diff --git a/leaderboard-submissions/results/claude.json b/leaderboard-submissions/results/claude.json
new file mode 100644
index 0000000..675be13
--- /dev/null
+++ b/leaderboard-submissions/results/claude.json
@@ -0,0 +1,87 @@
+{
+  "_submission_hash": "",
+  "_results_hash": "",
+  "metadata": {
+    "name": "Claude 2.1",
+    "authors": "Anthropic",
+    "url": "https://www.anthropic.com/news/claude-2-1",
+    "citation": "Anthropic, 2023",
+    "type": "FOUNDATION",
+    "context": 200000
+  },
+  "closedbook": {
+    "acc": {
+      "loose": 0.34087118650894077,
+      "strict": 0.04143646408839779
+    },
+    "rouge": {
+      "rouge1": {
+        "precision": 0.5180287739482223,
+        "recall": 0.3878211545435264,
+        "fscore": 0.41162891337334295
+      },
+      "rouge2": {
+        "precision": 0.25046659737457144,
+        "recall": 0.19938401442157735,
+        "fscore": 0.20843439451844803
+      },
+      "rougeL": {
+        "precision": 0.4368122438044132,
+        "recall": 0.3228172228944878,
+        "fscore": 0.34362967985991916
+      }
+    },
+    "bleurt": 0.42636404607383255,
+    "gpt": 0.11049723756906077
+  },
+  "openbook": {
+    "acc": {
+      "loose": 0.47120748528585843,
+      "strict": 0.0856353591160221
+    },
+    "rouge": {
+      "rouge1": {
+        "precision": 0.2330077534090562,
+        "recall": 0.5457109366018758,
+        "fscore": 0.29497641803677077
+      },
+      "rouge2": {
+        "precision": 0.12616194413675985,
+        "recall": 0.2804704207979029,
+        "fscore": 0.15747334844988234
+      },
+      "rougeL": {
+        "precision": 0.19843856217260156,
+        "recall": 0.4759886498517577,
+        "fscore": 0.2527928960282501
+      }
+    },
+    "bleurt": 0.48486519522594484,
+    "gpt": 0.21823204419889503
+  },
+  "evidenceprovided": {
+    "acc": {
+      "loose": 0.6531674930336602,
+      "strict": 0.2154696132596685
+    },
+    "rouge": {
+      "rouge1": {
+        "precision": 0.32045520128134836,
+        "recall": 0.7180304376195379,
+        "fscore": 0.42300161074719367
+      },
+      "rouge2": {
+        "precision": 0.1979935998869878,
+        "recall": 0.4389654131557785,
+        "fscore": 0.26233077626475276
+      },
+      "rougeL": {
+        "precision": 0.2663865768311303,
+        "recall": 0.6115257311712957,
+        "fscore": 0.3538037743008641
+      }
+    },
+    "bleurt": 0.5081962022251187,
+    "gpt": 0.4696132596685083
+  }
+}
\ No newline at end of file
diff --git a/leaderboard-submissions/results/gpt-3.5-turbo.json b/leaderboard-submissions/results/gpt-3.5-turbo.json
new file mode 100644
index 0000000..ea1e9dd
--- /dev/null
+++ b/leaderboard-submissions/results/gpt-3.5-turbo.json
@@ -0,0 +1,87 @@
+{
+  "_submission_hash": "",
+  "_results_hash": "",
+  "metadata": {
+    "name": "GPT-3.5-turbo",
+    "authors": "OpenAI",
+    "url": "https://platform.openai.com/docs/models/gpt-3-5-turbo",
+    "citation": "OpenAI, 2023",
+    "type": "FOUNDATION",
+    "context": 16384
+  },
+  "closedbook": {
+    "acc": {
+      "loose": 0.3979994873440785,
+      "strict": 0.058011049723756904
+    },
+    "rouge": {
+      "rouge1": {
+        "precision": 0.40734904473273553,
+        "recall": 0.45162239056919035,
+        "fscore": 0.4012819044350075
+      },
+      "rouge2": {
+        "precision": 0.22803347570177684,
+        "recall": 0.2518584000616542,
+        "fscore": 0.2271839790263482
+      },
+      "rougeL": {
+        "precision": 0.34711466296455995,
+        "recall": 0.38661536042587596,
+        "fscore": 0.34195490807715956
+      }
+    },
+    "bleurt": 0.4551408462926169,
+    "gpt": 0.14502762430939226
+  },
+  "openbook": {
+    "acc": {
+      "loose": 0.15469947220693514,
+      "strict": 0.031767955801104975
+    },
+    "rouge": {
+      "rouge1": {
+        "precision": 0.09699008021536212,
+        "recall": 0.19469418167728442,
+        "fscore": 0.11418755334242695
+      },
+      "rouge2": {
+        "precision": 0.040413694872158276,
+        "recall": 0.08488911320642317,
+        "fscore": 0.05075429578237907
+      },
+      "rougeL": {
+        "precision": 0.0835343704701655,
+        "recall": 0.1699066826399081,
+        "fscore": 0.09861238283404707
+      }
+    },
+    "bleurt": 0.33750931579022775,
+    "gpt": 0.07596685082872928
+  },
+  "evidenceprovided": {
+    "acc": {
+      "loose": 0.5165072478945334,
+      "strict": 0.10220994475138122
+    },
+    "rouge": {
+      "rouge1": {
+        "precision": 0.463516335636312,
+        "recall": 0.5689152894435296,
+        "fscore": 0.45546862566608826
+      },
+      "rouge2": {
+        "precision": 0.24946325633429448,
+        "recall": 0.31371309343477694,
+        "fscore": 0.25221468710915207
+      },
+      "rougeL": {
+        "precision": 0.3653434458264324,
+        "recall": 0.45283802498465286,
+        "fscore": 0.3581738799002991
+      }
+    },
+    "bleurt": 0.49659434195546154,
+    "gpt": 0.2430939226519337
+  }
+}
\ No newline at end of file
diff --git a/leaderboard-submissions/results/gpt-4-turbo.json b/leaderboard-submissions/results/gpt-4-turbo.json
new file mode 100644
index 0000000..9e3297c
--- /dev/null
+++ b/leaderboard-submissions/results/gpt-4-turbo.json
@@ -0,0 +1,87 @@
+{
+  "_submission_hash": "",
+  "_results_hash": "",
+  "metadata": {
+    "name": "GPT-4-turbo",
+    "authors": "OpenAI",
+    "url": "https://platform.openai.com/docs/models/gpt-4-and-gpt-4-turbo",
+    "citation": "OpenAI, 2023",
+    "type": "FOUNDATION",
+    "context": 128000
+  },
+  "closedbook": {
+    "acc": {
+      "loose": 0.4597296177579326,
+      "strict": 0.10082872928176796
+    },
+    "rouge": {
+      "rouge1": {
+        "precision": 0.5061057938990791,
+        "recall": 0.5171893148007345,
+        "fscore": 0.48194841967428786
+      },
+      "rouge2": {
+        "precision": 0.29559659009870354,
+        "recall": 0.30901380162874503,
+        "fscore": 0.290250346638784
+      },
+      "rougeL": {
+        "precision": 0.43012909178526687,
+        "recall": 0.440115792132854,
+        "fscore": 0.4091321043635482
+      }
+    },
+    "bleurt": 0.49333308180228125,
+    "gpt": 0.19889502762430938
+  },
+  "openbook": {
+    "acc": {
+      "loose": 0.4703468836864732,
+      "strict": 0.10911602209944751
+    },
+    "rouge": {
+      "rouge1": {
+        "precision": 0.32591691806739764,
+        "recall": 0.5274025346455309,
+        "fscore": 0.35589614186761614
+      },
+      "rouge2": {
+        "precision": 0.18949097802681353,
+        "recall": 0.28817587063251693,
+        "fscore": 0.20743984742825158
+      },
+      "rougeL": {
+        "precision": 0.28537777495423555,
+        "recall": 0.46967882341300493,
+        "fscore": 0.31379331104952
+      }
+    },
+    "bleurt": 0.4865400605212424,
+    "gpt": 0.26243093922651933
+  },
+  "evidenceprovided": {
+    "acc": {
+      "loose": 0.6281475667110468,
+      "strict": 0.1919889502762431
+    },
+    "rouge": {
+      "rouge1": {
+        "precision": 0.6321127734126731,
+        "recall": 0.6764341478682872,
+        "fscore": 0.6144612886380147
+      },
+      "rouge2": {
+        "precision": 0.3984152059157445,
+        "recall": 0.4292697483707228,
+        "fscore": 0.39470073987610177
+      },
+      "rougeL": {
+        "precision": 0.536314082392947,
+        "recall": 0.5794550216005496,
+        "fscore": 0.5226280415927149
+      }
+    },
+    "bleurt": 0.5809288421923614,
+    "gpt": 0.4129834254143646
+  }
+}
\ No newline at end of file
diff --git a/leaderboard-submissions/results/gpt-4.json b/leaderboard-submissions/results/gpt-4.json
new file mode 100644
index 0000000..305e62a
--- /dev/null
+++ b/leaderboard-submissions/results/gpt-4.json
@@ -0,0 +1,87 @@
+{
+  "_submission_hash": "",
+  "_results_hash": "",
+  "metadata": {
+    "name": "GPT-4",
+    "authors": "OpenAI",
+    "url": "https://platform.openai.com/docs/models/gpt-4-and-gpt-4-turbo",
+    "citation": "OpenAI, 2023",
+    "type": "FOUNDATION",
+    "context": 8192
+  },
+  "closedbook": {
+    "acc": {
+      "loose": 0.3549958003169331,
+      "strict": 0.06629834254143646
+    },
+    "rouge": {
+      "rouge1": {
+        "precision": 0.3081323409240976,
+        "recall": 0.4026625098759217,
+        "fscore": 0.313123968945042
+      },
+      "rouge2": {
+        "precision": 0.1696203592964782,
+        "recall": 0.22556614456096988,
+        "fscore": 0.1769179306107922
+      },
+      "rougeL": {
+        "precision": 0.2618982426700318,
+        "recall": 0.3437078118709097,
+        "fscore": 0.26676820286543684
+      }
+    },
+    "bleurt": 0.4191427961588729,
+    "gpt": 0.14917127071823205
+  },
+  "openbook": {
+    "acc": {
+      "loose": 0.3152160636708284,
+      "strict": 0.05662983425414365
+    },
+    "rouge": {
+      "rouge1": {
+        "precision": 0.17356455306164578,
+        "recall": 0.39150580236680255,
+        "fscore": 0.20783575754357375
+      },
+      "rouge2": {
+        "precision": 0.09085032002525105,
+        "recall": 0.17549598793784338,
+        "fscore": 0.10625950758793883
+      },
+      "rougeL": {
+        "precision": 0.1532112048714597,
+        "recall": 0.34618346407417766,
+        "fscore": 0.18344705502411385
+      }
+    },
+    "bleurt": 0.4267584370109587,
+    "gpt": 0.1643646408839779
+  },
+  "evidenceprovided": {
+    "acc": {
+      "loose": 0.5456098545791228,
+      "strict": 0.143646408839779
+    },
+    "rouge": {
+      "rouge1": {
+        "precision": 0.4725312298278398,
+        "recall": 0.6085356260042157,
+        "fscore": 0.49998452049151393
+      },
+      "rouge2": {
+        "precision": 0.2815675162719931,
+        "recall": 0.35623992580949976,
+        "fscore": 0.3005037957568856
+      },
+      "rougeL": {
+        "precision": 0.38835972782295014,
+        "recall": 0.5045559933909823,
+        "fscore": 0.41272370572817085
+      }
+    },
+    "bleurt": 0.5298143146528723,
+    "gpt": 0.30386740331491713
+  }
+}
\ No newline at end of file
diff --git a/leaderboard-submissions/results/llama-chat.json b/leaderboard-submissions/results/llama-chat.json
new file mode 100644
index 0000000..f5209b3
--- /dev/null
+++ b/leaderboard-submissions/results/llama-chat.json
@@ -0,0 +1,87 @@
+{
+  "_submission_hash": "",
+  "_results_hash": "",
+  "metadata": {
+    "name": "LLaMA 2 70B",
+    "authors": "Meta",
+    "url": "https://ai.meta.com/research/publications/llama-2-open-foundation-and-fine-tuned-chat-models/",
+    "citation": "Touvron et al., 2023",
+    "type": "FOUNDATION",
+    "context": 4096
+  },
+  "closedbook": {
+    "acc": {
+      "loose": 0.4403229470249054,
+      "strict": 0.058011049723756904
+    },
+    "rouge": {
+      "rouge1": {
+        "precision": 0.21079994013879805,
+        "recall": 0.5309704790876308,
+        "fscore": 0.2847323680812482
+      },
+      "rouge2": {
+        "precision": 0.11206570754887477,
+        "recall": 0.26618658655979804,
+        "fscore": 0.14873440544450633
+      },
+      "rougeL": {
+        "precision": 0.17624114336611502,
+        "recall": 0.44614569152308986,
+        "fscore": 0.23787236888912539
+      }
+    },
+    "bleurt": 0.44125290332331185,
+    "gpt": 0.12016574585635359
+  },
+  "openbook": {
+    "acc": {
+      "loose": 0.38953698927856806,
+      "strict": 0.06353591160220995
+    },
+    "rouge": {
+      "rouge1": {
+        "precision": 0.09966641622516868,
+        "recall": 0.47799987641310493,
+        "fscore": 0.15662035695680138
+      },
+      "rouge2": {
+        "precision": 0.04823947632622272,
+        "recall": 0.21575914217888367,
+        "fscore": 0.07543987012466698
+      },
+      "rougeL": {
+        "precision": 0.08324811278648249,
+        "recall": 0.40852712042925454,
+        "fscore": 0.13141945954530423
+      }
+    },
+    "bleurt": 0.4429991969951938,
+    "gpt": 0.10773480662983426
+  },
+  "evidenceprovided": {
+    "acc": {
+      "loose": 0.5143679183027113,
+      "strict": 0.07734806629834254
+    },
+    "rouge": {
+      "rouge1": {
+        "precision": 0.3407245588154435,
+        "recall": 0.5902473705256917,
+        "fscore": 0.3762628122180759
+      },
+      "rouge2": {
+        "precision": 0.1832699274716267,
+        "recall": 0.31368060953904164,
+        "fscore": 0.20593914103223815
+      },
+      "rougeL": {
+        "precision": 0.27518702361418795,
+        "recall": 0.4795536695039635,
+        "fscore": 0.30410024296144206
+      }
+    },
+    "bleurt": 0.47221096980678773,
+    "gpt": 0.16160220994475138
+  }
+}
\ No newline at end of file
diff --git a/leaderboard-submissions/results/mistral-chat.json b/leaderboard-submissions/results/mistral-chat.json
new file mode 100644
index 0000000..f2f0b1f
--- /dev/null
+++ b/leaderboard-submissions/results/mistral-chat.json
@@ -0,0 +1,87 @@
+{
+  "_submission_hash": "",
+  "_results_hash": "",
+  "metadata": {
+    "name": "Mistral-7B",
+    "authors": "Mistral AI",
+    "url": "https://mistral.ai/news/announcing-mistral-7b/",
+    "citation": "Jiang et al., 2023",
+    "type": "FOUNDATION",
+    "context": 32000
+  },
+  "closedbook": {
+    "acc": {
+      "loose": 0.4271172854502475,
+      "strict": 0.055248618784530384
+    },
+    "rouge": {
+      "rouge1": {
+        "precision": 0.19504405031464528,
+        "recall": 0.5205896670595586,
+        "fscore": 0.2603643670617223
+      },
+      "rouge2": {
+        "precision": 0.09285001789519015,
+        "recall": 0.23254410979936643,
+        "fscore": 0.12283050286793348
+      },
+      "rougeL": {
+        "precision": 0.15867921904916787,
+        "recall": 0.42898549246034995,
+        "fscore": 0.21227960835014928
+      }
+    },
+    "bleurt": 0.4494648841801434,
+    "gpt": 0.10220994475138122
+  },
+  "openbook": {
+    "acc": {
+      "loose": 0.024145046175432918,
+      "strict": 0.0013812154696132596
+    },
+    "rouge": {
+      "rouge1": {
+        "precision": 0.007230514490414043,
+        "recall": 0.029838755315060313,
+        "fscore": 0.010116056959318522
+      },
+      "rouge2": {
+        "precision": 0.0030492661970760036,
+        "recall": 0.01235636714726415,
+        "fscore": 0.004309447012284605
+      },
+      "rougeL": {
+        "precision": 0.006576325561071797,
+        "recall": 0.02700577469421076,
+        "fscore": 0.009108932193761509
+      }
+    },
+    "bleurt": 0.1700935731461858,
+    "gpt": 0.011049723756906077
+  },
+  "evidenceprovided": {
+    "acc": {
+      "loose": 0.539846654625103,
+      "strict": 0.08839779005524862
+    },
+    "rouge": {
+      "rouge1": {
+        "precision": 0.25362992874397977,
+        "recall": 0.6206499844406299,
+        "fscore": 0.3300987746835614
+      },
+      "rouge2": {
+        "precision": 0.13136173541137755,
+        "recall": 0.31550366270027114,
+        "fscore": 0.17182351464162274
+      },
+      "rougeL": {
+        "precision": 0.20309078966310257,
+        "recall": 0.5001600255631405,
+        "fscore": 0.2639495371227864
+      }
+    },
+    "bleurt": 0.4745529419974069,
+    "gpt": 0.20165745856353592
+  }
+}
\ No newline at end of file
diff --git a/leaderboard-submissions/results/mixtral.json b/leaderboard-submissions/results/mixtral.json
new file mode 100644
index 0000000..c708cc5
--- /dev/null
+++ b/leaderboard-submissions/results/mixtral.json
@@ -0,0 +1,87 @@
+{
+  "_submission_hash": "",
+  "_results_hash": "",
+  "metadata": {
+    "name": "Mixtral-8x7B",
+    "authors": "Mistral AI",
+    "url": "https://mistral.ai/news/mixtral-of-experts/",
+    "citation": "Jiang et al., 2024",
+    "type": "FOUNDATION",
+    "context": 32000
+  },
+  "closedbook": {
+    "acc": {
+      "loose": 0.4695900993561285,
+      "strict": 0.08149171270718232
+    },
+    "rouge": {
+      "rouge1": {
+        "precision": 0.2402434133434171,
+        "recall": 0.5465023664516744,
+        "fscore": 0.3023042602650845
+      },
+      "rouge2": {
+        "precision": 0.1278099874524417,
+        "recall": 0.26409680478109976,
+        "fscore": 0.15751696515253602
+      },
+      "rougeL": {
+        "precision": 0.20205125579019406,
+        "recall": 0.46086662623646035,
+        "fscore": 0.2538329572357096
+      }
+    },
+    "bleurt": 0.46641780631565255,
+    "gpt": 0.18646408839779005
+  },
+  "openbook": {
+    "acc": {
+      "loose": 0.3961719668514913,
+      "strict": 0.055248618784530384
+    },
+    "rouge": {
+      "rouge1": {
+        "precision": 0.11787584988437909,
+        "recall": 0.47223446046975565,
+        "fscore": 0.17315178004485718
+      },
+      "rouge2": {
+        "precision": 0.053319584239651184,
+        "recall": 0.20480681092188244,
+        "fscore": 0.07820162065687233
+      },
+      "rougeL": {
+        "precision": 0.10000718238197719,
+        "recall": 0.4077342141256453,
+        "fscore": 0.147182462986372
+      }
+    },
+    "bleurt": 0.4493722631107213,
+    "gpt": 0.1477900552486188
+  },
+  "evidenceprovided": {
+    "acc": {
+      "loose": 0.5760681994469418,
+      "strict": 0.13535911602209943
+    },
+    "rouge": {
+      "rouge1": {
+        "precision": 0.337280859260002,
+        "recall": 0.6511326541771959,
+        "fscore": 0.40933745120007703
+      },
+      "rouge2": {
+        "precision": 0.1943735281050035,
+        "recall": 0.3485360713472991,
+        "fscore": 0.23141031987255675
+      },
+      "rougeL": {
+        "precision": 0.282396718505277,
+        "recall": 0.5503517413117182,
+        "fscore": 0.34298526601178303
+      }
+    },
+    "bleurt": 0.508856576296259,
+    "gpt": 0.28314917127071826
+  }
+}
\ No newline at end of file