Jev-1.13.0
Harness benchmark · measured on 29.09.2026 12:07
Benchmark-ID
run-20260929-100818-c6df4fDecision-Benchmark High V 1.0Runtime: python
ℹ
Public note: 200 neue komplexe synthetische Entscheidungsfragen, 10 Familien: Rechnung, Lager, Quorum, Beschaffung, Buchungen, Zeitintervalle, Ereignisse, Budget, Rechte, Graphen. 100 Noul (50/50),100 Choice (4 Optionen). Ein Punkt pro exakter Entscheidung. Unabhaengig gepruefte Sollwerte; Datensatz vor Modelltests eingefroren. Keine Tools, direkte Entscheidung ohne Thinking-Modus; keine allgemeine Reasoning-Bewertung. Concurrency1, keine Retries; gesamte HTTP-Antwortzeit inkl. erster Anfrage. 114/200 richtig. Mittel 256.171 ms; Median 247.415 ms; P95 324.991 ms. API-Fehler 0; Formatfehler 0 (zaehlen als falsch). TypeSafe Cloud jev-1.13.0, native typed API, Noul-Schwelle0.5; unbekannte Inferenzhardware; Internet/HTTPS enthalten.
Points114,00von 200,00
Points rate57,00%
Tasks passed114von 200
Total duration51,23s
Ranking in the field
28of 44 systems
Harness benchmark · Primary metric: Score rate (%)
This run is better than 37 % of all comparable systems.
Score rate
57 %
-7 % vs Ø 61,6
Tasks passed
114
+85 % vs Ø 61,6
Total duration
51,2 s
-97 % vs Ø 1.728,2
Distribution in the field10 – 100 %
Wie schlägt sich dieser Benchmark mit anderen Modellen?
Qwen3.6-35B-A3B-AWQNVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260929-153935-691df9
100 %
Jev-1.13.0 same modelCloud/API: TypeSafe AI (Hardware unbekannt) · run-20260929-091917-060aae
100 %
Qwen3.6-35B-A3B-AWQNVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260929-091748-cbe456
100 %
Qwen3.8-27B-Uncensored2× 2x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260929-091747-e13da0
100 %
Open-Jev-27B-v1.1NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260929-091747-5d8477
100 %
Qwen3.6-35B-A3B-AWQNVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260929-112249-dba0f2
97 %
Gemma-4-26B-A4B-itNVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260722-161611-05d866
91 %
Devstral-Small-2-24B-Instruct-2512AMD Radeon 8060S Graphics · run-20260722-161611-5f2f86
87 %
Gemma-4-26B-A4B-itAMD Radeon 8060S Graphics · run-20260722-161611-12a767
82 %
MiniMax-M2.53× 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260722-161611-f6cfe1
81 %
Gemma-4-26B-A4B-itAMD Radeon 8060S Graphics · run-20260722-161611-9b7325
80 %
Nemotron-Cascade-2-30B-A3BNVIDIA GeForce RTX 3090 · run-20260929-091748-b70591
80 %
Nemotron-Cascade-2-30B-A3BNVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260929-091748-15ef7f
80 %
MiniMax-M2.53× 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260722-161611-54019f
79 %
Jev-1.13.0 this runCloud/API: TypeSafe AI (Hardware unbekannt) · run-20260929-100818-c6df4f
57 %
Hardware
Cloud/API: TypeSafe AI (Hardware unbekannt)
Setup
Runtime: python
Quantization: -
Model: Jev-1.13.0
Aufgaben (200)
| Task | Status | Points | Duration |
|---|---|---|---|
| 001 - Beschaffung_Optimierung | failed | 0 / 1 | 0,33 s |
| 002 - permission_deny_override | passed | 1 / 1 | 0,25 s |
| 003 - Rechnung_Rundung | passed | 1 / 1 | 0,26 s |
| 004 - Rechnung_Rundung | passed | 1 / 1 | 0,28 s |
| 005 - graph_reachability_blocks | passed | 1 / 1 | 0,25 s |
| 006 - Beschaffung_Optimierung | passed | 1 / 1 | 0,25 s |
| 007 - time_interval_conflicts | passed | 1 / 1 | 0,27 s |
| 008 - time_interval_conflicts | failed | 0 / 1 | 0,60 s |
| 009 - Rechnung_Rundung | failed | 0 / 1 | 0,22 s |
| 010 - permission_deny_override | passed | 1 / 1 | 0,28 s |
| 011 - Abstimmung_Quorum | passed | 1 / 1 | 0,28 s |
| 012 - permission_deny_override | failed | 0 / 1 | 0,26 s |
| 013 - permission_deny_override | passed | 1 / 1 | 0,23 s |
| 014 - budget_dependency_selection | failed | 0 / 1 | 0,23 s |
| 015 - graph_reachability_blocks | passed | 1 / 1 | 0,23 s |
| 016 - Buchungen_Korrekturen | failed | 0 / 1 | 0,23 s |
| 017 - budget_dependency_selection | passed | 1 / 1 | 0,25 s |
| 018 - Lager_Haltbarkeit | failed | 0 / 1 | 0,27 s |
| 019 - version_event_reconstruction | failed | 0 / 1 | 0,23 s |
| 020 - permission_deny_override | passed | 1 / 1 | 0,25 s |
| 021 - Abstimmung_Quorum | passed | 1 / 1 | 0,26 s |
| 022 - Rechnung_Rundung | failed | 0 / 1 | 0,23 s |
| 023 - permission_deny_override | passed | 1 / 1 | 0,23 s |
| 024 - version_event_reconstruction | passed | 1 / 1 | 0,25 s |
| 025 - Lager_Haltbarkeit | failed | 0 / 1 | 0,25 s |
| 026 - time_interval_conflicts | passed | 1 / 1 | 0,22 s |
| 027 - permission_deny_override | passed | 1 / 1 | 0,23 s |
| 028 - Abstimmung_Quorum | passed | 1 / 1 | 0,24 s |
| 029 - Beschaffung_Optimierung | passed | 1 / 1 | 0,25 s |
| 030 - version_event_reconstruction | failed | 0 / 1 | 0,23 s |
| 031 - Lager_Haltbarkeit | failed | 0 / 1 | 0,22 s |
| 032 - Beschaffung_Optimierung | passed | 1 / 1 | 0,22 s |
| 033 - budget_dependency_selection | passed | 1 / 1 | 0,27 s |
| 034 - time_interval_conflicts | passed | 1 / 1 | 0,24 s |
| 035 - time_interval_conflicts | failed | 0 / 1 | 0,24 s |
| 036 - Rechnung_Rundung | failed | 0 / 1 | 0,23 s |
| 037 - budget_dependency_selection | passed | 1 / 1 | 0,24 s |
| 038 - time_interval_conflicts | passed | 1 / 1 | 0,58 s |
| 039 - Buchungen_Korrekturen | passed | 1 / 1 | 0,22 s |
| 040 - version_event_reconstruction | failed | 0 / 1 | 0,27 s |
| 041 - time_interval_conflicts | failed | 0 / 1 | 0,37 s |
| 042 - Lager_Haltbarkeit | passed | 1 / 1 | 0,23 s |
| 043 - Rechnung_Rundung | passed | 1 / 1 | 0,29 s |
| 044 - Rechnung_Rundung | passed | 1 / 1 | 0,25 s |
| 045 - Rechnung_Rundung | failed | 0 / 1 | 0,28 s |
| 046 - time_interval_conflicts | failed | 0 / 1 | 0,42 s |
| 047 - version_event_reconstruction | failed | 0 / 1 | 0,25 s |
| 048 - Lager_Haltbarkeit | failed | 0 / 1 | 0,25 s |
| 049 - Lager_Haltbarkeit | passed | 1 / 1 | 0,26 s |
| 050 - Beschaffung_Optimierung | passed | 1 / 1 | 0,25 s |
| 051 - Rechnung_Rundung | passed | 1 / 1 | 0,28 s |
| 052 - Lager_Haltbarkeit | failed | 0 / 1 | 0,24 s |
| 053 - Buchungen_Korrekturen | passed | 1 / 1 | 0,24 s |
| 054 - budget_dependency_selection | failed | 0 / 1 | 0,23 s |
| 055 - Buchungen_Korrekturen | failed | 0 / 1 | 0,22 s |
| 056 - Abstimmung_Quorum | passed | 1 / 1 | 0,27 s |
| 057 - Buchungen_Korrekturen | failed | 0 / 1 | 0,26 s |
| 058 - Buchungen_Korrekturen | failed | 0 / 1 | 0,25 s |
| 059 - Lager_Haltbarkeit | passed | 1 / 1 | 0,22 s |
| 060 - Rechnung_Rundung | failed | 0 / 1 | 0,23 s |
| 061 - Abstimmung_Quorum | passed | 1 / 1 | 0,30 s |
| 062 - Buchungen_Korrekturen | failed | 0 / 1 | 0,23 s |
| 063 - version_event_reconstruction | failed | 0 / 1 | 0,24 s |
| 064 - Abstimmung_Quorum | passed | 1 / 1 | 0,23 s |
| 065 - permission_deny_override | passed | 1 / 1 | 0,22 s |
| 066 - time_interval_conflicts | passed | 1 / 1 | 0,26 s |
| 067 - Abstimmung_Quorum | passed | 1 / 1 | 0,22 s |
| 068 - Buchungen_Korrekturen | failed | 0 / 1 | 0,42 s |
| 069 - Abstimmung_Quorum | passed | 1 / 1 | 0,26 s |
| 070 - permission_deny_override | passed | 1 / 1 | 0,23 s |
| 071 - permission_deny_override | failed | 0 / 1 | 0,23 s |
| 072 - permission_deny_override | passed | 1 / 1 | 0,25 s |
| 073 - Rechnung_Rundung | passed | 1 / 1 | 0,27 s |
| 074 - version_event_reconstruction | passed | 1 / 1 | 0,23 s |
| 075 - Buchungen_Korrekturen | failed | 0 / 1 | 0,24 s |
| 076 - graph_reachability_blocks | passed | 1 / 1 | 0,24 s |
| 077 - graph_reachability_blocks | passed | 1 / 1 | 0,33 s |
| 078 - time_interval_conflicts | passed | 1 / 1 | 0,27 s |
| 079 - time_interval_conflicts | failed | 0 / 1 | 0,23 s |
| 080 - graph_reachability_blocks | failed | 0 / 1 | 0,34 s |
| 081 - budget_dependency_selection | failed | 0 / 1 | 0,22 s |
| 082 - version_event_reconstruction | passed | 1 / 1 | 0,27 s |
| 083 - Beschaffung_Optimierung | passed | 1 / 1 | 0,23 s |
| 084 - Beschaffung_Optimierung | passed | 1 / 1 | 0,24 s |
| 085 - permission_deny_override | failed | 0 / 1 | 0,26 s |
| 086 - Lager_Haltbarkeit | passed | 1 / 1 | 0,28 s |
| 087 - budget_dependency_selection | failed | 0 / 1 | 0,26 s |
| 088 - Beschaffung_Optimierung | passed | 1 / 1 | 0,23 s |
| 089 - Rechnung_Rundung | passed | 1 / 1 | 0,27 s |
| 090 - Abstimmung_Quorum | passed | 1 / 1 | 0,28 s |
| 091 - Rechnung_Rundung | passed | 1 / 1 | 0,26 s |
| 092 - graph_reachability_blocks | passed | 1 / 1 | 0,22 s |
| 093 - Buchungen_Korrekturen | failed | 0 / 1 | 0,30 s |
| 094 - Buchungen_Korrekturen | failed | 0 / 1 | 0,28 s |
| 095 - version_event_reconstruction | failed | 0 / 1 | 0,24 s |
| 096 - Buchungen_Korrekturen | passed | 1 / 1 | 0,24 s |
| 097 - graph_reachability_blocks | failed | 0 / 1 | 0,24 s |
| 098 - Buchungen_Korrekturen | failed | 0 / 1 | 0,22 s |
| 099 - budget_dependency_selection | passed | 1 / 1 | 0,25 s |
| 100 - Abstimmung_Quorum | passed | 1 / 1 | 0,23 s |
| 101 - permission_deny_override | passed | 1 / 1 | 0,24 s |
| 102 - Beschaffung_Optimierung | failed | 0 / 1 | 0,24 s |
| 103 - Lager_Haltbarkeit | failed | 0 / 1 | 0,23 s |
| 104 - Lager_Haltbarkeit | passed | 1 / 1 | 0,25 s |
| 105 - time_interval_conflicts | passed | 1 / 1 | 0,26 s |
| 106 - graph_reachability_blocks | failed | 0 / 1 | 0,21 s |
| 107 - version_event_reconstruction | passed | 1 / 1 | 0,25 s |
| 108 - Abstimmung_Quorum | passed | 1 / 1 | 0,22 s |
| 109 - permission_deny_override | passed | 1 / 1 | 0,25 s |
| 110 - Abstimmung_Quorum | failed | 0 / 1 | 0,27 s |
| 111 - Abstimmung_Quorum | passed | 1 / 1 | 0,24 s |
| 112 - Lager_Haltbarkeit | passed | 1 / 1 | 0,26 s |
| 113 - permission_deny_override | passed | 1 / 1 | 0,27 s |
| 114 - version_event_reconstruction | failed | 0 / 1 | 0,27 s |
| 115 - version_event_reconstruction | passed | 1 / 1 | 0,27 s |
| 116 - budget_dependency_selection | passed | 1 / 1 | 0,23 s |
| 117 - Rechnung_Rundung | passed | 1 / 1 | 0,23 s |
| 118 - Buchungen_Korrekturen | failed | 0 / 1 | 0,23 s |
| 119 - Rechnung_Rundung | passed | 1 / 1 | 0,27 s |
| 120 - graph_reachability_blocks | failed | 0 / 1 | 0,22 s |
| 121 - version_event_reconstruction | failed | 0 / 1 | 0,22 s |
| 122 - graph_reachability_blocks | failed | 0 / 1 | 0,28 s |
| 123 - graph_reachability_blocks | failed | 0 / 1 | 0,23 s |
| 124 - permission_deny_override | failed | 0 / 1 | 0,27 s |
| 125 - Lager_Haltbarkeit | failed | 0 / 1 | 0,23 s |
| 126 - budget_dependency_selection | passed | 1 / 1 | 0,27 s |
| 127 - Lager_Haltbarkeit | failed | 0 / 1 | 0,28 s |
| 128 - Rechnung_Rundung | passed | 1 / 1 | 0,24 s |
| 129 - budget_dependency_selection | passed | 1 / 1 | 0,22 s |
| 130 - time_interval_conflicts | passed | 1 / 1 | 0,29 s |
| 131 - Abstimmung_Quorum | failed | 0 / 1 | 0,23 s |
| 132 - Buchungen_Korrekturen | passed | 1 / 1 | 0,28 s |
| 133 - budget_dependency_selection | passed | 1 / 1 | 0,35 s |
| 134 - Buchungen_Korrekturen | passed | 1 / 1 | 0,25 s |
| 135 - time_interval_conflicts | passed | 1 / 1 | 0,35 s |
| 136 - time_interval_conflicts | failed | 0 / 1 | 0,26 s |
| 137 - Beschaffung_Optimierung | passed | 1 / 1 | 0,27 s |
| 138 - time_interval_conflicts | failed | 0 / 1 | 0,22 s |
| 139 - Beschaffung_Optimierung | failed | 0 / 1 | 0,26 s |
| 140 - time_interval_conflicts | failed | 0 / 1 | 0,27 s |
| 141 - version_event_reconstruction | passed | 1 / 1 | 0,26 s |
| 142 - graph_reachability_blocks | failed | 0 / 1 | 0,24 s |
| 143 - budget_dependency_selection | failed | 0 / 1 | 0,24 s |
| 144 - Buchungen_Korrekturen | failed | 0 / 1 | 0,24 s |
| 145 - version_event_reconstruction | failed | 0 / 1 | 0,23 s |
| 146 - Buchungen_Korrekturen | failed | 0 / 1 | 0,26 s |
| 147 - graph_reachability_blocks | failed | 0 / 1 | 0,29 s |
| 148 - time_interval_conflicts | failed | 0 / 1 | 0,27 s |
| 149 - budget_dependency_selection | passed | 1 / 1 | 0,26 s |
| 150 - Rechnung_Rundung | failed | 0 / 1 | 0,24 s |
| 151 - permission_deny_override | passed | 1 / 1 | 0,27 s |
| 152 - version_event_reconstruction | passed | 1 / 1 | 0,23 s |
| 153 - Rechnung_Rundung | passed | 1 / 1 | 0,22 s |
| 154 - Beschaffung_Optimierung | passed | 1 / 1 | 0,23 s |
| 155 - version_event_reconstruction | failed | 0 / 1 | 0,25 s |
| 156 - Abstimmung_Quorum | passed | 1 / 1 | 0,25 s |
| 157 - Abstimmung_Quorum | passed | 1 / 1 | 0,26 s |
| 158 - Lager_Haltbarkeit | failed | 0 / 1 | 0,22 s |
| 159 - budget_dependency_selection | passed | 1 / 1 | 0,26 s |
| 160 - budget_dependency_selection | failed | 0 / 1 | 0,26 s |
| 161 - time_interval_conflicts | passed | 1 / 1 | 0,25 s |
| 162 - graph_reachability_blocks | passed | 1 / 1 | 0,25 s |
| 163 - graph_reachability_blocks | failed | 0 / 1 | 0,24 s |
| 164 - Abstimmung_Quorum | passed | 1 / 1 | 0,29 s |
| 165 - budget_dependency_selection | passed | 1 / 1 | 0,23 s |
| 166 - Beschaffung_Optimierung | failed | 0 / 1 | 0,24 s |
| 167 - Buchungen_Korrekturen | failed | 0 / 1 | 0,28 s |
| 168 - Beschaffung_Optimierung | failed | 0 / 1 | 0,22 s |
| 169 - Beschaffung_Optimierung | passed | 1 / 1 | 0,28 s |
| 170 - budget_dependency_selection | passed | 1 / 1 | 0,30 s |
| 171 - Lager_Haltbarkeit | passed | 1 / 1 | 0,27 s |
| 172 - Rechnung_Rundung | failed | 0 / 1 | 0,23 s |
| 173 - Abstimmung_Quorum | passed | 1 / 1 | 0,24 s |
| 174 - Beschaffung_Optimierung | passed | 1 / 1 | 0,23 s |
| 175 - Beschaffung_Optimierung | passed | 1 / 1 | 0,28 s |
| 176 - version_event_reconstruction | passed | 1 / 1 | 0,24 s |
| 177 - Beschaffung_Optimierung | failed | 0 / 1 | 0,22 s |
| 178 - Lager_Haltbarkeit | failed | 0 / 1 | 0,25 s |
| 179 - permission_deny_override | passed | 1 / 1 | 0,26 s |
| 180 - permission_deny_override | passed | 1 / 1 | 0,22 s |
| 181 - version_event_reconstruction | failed | 0 / 1 | 0,30 s |
| 182 - graph_reachability_blocks | passed | 1 / 1 | 0,23 s |
| 183 - Lager_Haltbarkeit | failed | 0 / 1 | 0,24 s |
| 184 - time_interval_conflicts | passed | 1 / 1 | 0,30 s |
| 185 - Abstimmung_Quorum | passed | 1 / 1 | 0,24 s |
| 186 - Rechnung_Rundung | failed | 0 / 1 | 0,33 s |
| 187 - Beschaffung_Optimierung | failed | 0 / 1 | 0,21 s |
| 188 - Buchungen_Korrekturen | passed | 1 / 1 | 0,27 s |
| 189 - graph_reachability_blocks | failed | 0 / 1 | 0,26 s |
| 190 - Abstimmung_Quorum | passed | 1 / 1 | 0,22 s |
| 191 - budget_dependency_selection | passed | 1 / 1 | 0,28 s |
| 192 - permission_deny_override | passed | 1 / 1 | 0,23 s |
| 193 - graph_reachability_blocks | passed | 1 / 1 | 0,24 s |
| 194 - budget_dependency_selection | passed | 1 / 1 | 0,22 s |
| 195 - Lager_Haltbarkeit | passed | 1 / 1 | 0,24 s |
| 196 - graph_reachability_blocks | failed | 0 / 1 | 0,24 s |
| 197 - graph_reachability_blocks | passed | 1 / 1 | 0,24 s |
| 198 - Lager_Haltbarkeit | failed | 0 / 1 | 0,25 s |
| 199 - Beschaffung_Optimierung | failed | 0 / 1 | 0,28 s |
| 200 - version_event_reconstruction | failed | 0 / 1 | 0,28 s |
Configuration
# LLM-Benchmark Konfiguration
# Modell : Jev-1.13.0
# Engine : api
# Run-ID : run-20260929-100818-c6df4f
# GPU : Cloud/API: TypeSafe AI (Hardware unbekannt)
bench@llm-benchmark:~$ cat benchmark.conf
dataset_sha256 d7ffc569be958f5f83d92ceb679b9a4aa4f563bbfad8cf3907ca78a134196066
concurrency 1
retries 0
model_version jev-1.13.0
mean_response_ms 256.17075582617
median_response_ms 247.41527898004
p95_response_ms 324.99050302431
execution_type cloud
cloud_provider TypeSafe AI
| dataset_sha256 | d7ffc569be958f5f83d92ceb679b9a4aa4f563bbfad8cf3907ca78a134196066 |
| concurrency | 1 |
| retries | 0 |
| first_request_included | 1 |
| model_version | jev-1.13.0 |
| mean_response_ms | 256.17075582617 |
| median_response_ms | 247.41527898004 |
| p95_response_ms | 324.99050302431 |
| execution_type | cloud |
| cloud_provider | TypeSafe AI |
Contributed by
Mario Alka Administrator
@marioalka
Ich bin Unternehmer, Softwareentwickler und KI-Enthusiast. Seit vielen Jahren entwickle ich Unternehmenssoftware und beschäftige mich inzwischen fast täglich mit lokalen LLMs, KI-Agenten und leistungsfähiger KI-Hardware.
Mit LLM-Benchmark.de möchte ich eine Plattform schaffen, auf der Modelle, GPUs und Agenten objektiv und reproduzierbar miteinander verglichen werden.
