-
Notifications
You must be signed in to change notification settings - Fork 0
Files
/
Copy pathelo.csv
195 lines (195 loc) · 10.8 KB
/
elo.csv
1 | model | overall | hard | coding | cpmi | launch | end | source |
---|---|---|---|---|---|---|---|---|
2 | gemini-2.0-flash-thinking-exp-01-21 | 1310 | 1381 | 1359 | 4.001 | 2025-01 | ||
3 | gemini-2.0-pro-exp-02-05 | 1318 | 1381 | 1371 | 5.001 | 2025-02 | ||
4 | gemini-exp-1206 | 1321 | 1311 | 1368 | 5.001 | 2024-11 | ||
5 | gemini-2.0-flash-thinking-exp-1219 | 1308 | 1302 | 1343 | 4.001 | 2024-12 | 2024-12 | |
6 | chatgpt-4o-latest-20241120 | 1318 | 1340 | 1351 | 5 | 2024-11 | https://openai.com/api/pricing/ | |
7 | gemini-2.0-flash | 1286 | 1350 | 1348 | 0.1 | 2025-02 | ||
8 | deepseek-r1 | 1319 | 1367 | 1362 | 0.27 | 2025-01 | ||
9 | o1-2024-12-17 | 1322 | 1370 | 1362 | 15 | 2024-12 | ||
10 | o1-preview | 1303 | 1351 | 1355 | 15 | 2024-09 | https://openai.com/api/pricing/ | |
11 | qwen2.5-max | 1280 | 1343 | 1339 | 1.6 | 2025-01 | ||
12 | gemini-2.0-flash-exp | 1296 | 1291 | 1351 | 2.001 | 2024-12 | ||
13 | chatgpt-4o-latest-20240903 | 1291 | 1277 | 1347 | 5 | 2024-08 | 2024-11 | https://openai.com/api/pricing/ |
14 | o3-mini | 1274 | 1368 | 1356 | 1.1 | 2025-01 | ||
15 | deepseek-v3 | 1274 | 1304 | 1316 | 0.14 | 2024-12 | ||
16 | gemini-2.0-flash-lite-preview | 1265 | 1317 | 1309 | 0.075 | 2025-02 | ||
17 | claude-3-5-sonnet-20241022 | 1285 | 1303 | 1324 | 3 | 2024-10 | ||
18 | step-2-16k-exp-202412 | 1250 | 1294 | 1295 | 2024-12 | |||
19 | gemini-exp-1114 | 1268 | 1272 | 1325 | 5.001 | 2024-11 | 2024-12 | |
20 | glm-4-plus-0111 | 1249 | 1283 | 1290 | ||||
21 | gemini-1.5-pro-002 | 1268 | 1295 | 1289 | 5 | 2024-10 | ||
22 | gpt-4o-2024-05-13 | 1263 | 1284 | 1292 | 2.5 | 2024-09 | ||
23 | claude-3-5-sonnet-20240620 | 1259 | 1279 | 1294 | 3 | 2024-06 | ||
24 | o1-mini | 1256 | 1335 | 1353 | 3 | 2024-09 | https://openai.com/api/pricing/ | |
25 | gemini-advanced-0514 | 1254 | 1253 | 1254 | 2024-05 | |||
26 | qwen2.5-plus-1127 | 1231 | 1299 | 1302 | 2024-12 | |||
27 | llama-3.1-405b-instruct-fp8 | 1252 | 1266 | 1275 | 2.75 | 2024-07 | https://openrouter.ai/meta-llama/llama-3.1-405b-instruct | |
28 | deepseek-v2.5-1210 | 1240 | 1290 | 1296 | 0.14 | 2024-12 | ||
29 | llama-3.1-405b-instruct-bf16 | 1253 | 1268 | 1278 | 2 | 2024-06 | https://openrouter.ai/models/meta-llama/llama-3.1-405b | |
30 | gpt-4o-2024-08-06 | 1250 | 1266 | 1273 | 2.5 | 2024-08 | https://openai.com/api/pricing/ | |
31 | grok-2-2024-08-13 | 1249 | 1273 | 1282 | 5 | 2024-09 | https://openrouter.ai/x-ai/grok-2 | |
32 | yi-lightning | 1246 | 1299 | 1302 | 2024-10 | |||
33 | gpt-4-turbo-2024-04-09 | 1242 | 1254 | 1262 | 10 | 2024-04 | https://openai.com/api/pricing/ | |
34 | gemini-1.5-pro-001 | 1241 | 1258 | 1262 | 3.5 | 2024-05 | https://ai.google.dev/pricing | |
35 | claude-3-opus-20240229 | 1238 | 1245 | 1250 | 15 | 2024-02 | ||
36 | yi-lightning-lite | 1238 | 1235 | 1266 | 2024-10 | |||
37 | claude-3-5-haiku-20241022 | 1232 | 1246 | 1263 | 0.8 | 2024-11 | ||
38 | glm-4-plus | 1235 | 1273 | 1283 | 0.33 | 2024-10 | https://open.bigmodel.cn/pricing | |
39 | gpt-4-1106-preview | 1234 | 1246 | 1252 | 10 | 2023-11 | https://openai.com/api/pricing/ | |
40 | athene-v2-chat | 1230 | 1292 | 1299 | 2024-12 | |||
41 | gpt-4o-mini-2024-07-18 | 1235 | 1268 | 1284 | 0.15 | 2024-07 | https://openai.com/api/pricing/ | |
42 | qwen-max-0919 | 1231 | 1272 | 1279 | 2024-09 | |||
43 | llama-3.3-70b-instruct | 1234 | 1260 | 1258 | 0.13 | 2024-12 | https://openrouter.ai/meta-llama/llama-3.3-70b-instruct | |
44 | mistral-large-2407 | 1231 | 1259 | 1269 | 2 | 2024-07 | https://openrouter.ai/models/mistralai/mistral-large | |
45 | gpt-4-0125-preview | 1231 | 1241 | 1243 | 10 | 2024-01 | https://openai.com/api/pricing/ | |
46 | gemini-1.5-flash-002 | 1229 | 1258 | 1253 | 0.075 | 2024-10 | ||
47 | deepseek-v2.5 | 1226 | 1272 | 1287 | 0.14 | 2024-08 | https://openrouter.ai/models/deepseek/deepseek-chat | |
48 | grok-2-mini-2024-08-13 | 1224 | 1258 | 1261 | 2024-08 | |||
49 | qwen2.5-72b-instruct | 1222 | 1270 | 1282 | 0.35 | 2024-09 | https://openrouter.ai/models/qwen/qwen-2.5-72b-instruct | |
50 | athene-70b-0725 | 1223 | 1247 | 1253 | 2024-07 | |||
51 | mistral-large-2411 | 1217 | 1248 | 1262 | 2 | 2024-11 | ||
52 | amazon-nova-pro-v1.0 | 1208 | 1240 | 1258 | 0.8 | 2024-11 | ||
53 | llama-3.1-nemotron-70b-instruct | 1216 | 1265 | 1270 | 0.35 | 2024-10 | https://openrouter.ai/nvidia/llama-3.1-nemotron-70b-instruct | |
54 | llama-3.1-tulu-3-70b | 1208 | 1223 | 1231 | ||||
55 | llama-3.1-70b-instruct | 1214 | 1243 | 1251 | 0.52 | 2024-06 | https://openrouter.ai/models/meta-llama/llama-3.1-70b-instruct | |
56 | yi-large-preview | 1206 | 1206 | 1245 | 2024-07 | |||
57 | reka-core-20240904 | 1207 | 1215 | 1221 | 2024-09 | |||
58 | gemma-2-27b-it | 1207 | 1204 | 1209 | 0.27 | 2024-06 | https://openrouter.ai/models/google/gemma-2-27b-it | |
59 | qwen-plus-0828 | 1206 | 1209 | 1245 | 2024-08 | |||
60 | reka-core-20240722 | 1204 | 1186 | 1208 | 2024-07 | |||
61 | jamba-1.5-large | 1205 | 1219 | 1227 | 2 | 2024-08 | https://openrouter.ai/models/ai21/jamba-1-5-large | |
62 | gemini-1.5-flash-001 | 1204 | 1224 | 1231 | 0.075 | 2024-08 | https://ai.google.dev/pricing | |
63 | llama-3.1-nemotron-51b-instruct | 1203 | 1206 | 1210 | 0.35 | 2024-10 | https://openrouter.ai/nvidia/llama-3.1-nemotron-70b-instruct | |
64 | amazon-nova-lite-v1.0 | 1184 | 1222 | 1234 | 0.06 | 2024-11 | ||
65 | deepseek-v2-api-0628 | 1202 | 1211 | 1241 | 0.14 | 2024-06 | ||
66 | gpt-4-0314 | 1199 | 1195 | 1195 | 30 | 2024-03 | https://platform.openai.com/docs/deprecations/ | |
67 | gemma-2-9b-it-simpo | 1199 | 1203 | 1196 | ||||
68 | phi-4 | 1179 | 1228 | 1240 | 2024-11 | |||
69 | claude-3-sonnet-20240229 | 1197 | 1199 | 1212 | 3 | 2024-02 | ||
70 | command-r-plus-08-2024 | 1197 | 1188 | 1181 | 2024-08 | |||
71 | deepseek-coder-v2-0724 | 1197 | 1210 | 1266 | 0.14 | 2024-07 | ||
72 | nemotron-4-340b-instruct | 1196 | 1202 | 1198 | 4.2 | 2024-06 | https://openrouter.ai/models/nvidia/nemotron-4-340b-instruct | |
73 | c4ai-aya-expanse-32b | 1185 | 1197 | 1192 | 2024-11 | |||
74 | yi-large | 1194 | 1185 | 1219 | 3 | 2023-10 | https://openrouter.ai/models/01-ai/yi-large | |
75 | llama-3-70b-instruct | 1195 | 1197 | 1199 | 0.59 | 2024-04 | https://openrouter.ai/models/meta-llama/llama-3-70b-instruct | |
76 | qwen2.5-coder-32b-instruct | 1189 | 1256 | 1260 | 2024-10 | |||
77 | reka-flash-20240904 | 1192 | 1185 | 1190 | 2024-09 | |||
78 | glm-4-0520 | 1188 | 1213 | 1216 | 0.66 | 2024-05 | https://open.bigmodel.cn/pricing | |
79 | gpt-4-0613 | 1185 | 1167 | 1166 | 30 | 2024-06 | https://platform.openai.com/docs/deprecations/ | |
80 | llama-3.1-tulu-3-8b | 1146 | 1179 | 1178 | 2025-01 | |||
81 | command-r-plus | 1182 | 1168 | 1164 | 3 | 2024-01 | ||
82 | deepseek-coder-v2 | 1182 | 1211 | 1239 | 0.14 | 2024-07 | https://openrouter.ai/models/deepseek/deepseek-coder | |
83 | reka-flash-20240722 | 1180 | 1165 | 1186 | 2024-07 | |||
84 | qwen2-72b-instruct | 1180 | 1188 | 1186 | 0.34 | 2024-06 | https://openrouter.ai/qwen/qwen-2-72b-instruct | |
85 | gemini-1.5-flash-8b-001 | 1179 | 1212 | 1207 | 0.0375 | 2024-10 | ||
86 | amazon-nova-micro-v1.0 | 1163 | 1197 | 1211 | 0.035 | 2024-11 | ||
87 | gemma-2-9b-it | 1180 | 1173 | 1173 | 0.2 | 2024-06 | https://openrouter.ai/models/google/gemma-2-9b-it | |
88 | reka-core-20240501 | 1177 | 1168 | 1189 | 2024-05 | |||
89 | claude-3-haiku-20240307 | 1177 | 1178 | 1189 | 0.25 | 2024-03 | ||
90 | command-r-08-2024 | 1175 | 1169 | 1161 | 2024-08 | |||
91 | gemini-1.5-flash-8b-exp-0827 | 1172 | 1162 | 1189 | 2024-08 | |||
92 | qwen-max-0428 | 1171 | 1168 | 1189 | 2024-04 | |||
93 | c4ai-aya-expanse-8b | 1150 | 1162 | 1165 | 2024-11 | |||
94 | glm-4-0116 | 1162 | 1165 | 1190 | 2024-01 | |||
95 | ministral-8b-2410 | 1159 | 1198 | 1201 | 0.1 | 2024-10 | https://openrouter.ai/mistralai/ministral-8b | |
96 | jamba-1.5-mini | 1160 | 1168 | 1180 | 0.2 | 2024-08 | https://openrouter.ai/models/ai21/jamba-1-5-mini | |
97 | claude-1 | 1158 | 1134 | 1135 | 8 | 2023-03 | ||
98 | mistral-large-2402 | 1157 | 1165 | 1169 | 8 | 2023-11 | ||
99 | qwen1.5-110b-chat | 1155 | 1168 | 1174 | 1.62 | 2024-04 | https://openrouter.ai/models/qwen/qwen-110b-chat | |
100 | hunyuan-standard-256k | 1152 | 1220 | 1226 | ||||
101 | reka-flash-preview-20240611 | 1151 | 1136 | 1155 | 2024-08 | |||
102 | granite-3.1-8b-instruct | 1134 | 1148 | 1171 | 2024-11 | |||
103 | reka-flash-21b-20240226-online | 1151 | 1142 | 1146 | 2024-02 | |||
104 | mixtral-8x22b-instruct-v0.1 | 1149 | 1148 | 1152 | 0.7 | 2024-05 | ||
105 | mistral-next | 1149 | 1147 | 1132 | ||||
106 | command-r | 1147 | 1119 | 1122 | 0.5 | 2023-12 | ||
107 | qwen1.5-72b-chat | 1148 | 1146 | 1159 | 0.81 | 2024-01 | https://openrouter.ai/models/qwen/qwen-72b-chat | |
108 | gemini-pro-dev-api | 1147 | 1105 | 1102 | 0.5 | 2024-01 | https://ai.google.dev/pricing | |
109 | claude-2.0 | 1145 | 1140 | 1134 | 8 | 2023-07 | ||
110 | granite-3.1-2b-instruct | 1103 | 1143 | 1146 | 2024-11 | |||
111 | llama-3-8b-instruct | 1142 | 1137 | 1145 | 0.05 | 2024-04 | ||
112 | reka-flash-21b-20240226 | 1141 | 1133 | 1141 | 2024-02 | |||
113 | mistral-medium | 1141 | 1144 | 1152 | 2.7 | 2023-11 | ||
114 | gpt-3.5-turbo-0314 | 1141 | 1138 | 1114 | 0.5 | 2023-03 | ||
115 | gpt-3.5-turbo-0125 | 1137 | 1112 | 1123 | 0.5 | 2024-01 | ||
116 | qwq-32b-preview | 1088 | 1174 | 1146 | 2024-11 | |||
117 | gpt-3.5-turbo-0613 | 1136 | 1134 | 1134 | 1.5 | 2023-06 | https://openai.com/api/pricing/ | |
118 | claude-2.1 | 1134 | 1135 | 1131 | 8 | 2023-11 | ||
119 | yi-1.5-34b-chat | 1133 | 1160 | 1162 | 2024-05 | |||
120 | llama-3.1-8b-instruct | 1133 | 1182 | 1186 | 0.06 | 2024-06 | https://openrouter.ai/models/meta-llama/llama-3.1-8b-instruct | |
121 | gemini-pro | 1131 | 1083 | 1091 | 0.5 | 2023-12 | https://ai.google.dev/pricing | |
122 | zephyr-orpo-141b-A35b-v0.1 | 1130 | 1116 | 1124 | ||||
123 | qwen1.5-32b-chat | 1126 | 1135 | 1149 | 0.72 | 2023-11 | https://openrouter.ai/models/qwen/qwen-32b-chat | |
124 | claude-instant-1 | 1127 | 1123 | 1108 | 0.8 | 2023-03 | ||
125 | phi-3-medium-4k-instruct | 1118 | 1129 | 1125 | https://openrouter.ai/microsoft/phi-3-medium-4k-instruct | |||
126 | internlm2_5-20b-chat | 1116 | 1164 | 1157 | ||||
127 | gemma-2-2b-it | 1117 | 1118 | 1106 | 0.06 | 2024-06 | https://openrouter.ai/google/gemma-2-9b-it | |
128 | mixtral-8x7b-instruct-v0.1 | 1114 | 1114 | 1114 | 0.3 | 2024-03 | ||
129 | dbrx-instruct-preview | 1113 | 1109 | 1117 | ||||
130 | granite-3.0-8b-instruct | 1109 | 1109 | 1097 | 2024-11 | |||
131 | gpt-3.5-turbo-1106 | 1109 | 1090 | 1094 | 0.5 | 2023-11 | ||
132 | qwen1.5-14b-chat | 1106 | 1116 | 1125 | 0.27 | 2023-09 | https://openrouter.ai/models/qwen/qwen-14b-chat | |
133 | wizardlm-70b | 1104 | 1077 | 1071 | ||||
134 | snowflake-arctic-instruct | 1102 | 1073 | 1076 | 2.16 | 2023-12 | https://openrouter.ai/models/snowflake/snowflake-arctic-instruct | |
135 | yi-34b-chat | 1101 | 1102 | 1106 | 0.72 | 2023-11 | https://openrouter.ai/models/01-ai/yi-34b-chat | |
136 | openchat-3.5-0106 | 1100 | 1083 | 1101 | 0.13 | 2024-01 | ||
137 | phi-3-small-8k-instruct | 1098 | 1107 | 1107 | ||||
138 | gemma-1.1-7b-it | 1099 | 1076 | 1084 | 0.1 | 2024-04 | ||
139 | openchat-3.5 | 1094 | 1065 | 1053 | 0.13 | 2024-01 | ||
140 | llama-3.2-3b-instruct | 1093 | 1102 | 1080 | ||||
141 | tulu-2-dpo-70b | 1092 | 1098 | 1093 | ||||
142 | starling-lm-7b-beta | 1091 | 1119 | 1129 | 2024-03 | |||
143 | vicuna-33b | 1091 | 1066 | 1067 | ||||
144 | deepseek-llm-67b-chat | 1090 | 1065 | 1079 | ||||
145 | openhermes-2.5-mistral-7b | 1089 | 1068 | 1057 | ||||
146 | smollm2-1.7b-instruct | 1051 | 1078 | 1043 | 2025-01 | |||
147 | starling-lm-7b-alpha | 1083 | 1072 | 1079 | ||||
148 | llama-2-70b-chat | 1081 | 1070 | 1072 | 0.64 | 2023-07 | ||
149 | granite-3.0-2b-instruct | 1081 | 1089 | 1087 | 2024-11 | |||
150 | pplx-70b-online | 1076 | 1029 | 1028 | 1 | 2024-02 | ||
151 | llama2-70b-steerlm-chat | 1073 | 1045 | 1022 | 2023-07 | |||
152 | nous-hermes-2-mixtral-8x7b-dpo | 1071 | 1052 | 1079 | ||||
153 | dolphin-2.2.1-mistral-7b | 1068 | 1050 | 1024 | ||||
154 | mistral-7b-instruct-v0.2 | 1067 | 1068 | 1073 | 0.06 | 2023-12 | ||
155 | phi-3-mini-4k-instruct-june-2024 | 1068 | 1095 | 1081 | ||||
156 | qwen1.5-7b-chat | 1065 | 1067 | 1089 | 0.18 | 2023-09 | https://openrouter.ai/models/qwen/qwen-7b-chat | |
157 | solar-10.7b-instruct-v1.0 | 1065 | 1056 | 1047 | ||||
158 | wizardlm-13b | 1063 | 1013 | 1025 | ||||
159 | mpt-30b-chat | 1060 | 1047 | 1030 | ||||
160 | falcon-180b-chat | 1058 | 1000 | 1017 | ||||
161 | vicuna-13b | 1058 | 1025 | 1032 | ||||
162 | qwen-14b-chat | 1056 | 1023 | 1056 | ||||
163 | phi-3-mini-4k-instruct | 1055 | 1078 | 1085 | 2024-05 | |||
164 | llama-2-13b-chat | 1054 | 1049 | 1051 | 0.1 | 2023-07 | ||
165 | zephyr-7b-beta | 1049 | 1026 | 1030 | ||||
166 | phi-3-mini-128k-instruct | 1048 | 1035 | 1029 | 2024-05 | |||
167 | codellama-34b-instruct | 1047 | 1027 | 1041 | ||||
168 | gemma-7b-it | 1048 | 1045 | 1046 | 0.1 | 2024-04 | ||
169 | zephyr-7b-alpha | 1046 | 1022 | 1034 | ||||
170 | llama-3.2-1b-instruct | 1045 | 1058 | 1046 | ||||
171 | palm-2 | 1042 | 1000 | 990 | ||||
172 | pplx-7b-online | 1041 | 1017 | 1014 | 0.2 | 2024-02 | ||
173 | guanaco-33b | 1039 | 1000 | 965 | ||||
174 | gemma-1.1-2b-it | 1040 | 1015 | 1035 | 2024-04 | |||
175 | codellama-70b-instruct | 1037 | 1051 | 1047 | ||||
176 | stripedhyena-nous-7b | 1033 | 995 | 999 | ||||
177 | mistral-7b-instruct | 1026 | 1002 | 1007 | 0.11 | 2023-09 | ||
178 | llama-2-7b-chat | 1024 | 1009 | 1002 | 0.56 | 2023-07 | ||
179 | vicuna-7b | 1021 | 989 | 981 | ||||
180 | qwen1.5-4b-chat | 1014 | 977 | 990 | 0.09 | 2023-09 | https://openrouter.ai/models/qwen/qwen-4b-chat | |
181 | gemma-2b-it | 1008 | 987 | 1000 | ||||
182 | olmo-7b-instruct | 993 | 994 | 1017 | ||||
183 | koala-13b | 979 | 924 | 937 | ||||
184 | chatglm3-6b | 974 | 952 | 953 | ||||
185 | gpt4all-13b-snoozy | 971 | 930 | 909 | ||||
186 | mpt-7b-chat | 967 | 891 | 899 | ||||
187 | alpaca-13b | 966 | 818 | 789 | ||||
188 | RWKV-4-Raven-14B | 948 | 890 | 896 | ||||
189 | chatglm2-6b | 942 | 914 | 892 | ||||
190 | oasst-pythia-12b | 930 | 880 | 873 | ||||
191 | fastchat-t5-3b | 896 | 808 | 759 | ||||
192 | chatglm-6b | 887 | 893 | 883 | ||||
193 | dolly-v2-12b | 880 | 797 | 746 | ||||
194 | llama-13b | 866 | 723 | 669 | ||||
195 | stablelm-tuned-alpha-7b | 858 | 830 | 858 |