/qwen3-vl-8b-thinking

638948514122960907_37_u_033

Field Model Response Ground Truth Fuzzy Score Match
b_id.transcription (empty) B.51.322.GB.468. 0.000 ❌
company.transcription (empty) Mas, & Co., Michel 0.000 ❌
date (empty) (empty) 1.000 ✅
information[0].transcription (empty) Britische schwarze Liste
Amendment 2, Februar 1942.		 0.000 ❌
information[1].transcription (empty) gestrichen:
Amendment 7, 18.6.1945.		 0.000 ❌
information[2].transcription (empty) fig noch auf franz Liste Suppl. 6, 31.8.45. 0.000 ❌
location.transcription (empty) ZUERICH 0.000 ❌

Result for 638948514122960907_37_u_087

Average Fuzzy Score: 0.400 (higher is better)
Total Fields: 5
View raw result from qwen/qwen3-vl-8b-thinking

638948514122960907_37_u_087

Field Model Response Ground Truth Fuzzy Score Match
b_id.transcription (empty) B.57.322.01 0.000 ❌
company.transcription (empty) Metallwerke 0.000 ❌
date (empty) (empty) 1.000 ✅
information (empty) (empty) 1.000 ✅
location.transcription (empty) Dornach 0.000 ❌

Result for 638948514122960907_37_u_145

Average Fuzzy Score: 0.000 (higher is better)
Total Fields: 8
View raw result from qwen/qwen3-vl-8b-thinking

638948514122960907_37_u_145

Field Model Response Ground Truth Fuzzy Score Match
b_id.transcription (empty) B.51.322.GB.377. 0.000 ❌
company.transcription (empty) Montaner Juan 0.000 ❌
date (empty) 1945-06-18 0.000 ❌
information[0].transcription (empty) Britische schwarze Liste
Amendment 14, v.25.8.41.		 0.000 ❌
information[1].transcription (empty) gestrichen:
Amendment 7, 18.6.1945.		 0.000 ❌
information[2].transcription (empty) fig wird auf franz. liste Suppl. 6, 31.8.45, 0.000 ❌
information[3].transcription (empty) rue vieux collège 0.000 ❌
location.transcription (empty) GENEVE 0.000 ❌

Result for 638948515760652556_40_u_029

Average Fuzzy Score: 0.167 (higher is better)
Total Fields: 6
View raw result from qwen/qwen3-vl-8b-thinking

638948515760652556_40_u_029

Field Model Response Ground Truth Fuzzy Score Match
b_id.transcription (empty) B.51.322.GB.1285. 0.000 ❌
company.transcription (empty) Ott Martin 0.000 ❌
date (empty) (empty) 1.000 ✅
information[0].transcription (empty) Britische schwarze Liste
Amendment 5, April 1944.		 0.000 ❌
information[1].transcription (empty) Gestrichen:
Amendment 13, 23.11.1945.		 0.000 ❌
location.transcription (empty) Kloten 0.000 ❌

Result for 638948515760652556_40_u_089

Average Fuzzy Score: 0.167 (higher is better)
Total Fields: 6
View raw result from qwen/qwen3-vl-8b-thinking

638948515760652556_40_u_089

Field Model Response Ground Truth Fuzzy Score Match
b_id.transcription (empty) B.51.322.GB.970. 0.000 ❌
company.transcription (empty) "Piag" A.G. 0.000 ❌
date (empty) (empty) 1.000 ✅
information[0].transcription (empty) Britische schwarze Liste,
Amendment 5, April 1943.		 0.000 ❌
information[1].transcription (empty) gestrichen:
Amendment 13, 23.11.1945.		 0.000 ❌
location.transcription (empty) Luzern 0.000 ❌

Result for 638948515760652556_40_u_143

Average Fuzzy Score: 0.000 (higher is better)
Total Fields: 6
View raw result from qwen/qwen3-vl-8b-thinking

638948515760652556_40_u_143

Field Model Response Ground Truth Fuzzy Score Match
b_id.transcription (empty) B.51.322.GB.1440. 0.000 ❌
company.transcription (empty) Produits dentaires S.A. 0.000 ❌
date (empty) 1944-12-16 0.000 ❌
information[0].transcription (empty) Britische schwarze Liste.
Amendment 14, Dezember 1944.		 0.000 ❌
information[1].transcription (empty) gestrichen:
Amendment 13, 23.11.1945.		 0.000 ❌
location.transcription (empty) VEVEY 0.000 ❌

Result for 638948516859460116_45_u_045

Average Fuzzy Score: 0.167 (higher is better)
Total Fields: 6
View raw result from qwen/qwen3-vl-8b-thinking

638948516859460116_45_u_045

Field Model Response Ground Truth Fuzzy Score Match
b_id.transcription (empty) B.51.322.GB.808. 0.000 ❌
company.transcription (empty) Ritzi & Wagner 0.000 ❌
date (empty) (empty) 1.000 ✅
information[0].transcription (empty) Britische schwarze Liste
Amendment 20, Dezember 1942.		 0.000 ❌
information[1].transcription (empty) gestrichen:
Amendment 13, 23.11.1945.		 0.000 ❌
location.transcription (empty) St.Gallen (Amriswil) 0.000 ❌

Result for 638948517510844987_48_u_007

Average Fuzzy Score: 0.167 (higher is better)
Total Fields: 6
View raw result from qwen/qwen3-vl-8b-thinking

638948517510844987_48_u_007

Field Model Response Ground Truth Fuzzy Score Match
b_id.transcription (empty) B.51.322.GB.397. 0.000 ❌
company.transcription (empty) Sacom (S.a.) 0.000 ❌
date (empty) (empty) 1.000 ✅
information[0].transcription (empty) Britische Schwarze Liste
Amendment 16, vom 2.10.1941.		 0.000 ❌
information[1].transcription (empty) gestrichen:
Amendment 13, 23.11.1945.		 0.000 ❌
location.transcription (empty) LUGANO 0.000 ❌

Result for 638948517510844987_48_u_067

Average Fuzzy Score: 0.167 (higher is better)
Total Fields: 6
View raw result from qwen/qwen3-vl-8b-thinking

638948517510844987_48_u_067

Field Model Response Ground Truth Fuzzy Score Match
b_id.transcription (empty) B.51.322.GB.976. 0.000 ❌
company.transcription (empty) Skiff A.G. 0.000 ❌
date (empty) (empty) 1.000 ✅
information[0].transcription (empty) Britische schwarze Liste,
Amendment 5, April 1943.		 0.000 ❌
information[1].transcription (empty) gestrichen:
Amendment 3, März 1944.		 0.000 ❌
location.transcription (empty) Luzern 0.000 ❌

Result for 638948517510844987_48_u_127

Average Fuzzy Score: 0.167 (higher is better)
Total Fields: 6
View raw result from qwen/qwen3-vl-8b-thinking

638948517510844987_48_u_127

Field Model Response Ground Truth Fuzzy Score Match
b_id.transcription (empty) B.51.322.GB.71. 0.000 ❌
company.transcription (empty) Società Finanziaria Assicurativa Milano 0.000 ❌
date (empty) (empty) 1.000 ✅
information[0].transcription (empty) Britische schwarze Liste
13. Amendment vom 16. 12. 1940		 0.000 ❌
information[1].transcription (empty) gestrichen:
Amendment 11, 30.10.45.		 0.000 ❌
location.transcription (empty) Succursale Zurigo 0.000 ❌

Result for 638948517510844987_48_u_183

Average Fuzzy Score: 0.167 (higher is better)
Total Fields: 6
View raw result from qwen/qwen3-vl-8b-thinking

638948517510844987_48_u_183

Field Model Response Ground Truth Fuzzy Score Match
b_id.transcription (empty) B.51.322.GB.1263. 0.000 ❌
company.transcription (empty) Spuhler Clemens 0.000 ❌
date (empty) (empty) 1.000 ✅
information[0].transcription (empty) Britische schwarze Liste,
Amendment 2, Februar 1944.		 0.000 ❌
information[1].transcription (empty) gestrichen:
Amendment 13, 23.11.1945.		 0.000 ❌
location.transcription (empty) Zürich 0.000 ❌

Result for 638948518962299305_51_u_049

Average Fuzzy Score: 0.167 (higher is better)
Total Fields: 6
View raw result from qwen/qwen3-vl-8b-thinking

638948518962299305_51_u_049

Field Model Response Ground Truth Fuzzy Score Match
b_id.transcription (empty) B.51.322.GB.1305. 0.000 ❌
company.transcription (empty) Schneider Max, Dr. 0.000 ❌
date (empty) (empty) 1.000 ✅
information[0].transcription (empty) Britische schwarze Liste,
Amendment 6, Mai 1944.		 0.000 ❌
information[1].transcription (empty) gestrichen:
Von der britischen schwarzen Liste.
Amendment No. 15, vom 10.April 1946.		 0.000 ❌
location.transcription (empty) Zürich 0.000 ❌

Result for 638948518962299305_51_u_093

Average Fuzzy Score: 0.200 (higher is better)
Total Fields: 5
View raw result from qwen/qwen3-vl-8b-thinking

638948518962299305_51_u_093

Field Model Response Ground Truth Fuzzy Score Match
b_id.transcription (empty) B.51.322.01 0.000 ❌
company.transcription (empty) Schweizerische Sodafabrik 0.000 ❌
date (empty) (empty) 1.000 ✅
information[0].transcription (empty) (U'Chemise) 0.000 ❌
location.transcription (empty) ZURZACH 0.000 ❌

Result for 638948520112305720_57_u_001

Average Fuzzy Score: 0.167 (higher is better)
Total Fields: 6
View raw result from qwen/qwen3-vl-8b-thinking

638948520112305720_57_u_001

Field Model Response Ground Truth Fuzzy Score Match
b_id.transcription (empty) B.51.322.GB.1155. 0.000 ❌
company.transcription (empty) Tabador S.A. 0.000 ❌
date (empty) (empty) 1.000 ✅
information[0].transcription (empty) Britische schwarze Liste,
Amendment 14, Oktober 1943.		 0.000 ❌
information[1].transcription (empty) gestrichen:
Amendment 3, Februar 1945.		 0.000 ❌
location.transcription (empty) Genève 0.000 ❌

Result for 638948520112305720_57_u_047

Average Fuzzy Score: 0.400 (higher is better)
Total Fields: 5
View raw result from qwen/qwen3-vl-8b-thinking

638948520112305720_57_u_047

Field Model Response Ground Truth Fuzzy Score Match
b_id.transcription (empty) (empty) 1.000 ✅
company.transcription (empty) Trullas & Cie.S.A. 0.000 ❌
date (empty) (empty) 1.000 ✅
information[0].transcription (empty) siehe: S.A. Trullas & Cie, Genf. (gestrichen) 0.000 ❌
location.transcription (empty) GENEVE 0.000 ❌

Result for 638948520648250905_63_u_027

Average Fuzzy Score: 0.143 (higher is better)
Total Fields: 7
View raw result from qwen/qwen3-vl-8b-thinking

638948520648250905_63_u_027

Field Model Response Ground Truth Fuzzy Score Match
b_id.transcription (empty) B.51.322.GB.501. 0.000 ❌
company.transcription (empty) Vieli, Joseph 0.000 ❌
date (empty) (empty) 1.000 ✅
information[0].transcription (empty) Britische schwarze Liste
Amendment 3, März 1942.		 0.000 ❌
information[1].transcription (empty) gestrichen:
Amendment 4, März 1945.		 0.000 ❌
information[2].transcription (empty) fig auch auf franz. Liste - Suppl. 6, 31.8.45. 0.000 ❌
location.transcription (empty) ZUERICH 0.000 ❌

Result for 638948521003028544_66_u_019

Average Fuzzy Score: 0.143 (higher is better)
Total Fields: 7
View raw result from qwen/qwen3-vl-8b-thinking

638948521003028544_66_u_019

Field Model Response Ground Truth Fuzzy Score Match
b_id.transcription (empty) B.51.322.GB.1162. 0.000 ❌
company.transcription (empty) Wehrli-Bleuler E., Dr. 0.000 ❌
date (empty) (empty) 1.000 ✅
information[0].transcription (empty) Britische schwarze Liste
Amendment 14, Oktober 1943.		 0.000 ❌
information[1].transcription (empty) gestrichen:
Amdnement 3, Februar 1945.		 0.000 ❌
information[2].transcription (empty) fig noch auf franz. liste Suppl. 6, 31.8.45. 0.000 ❌
location.transcription (empty) Zollikon 0.000 ❌

Result for 638948521003028544_66_u_055

Average Fuzzy Score: 0.167 (higher is better)
Total Fields: 6
View raw result from qwen/qwen3-vl-8b-thinking

638948521003028544_66_u_055

Field Model Response Ground Truth Fuzzy Score Match
b_id.transcription (empty) B.51.322.GB.452. 0.000 ❌
company.transcription (empty) Winterstein & Co., Ernst 0.000 ❌
date (empty) (empty) 1.000 ✅
information[0].transcription (empty) Britische schwarze Liste
Amendment 21, Dezember 1941.		 0.000 ❌
information[1].transcription (empty) gestrichen:
Amendment 13, 23.11.1945.		 0.000 ❌
location.transcription (empty) ZUERICH 0.000 ❌

Result for 638948521556863527_71_u_029

Average Fuzzy Score: 0.167 (higher is better)
Total Fields: 6
View raw result from qwen/qwen3-vl-8b-thinking

638948521556863527_71_u_029

Field Model Response Ground Truth Fuzzy Score Match
b_id.transcription (empty) B.51.322.GB.550. 0.000 ❌
company.transcription (empty) Zürcher Lagerhaus A.G. 0.000 ❌
date (empty) (empty) 1.000 ✅
information[0].transcription (empty) Britische schwarze Liste
Amendment 6, April 1942.		 0.000 ❌
information[1].transcription (empty) gestrichen:
Amendment 13, 23.11.1945.		 0.000 ❌
location.transcription (empty) ZUERICH 0.000 ❌