German Language LLM Index
a PeerBench project

Fresh evidence

New results

Completed benchmark runs, newest first. Every entry links to a permanent static result page.

Published runs

243 canonical results across 54 models + 8 early samples.

Follow via RSS →
  1. Ling 3.1 Flash · MMLU-ProX (DE)

    inclusionAI Exact match provider-internal early sample

    79.2%ᵖ
  2. MiMo V2.6 Pro · MuSR (DE)

    Xiaomi Accuracy early sample

    77.1%ᵖ
  3. MiMo V2.6 Pro · INCLUDE (DE)

    Xiaomi Exact match early sample

    83.2%ᵖ
  4. MiMo V2.6 Pro · SB10K (DE)

    Xiaomi MCC early sample

    63.4%ᵖ
  5. MiMo V2.6 Pro · GermEval NER (DE)

    Xiaomi Micro-F1 (no MISC) early sample

    85.1%ᵖ
  6. MiMo V2.6 Pro · ScaLA (DE)

    Xiaomi MCC early sample

    72.0%ᵖ
  7. Muse Spark Open · MMLU-ProX (DE)

    Meta Exact match provider-internal early sample

    86.7%ᵖ
  8. Ling 3.1 Flash · GermEval NER (DE)

    inclusionAI Micro-F1 (no MISC) provider-internal

    80.0%
  9. Ling 3.1 Flash · INCLUDE (DE)

    inclusionAI Exact match provider-internal

    85.0%
  10. Ling 3.1 Flash · MuSR (DE)

    inclusionAI Accuracy provider-internal

    84.6%
  11. Ling 3.1 Flash · SB10K (DE)

    inclusionAI MCC provider-internal

    58.8%
  12. Ling 3.1 Flash · ScaLA (DE)

    inclusionAI MCC provider-internal

    71.3%
  13. Muse Spark Open · GermEval NER (DE)

    Meta Micro-F1 (no MISC) provider-internal

    87.7%
  14. Muse Spark Open · MuSR (DE)

    Meta Accuracy provider-internal

    87.9%
  15. Muse Spark Open · SB10K (DE)

    Meta MCC provider-internal

    66.4%
  16. Muse Spark Open · ScaLA (DE)

    Meta MCC provider-internal

    67.8%
  17. 76.9%
  18. Qwen3.8 Flash · MMLU-ProX (DE)

    Alibaba Exact match provider-internal early sample

    80.8%ᵖ
  19. Muse Spark Open · INCLUDE (DE)

    Meta Exact match provider-internal

    86.9%
  20. 73.4%
  21. 73.8%
  22. 52.8%
  23. 58.9%
  24. Qwen3.8 Flash · GermEval NER (DE)

    Alibaba Micro-F1 (no MISC) provider-internal

    79.1%
  25. Qwen3.8 Flash · INCLUDE (DE)

    Alibaba Exact match provider-internal

    89.7%
  26. Qwen3.8 Flash · SB10K (DE)

    Alibaba MCC provider-internal

    62.5%
  27. Qwen3.8 Flash · ScaLA (DE)

    Alibaba MCC provider-internal

    67.6%
  28. Gemini 4 Argon · GermEval NER (DE)

    Google Micro-F1 (no MISC) provider-internal

    86.7%
  29. Gemini 4 Argon · INCLUDE (DE)

    Google Exact match provider-internal

    89.7%
  30. Gemini 4 Argon · MMLU-ProX (DE)

    Google Exact match provider-internal

    91.6%
  31. Gemini 4 Argon · MuSR (DE)

    Google Accuracy provider-internal

    93.5%
  32. Gemini 4 Argon · SB10K (DE)

    Google MCC provider-internal

    71.8%
  33. Gemini 4 Argon · ScaLA (DE)

    Google MCC provider-internal

    86.2%
  34. Mistral Large 4 (preview) · GermEval NER (DE)

    Mistral Micro-F1 (no MISC) provider-internal

    79.9%
  35. Mistral Large 4 (preview) · INCLUDE (DE)

    Mistral Exact match provider-internal

    83.2%
  36. 59.9%
  37. 61.3%
  38. 72.7%
  39. 75.7%
  40. 67.0%
  41. 81.4%
  42. 58.4%
  43. 59.6%
  44. Gemini 3.8 Flash · GermEval NER (DE)

    Google Micro-F1 (no MISC) provider-internal

    87.2%
  45. Gemini 3.8 Flash · MMLU-ProX (DE)

    Google Exact match provider-internal

    89.0%
  46. Gemini 3.8 Flash · SB10K (DE)

    Google MCC provider-internal

    66.9%
  47. Gemini 3.8 Flash · ScaLA (DE)

    Google MCC provider-internal

    80.6%
  48. Gemini 3.8 Flash · INCLUDE (DE)

    Google Exact match provider-internal

    93.5%
  49. Gemini 3.8 Flash · MuSR (DE)

    Google Accuracy provider-internal

    89.0%
  50. Gemini 3.5 Flash-Lite · GermEval NER (DE)

    Google Micro-F1 (no MISC) provider-internal

    85.4%
  51. Gemini 3.5 Flash-Lite · INCLUDE (DE)

    Google Exact match provider-internal

    85.0%
  52. Gemini 3.5 Flash-Lite · MuSR (DE)

    Google Accuracy provider-internal

    82.3%
  53. Gemini 3.5 Flash-Lite · SB10K (DE)

    Google MCC provider-internal

    62.5%
  54. Gemini 3.5 Flash-Lite · ScaLA (DE)

    Google MCC provider-internal

    75.1%
  55. GLM-5.3 Flash · GermEval NER (DE)

    Z.ai Micro-F1 (no MISC) fp8

    86.4%
  56. 86.9%
  57. 81.9%
  58. 63.6%
  59. 77.2%
  60. Tencent HY3 · GermEval NER (DE)

    Tencent Micro-F1 (no MISC) fp8

    76.1%
  61. 83.2%
  62. 85.0%
  63. 62.4%
  64. 69.7%
  65. 82.1%
  66. 86.9%
  67. 80.1%
  68. 62.4%
  69. 74.0%
  70. Gemini 3.1 Pro · MMLU-ProX (DE)

    Google Exact match provider-internal

    89.2%
  71. 86.0%
  72. 86.1%
  73. 86.9%
  74. 82.7%
  75. 83.2%
  76. 82.3%
  77. 84.4%
  78. 61.0%
  79. 71.7%
  80. 81.5%
  81. 87.9%
  82. 79.9%
  83. 86.1%
  84. 62.6%
  85. 66.9%
  86. 81.6%
  87. 86.9%
  88. 80.0%
  89. 62.7%
  90. 66.3%
  91. 80.7%
  92. Gemini 3.7 Flash · GermEval NER (DE)

    Google Micro-F1 (no MISC) provider-internal

    86.9%
  93. Gemini 3.7 Flash · INCLUDE (DE)

    Google Exact match provider-internal

    93.5%
  94. Gemini 3.7 Flash · MMLU-ProX (DE)

    Google Exact match provider-internal

    88.2%
  95. Gemini 3.7 Flash · MuSR (DE)

    Google Accuracy provider-internal

    88.6%
  96. Gemini 3.7 Flash · SB10K (DE)

    Google MCC provider-internal

    67.5%
  97. Gemini 3.7 Flash · ScaLA (DE)

    Google MCC provider-internal

    79.1%
  98. DeepSeek V4 Pro 0813 · GermEval NER (DE)

    DeepSeek Micro-F1 (no MISC) provider-internal

    81.7%
  99. DeepSeek V4 Pro 0813 · INCLUDE (DE)

    DeepSeek Exact match provider-internal

    87.9%
  100. DeepSeek V4 Pro 0813 · MuSR (DE)

    DeepSeek Accuracy provider-internal

    82.3%
  101. 60.8%
  102. 75.6%
  103. GPT-5.6 Luna · GermEval NER (DE)

    OpenAI Micro-F1 (no MISC) provider-internal

    81.9%
  104. GPT-5.6 Luna · INCLUDE (DE)

    OpenAI Exact match provider-internal

    86.0%
  105. GPT-5.6 Luna · MuSR (DE)

    OpenAI Accuracy provider-internal

    75.8%
  106. GPT-5.6 Luna · SB10K (DE)

    OpenAI MCC provider-internal

    61.9%
  107. GPT-5.6 Luna · ScaLA (DE)

    OpenAI MCC provider-internal

    72.2%
  108. GPT-5.6 Terra · INCLUDE (DE)

    OpenAI Exact match provider-internal

    88.8%
  109. GPT-5.6 Terra · MuSR (DE)

    OpenAI Accuracy provider-internal

    78.7%
  110. GPT-5.6 Terra · GermEval NER (DE)

    OpenAI Micro-F1 (no MISC) provider-internal

    83.3%
  111. GPT-5.6 Terra · SB10K (DE)

    OpenAI MCC provider-internal

    62.7%
  112. GPT-5.6 Terra · ScaLA (DE)

    OpenAI MCC provider-internal

    75.1%
  113. 80.3%
  114. 80.7%
  115. 85.3%
  116. 61.9%
  117. 74.0%
  118. 82.0%
  119. 61.2%
  120. 76.1%
  121. MiMo V2.5 · GermEval NER (DE)

    Xiaomi Micro-F1 (no MISC) fp8

    80.8%
  122. 61.2%
  123. 53.4%
  124. Gemini 3.5 Flash-Lite · MMLU-ProX (DE)

    Google Exact match provider-internal

    80.2%
  125. Gemini 3.6 Flash · GermEval NER (DE)

    Google Micro-F1 (no MISC) provider-internal

    86.2%
  126. Gemini 3.6 Flash · INCLUDE (DE)

    Google Exact match provider-internal

    74.8%
  127. Gemini 3.6 Flash · MMLU-ProX (DE)

    Google Exact match provider-internal

    86.0%
  128. Gemini 3.6 Flash · MuSR (DE)

    Google Accuracy provider-internal

    80.3%
  129. Gemini 3.6 Flash · SB10K (DE)

    Google MCC provider-internal

    64.5%
  130. Gemini 3.6 Flash · ScaLA (DE)

    Google MCC provider-internal

    77.6%
  131. Claude Sonnet 5 · INCLUDE (DE)

    Anthropic Exact match provider-internal

    72.7%
  132. Claude Fable 5 · GermEval NER (DE)

    Anthropic Micro-F1 (no MISC) provider-internal

    87.7%
  133. Claude Fable 5 · SB10K (DE)

    Anthropic MCC provider-internal

    67.3%
  134. Claude Fable 5 · ScaLA (DE)

    Anthropic MCC provider-internal

    83.6%
  135. Claude Fable 5 · INCLUDE (DE)

    Anthropic Exact match provider-internal

    72.7%
  136. Claude Fable 5 · MuSR (DE)

    Anthropic Accuracy provider-internal

    89.5%
  137. GPT-5.5 · MMLU-ProX (DE)

    OpenAI Exact match provider-internal

    87.2%
  138. Gemini 3 Flash Preview · GermEval NER (DE)

    Google Micro-F1 (no MISC) provider-internal

    84.7%
  139. Gemini 3 Flash Preview · INCLUDE (DE)

    Google Exact match provider-internal

    71.9%
  140. Gemini 3 Flash Preview · MMLU-ProX (DE)

    Google Exact match provider-internal

    86.3%
  141. Gemini 3 Flash Preview · MuSR (DE)

    Google Accuracy provider-internal

    79.3%
  142. 63.6%
  143. 77.0%
  144. DeepSeek V4 Pro · MuSR (DE)

    DeepSeek Accuracy provider-internal

    85.3%
  145. DeepSeek V4 Flash · MMLU-ProX (DE)

    DeepSeek Exact match provider-internal

    74.9%
  146. DeepSeek V4 Pro · MMLU-ProX (DE)

    DeepSeek Exact match provider-internal

    80.8%
  147. Claude Opus 4.8 · GermEval NER (DE)

    Anthropic Micro-F1 (no MISC) provider-internal

    85.8%
  148. Claude Opus 4.8 · MuSR (DE)

    Anthropic Accuracy provider-internal

    86.3%
  149. Claude Opus 4.8 · SB10K (DE)

    Anthropic MCC provider-internal

    64.5%
  150. Claude Opus 4.8 · ScaLA (DE)

    Anthropic MCC provider-internal

    82.6%
  151. GPT-5.5 · GermEval NER (DE)

    OpenAI Micro-F1 (no MISC) provider-internal

    85.9%
  152. GPT-5.5 · MuSR (DE)

    OpenAI Accuracy provider-internal

    86.3%
  153. GPT-5.5 · SB10K (DE)

    OpenAI MCC provider-internal

    62.5%
  154. GPT-5.5 · ScaLA (DE)

    OpenAI MCC provider-internal

    79.7%
  155. Claude Opus 4.8 · INCLUDE (DE)

    Anthropic Exact match provider-internal

    71.9%
  156. GPT-5.5 · INCLUDE (DE)

    OpenAI Exact match provider-internal

    74.8%
  157. Gemma 4 12B · GermEval NER (DE)

    Google Micro-F1 (no MISC) bf16

    79.6%
  158. Gemma 4 12B · INCLUDE (DE)

    Google Exact match bf16

    69.1%
  159. 73.1%
  160. 81.6%
  161. 62.2%
  162. 64.1%
  163. Gemma 4 31B · GermEval NER (DE)

    Google Micro-F1 (no MISC) bf16

    82.6%
  164. Gemma 4 31B · INCLUDE (DE)

    Google Exact match bf16

    68.3%
  165. 82.1%
  166. 83.5%
  167. 61.0%
  168. 71.0%
  169. Qwen3 14B · GermEval NER (DE)

    Alibaba Micro-F1 (no MISC) bf16

    73.0%
  170. Qwen3 14B · INCLUDE (DE)

    Alibaba Exact match bf16

    63.3%
  171. Qwen3 14B · MMLU-ProX (DE)

    Alibaba Exact match bf16

    64.1%
  172. Qwen3 14B · MuSR (DE)

    Alibaba Accuracy bf16

    69.7%
  173. 56.1%
  174. 64.0%
  175. Qwen3.5 9B · GermEval NER (DE)

    Alibaba Micro-F1 (no MISC) bf16

    72.6%
  176. Qwen3.5 9B · INCLUDE (DE)

    Alibaba Exact match bf16

    64.7%
  177. 73.4%
  178. 80.9%
  179. 55.7%
  180. 83.5%
  181. Gemini 3.1 Flash-Lite · INCLUDE (DE)

    Google Exact match provider-internal

    71.9%
  182. Gemini 3.1 Pro · INCLUDE (DE)

    Google Exact match provider-internal

    77.7%
  183. Gemini 3.5 Flash · INCLUDE (DE)

    Google Exact match provider-internal

    74.1%
  184. 83.7%
  185. GLM-5.1 · MuSR (DE)

    Z.ai Accuracy fp8

    81.4%
  186. 80.9%
  187. 62.4%
  188. 80.2%
  189. 62.4%
  190. 74.9%
  191. 82.2%
  192. 60.0%
  193. 73.5%
  194. Gemini 2.5 Flash · GermEval NER (DE)

    Google Micro-F1 (no MISC) provider-internal

    81.8%
  195. Gemini 2.5 Flash · MuSR (DE)

    Google Accuracy provider-internal

    83.3%
  196. Gemini 2.5 Flash · SB10K (DE)

    Google MCC provider-internal

    61.6%
  197. Gemini 2.5 Flash · ScaLA (DE)

    Google MCC provider-internal

    77.1%
  198. Gemini 3.1 Flash-Lite · MuSR (DE)

    Google Accuracy provider-internal

    84.4%
  199. Gemini 3.1 Pro · GermEval NER (DE)

    Google Micro-F1 (no MISC) provider-internal

    87.3%
  200. Gemini 3.1 Pro · MuSR (DE)

    Google Accuracy provider-internal

    88.1%
  201. Gemini 3.1 Pro · SB10K (DE)

    Google MCC provider-internal

    70.1%
  202. Gemini 3.1 Pro · ScaLA (DE)

    Google MCC provider-internal

    80.4%
  203. Gemini 3.5 Flash · GermEval NER (DE)

    Google Micro-F1 (no MISC) provider-internal

    86.0%
  204. Gemini 3.5 Flash · MuSR (DE)

    Google Accuracy provider-internal

    84.2%
  205. Gemini 3.5 Flash · SB10K (DE)

    Google MCC provider-internal

    64.3%
  206. Gemini 3.5 Flash · ScaLA (DE)

    Google MCC provider-internal

    79.4%
  207. GLM-5.1 · GermEval NER (DE)

    Z.ai Micro-F1 (no MISC) fp8

    52.2%
  208. 23.1%
  209. 69.9%
  210. MiMo V2.5 Pro · GermEval NER (DE)

    Xiaomi Micro-F1 (no MISC) fp8

    81.9%
  211. 61.7%
  212. 74.8%
  213. Qwen3.6 35B-A3B · GermEval NER (DE)

    Alibaba Micro-F1 (no MISC) fp8

    79.9%
  214. 58.4%
  215. 64.2%
  216. Qwen3.7 Max · GermEval NER (DE)

    Alibaba Micro-F1 (no MISC) provider-internal

    82.1%
  217. Qwen3.7 Max · SB10K (DE)

    Alibaba MCC provider-internal

    63.2%
  218. Qwen3.7 Max · ScaLA (DE)

    Alibaba MCC provider-internal

    69.8%
  219. Tencent HY3-Preview · GermEval NER (DE)

    Tencent Micro-F1 (no MISC) provider-internal

    77.3%
  220. Tencent HY3-Preview · SB10K (DE)

    Tencent MCC provider-internal

    38.9%
  221. Tencent HY3-Preview · ScaLA (DE)

    Tencent MCC provider-internal

    62.5%
  222. 70.5%
  223. 70.5%
  224. Gemini 3.1 Flash-Lite · GermEval NER (DE)

    Google Micro-F1 (no MISC) provider-internal

    83.2%
  225. Gemini 3.1 Flash-Lite · SB10K (DE)

    Google MCC provider-internal

    60.4%
  226. Gemini 3.1 Flash-Lite · ScaLA (DE)

    Google MCC provider-internal

    74.2%
  227. Gemma 4 26B A4B · GermEval NER (DE)

    Google Micro-F1 (no MISC) provider-internal

    81.8%
  228. Gemma 4 26B A4B · SB10K (DE)

    Google MCC provider-internal

    15.2%
  229. Gemma 4 26B A4B · ScaLA (DE)

    Google MCC provider-internal

    66.3%
  230. GLM-5.1 · INCLUDE (DE)

    Z.ai Exact match fp8

    82.2%
  231. 69.8%
  232. 67.6%
  233. Qwen3.7 Max · INCLUDE (DE)

    Alibaba Exact match provider-internal

    71.2%
  234. 78.2%
  235. Claude Haiku 4.5 · MMLU-ProX (DE)

    Anthropic Exact match provider-internal

    75.3%
  236. Gemini 2.5 Flash-Lite · MMLU-ProX (DE)

    Google Exact match provider-internal

    71.2%
  237. Gemini 3.1 Flash-Lite · MMLU-ProX (DE)

    Google Exact match provider-internal

    82.2%
  238. 53.2%
  239. 64.7%
  240. 63.3%
  241. 58.3%
  242. Claude Haiku 4.5 · INCLUDE (DE)

    Anthropic Exact match provider-internal

    68.3%
  243. Gemini 2.5 Flash · INCLUDE (DE)

    Google Exact match provider-internal

    70.5%
  244. 68.3%
  245. Tencent HY3-Preview · INCLUDE (DE)

    Tencent Exact match provider-internal

    69.1%
  246. 80.0%
  247. 66.2%
  248. Tencent HY3-Preview · MMLU-ProX (DE)

    Tencent Exact match provider-internal

    73.2%
  249. Gemini 2.5 Flash · MMLU-ProX (DE)

    Google Exact match provider-internal

    79.6%
  250. Gemini 3.5 Flash · MMLU-ProX (DE)

    Google Exact match provider-internal

    86.5%
  251. Undated 72.7%