Human Leaderboard: 7 day

  • Ranking: The position of the model in the leaderboard as ordered by Overall Score
  • Organization: The group responsible for the model or forecasts
  • Model: The LLM model & prompt info or the human group and forecast aggregation method
    • zero shot: used a zero-shot prompt
    • scratchpad: used a scratchpad prompt with instructions that outline a procedure the model should use to reason about the question
    • with freeze values: means that, for questions from market sources, the prompt was supplemented with the aggregate human forecast from the relevant platform on the day the question set was generated
    • with news: means that the prompt was supplemented with relevant news summaries obtained through an automated process
  • Dataset Score: The average Brier score across all questions sourced from datasets
  • Market Score (resolved): The average Brier score across all resolved questions sourced from prediction markets and forecast aggregation platforms
  • Market Score (unresolved): The average Brier score across all unresolved questions sourced from prediction markets and forecast aggregation platforms
  • Market Score (overall): The average Brier score across all questions sourced from prediction markets and forecast aggregation platforms
  • Overall Resolved Score: The average of the Dataset Score and the Market Score (resolved) columns
  • Overall Score: The average of the Dataset Score and the Market Score (overall) columns
  • Overall Score 95% CI: The 95% confidence interval for the Overall Score
  • Pairwise p-value comparing to No. 1 (bootstrapped): The p-value calculated by bootstrapping the differences in overall score between each model and the best forecaster (the group with rank 1) under the null hypothesis that there's no difference.
  • Pct. more accurate than No. 1: The percent of questions where this forecaster had a better overall score than the best forecaster (with rank 1)
  • Pct. imputed: The percent of questions for which this forecaster did not provide a forecast and hence had a forecast value imputed (0.5 for dataset questions and the aggregate human forecast on the forecast due date for questions sourced from prediction markets or forecast aggregation platforms)
Ranking Organization Model Dataset Score (N=104) Market Score (resolved) (N=14) Market Score (unresolved) (N=63) Market Score (overall) (N=77) Overall Resolved Score (N=118) Overall Score (N=181) Overall Score 95% CI Pairwise p-value comparing to No. 1 (bootstrapped) Pct. more accurate than No. 1 Pct. Imputed
1 ForecastBench Superforecaster median forecast 0.132 0.119 0.036 0.051 0.125 0.091 [0.07, 0.113] 0% 0%
2 OpenAI GPT-4 (zero shot with freeze values) 0.158 0.184 0.028 0.056 0.171 0.107 [0.085, 0.129] 0.062 38% 0%
3 ForecastBench Public median forecast 0.172 0.165 0.022 0.048 0.169 0.110 [0.089, 0.132] 0.015 29% 0%
4 OpenAI GPT-4o (scratchpad with freeze values) 0.163 0.170 0.034 0.059 0.167 0.111 [0.09, 0.133] 0.031 30% 0%
5 Anthropic Claude-3-5-Sonnet-20240620 (scratchpad with freeze values) 0.159 0.196 0.039 0.067 0.177 0.113 [0.089, 0.137] 0.027 30% 0%
6 Anthropic Claude-3-5-Sonnet-20240620 (zero shot with freeze values) 0.152 0.288 0.026 0.074 0.220 0.113 [0.087, 0.139] 0.038 35% 0%
7 OpenAI GPT-4-Turbo-2024-04-09 (zero shot with freeze values) 0.172 0.184 0.026 0.055 0.178 0.114 [0.093, 0.134] 0.007 36% 0%
8 Anthropic Claude-3-5-Sonnet-20240620 (scratchpad with news with freeze values) 0.161 0.215 0.038 0.070 0.188 0.115 [0.093, 0.138] 0.019 31% 0%
9 Mistral AI Mistral-Large-Latest (zero shot with freeze values) 0.160 0.196 0.047 0.074 0.178 0.117 [0.094, 0.14] 0.008 29% 0%
10 OpenAI GPT-4o (scratchpad with news with freeze values) 0.183 0.119 0.045 0.059 0.151 0.121 [0.098, 0.143] 0.002 29% 0%
11 Mistral AI Mistral-Large-Latest (scratchpad with freeze values) 0.164 0.158 0.064 0.081 0.161 0.123 [0.105, 0.14] 0.001 24% 0%
12 Meta Llama-3-70b-Chat-Hf (zero shot with freeze values) 0.171 0.177 0.053 0.076 0.174 0.123 [0.101, 0.145] 0.003 29% 0%
13 OpenAI GPT-4o (scratchpad) 0.163 0.199 0.059 0.084 0.181 0.124 [0.103, 0.145] 0.002 25% 0%
14 OpenAI GPT-4 (scratchpad with freeze values) 0.180 0.173 0.046 0.069 0.176 0.124 [0.107, 0.141] 0.001 25% 0%
15 Anthropic Claude-3-5-Sonnet-20240620 (scratchpad) 0.159 0.252 0.058 0.093 0.206 0.126 [0.102, 0.15] 0.007 26% 0%
16 Meta Llama-3-70b-Chat-Hf (scratchpad with freeze values) 0.180 0.149 0.059 0.076 0.164 0.128 [0.111, 0.144] <0.001 24% 0%
17 Anthropic Claude-3-5-Sonnet-20240620 (superforecaster with news 3) 0.174 0.186 0.058 0.082 0.180 0.128 [0.107, 0.149] 0.001 26% 0%
18 Qwen Qwen1.5-110B-Chat (zero shot with freeze values) 0.190 0.170 0.042 0.065 0.180 0.128 [0.108, 0.148] <0.001 30% 0%
19 Anthropic Claude-3-Opus-20240229 (zero shot with freeze values) 0.185 0.206 0.041 0.071 0.196 0.128 [0.103, 0.154] 0.004 35% 0%
20 Anthropic Claude-3-5-Sonnet-20240620 (scratchpad with news) 0.161 0.222 0.069 0.097 0.191 0.129 [0.105, 0.152] 0.002 26% 0%
21 Anthropic Claude-2.1 (scratchpad with freeze values) 0.203 0.061 0.054 0.055 0.132 0.129 [0.113, 0.145] <0.001 30% 23%
22 Anthropic Claude-3-Opus-20240229 (scratchpad with freeze values) 0.172 0.173 0.074 0.092 0.173 0.132 [0.11, 0.154] <0.001 26% 0%
23 Mistral AI Mixtral-8x22B-Instruct-V0.1 (zero shot with freeze values) 0.185 0.183 0.056 0.079 0.184 0.132 [0.107, 0.157] 0.002 32% 0%
24 Anthropic Claude-3-5-Sonnet-20240620 (superforecaster with news 1) 0.176 0.228 0.058 0.089 0.202 0.132 [0.109, 0.156] 0.001 26% 0%
25 Anthropic Claude-3-5-Sonnet-20240620 (zero shot) 0.152 0.308 0.071 0.114 0.230 0.133 [0.106, 0.16] 0.005 26% 0%
26 Google Gemini-1.5-Flash (zero shot with freeze values) 0.177 0.205 0.063 0.089 0.191 0.133 [0.104, 0.162] 0.004 31% 0%
27 Google Gemini-1.5-Pro (zero shot with freeze values) 0.191 0.201 0.048 0.076 0.196 0.133 [0.107, 0.16] 0.002 30% 0%
28 Google Gemini-1.5-Flash (scratchpad with freeze values) 0.190 0.164 0.058 0.077 0.177 0.134 [0.111, 0.156] 0.001 25% 0%
29 OpenAI GPT-4o (zero shot with freeze values) 0.205 0.185 0.036 0.063 0.195 0.134 [0.108, 0.16] 0.001 33% 0%
30 Mistral AI Mixtral-8x22B-Instruct-V0.1 (scratchpad with freeze values) 0.183 0.187 0.063 0.086 0.185 0.134 [0.115, 0.153] <0.001 25% 0%
31 OpenAI GPT-4-Turbo-2024-04-09 (zero shot) 0.172 0.235 0.067 0.098 0.204 0.135 [0.114, 0.156] <0.001 22% 0%
32 OpenAI GPT-4o (scratchpad with news) 0.183 0.195 0.065 0.089 0.189 0.136 [0.11, 0.161] <0.001 25% 0%
33 Anthropic Claude-3-Opus-20240229 (scratchpad) 0.172 0.189 0.080 0.100 0.180 0.136 [0.115, 0.157] <0.001 25% 0%
34 OpenAI GPT-4-Turbo-2024-04-09 (scratchpad with freeze values) 0.188 0.152 0.070 0.085 0.170 0.136 [0.111, 0.161] 0.001 28% 0%
35 Anthropic Claude-2.1 (scratchpad) 0.203 0.111 0.061 0.070 0.157 0.136 [0.117, 0.156] <0.001 28% 23%
36 Google Gemini-1.5-Pro (scratchpad with freeze values) 0.175 0.222 0.072 0.099 0.198 0.137 [0.117, 0.157] <0.001 26% 0%
37 OpenAI GPT-4 (scratchpad) 0.180 0.176 0.079 0.096 0.178 0.138 [0.121, 0.155] <0.001 21% 0%
38 OpenAI GPT-4 (zero shot) 0.158 0.181 0.105 0.119 0.169 0.138 [0.119, 0.158] <0.001 24% 0%
39 ForecastBench LLM Crowd (gpt-4o, claude-3.5-sonnet, gemini-1.5-pro) with news 0.194 0.206 0.062 0.088 0.200 0.141 [0.12, 0.162] <0.001 24% 0%
40 Google Gemini-1.5-Pro (scratchpad with news with freeze values) 0.187 0.176 0.079 0.096 0.181 0.141 [0.119, 0.164] <0.001 24% 0%
41 ForecastBench LLM Crowd (gpt-4o, claude-3.5-sonnet, gemini-1.5-pro) with news 0.196 0.197 0.063 0.087 0.196 0.141 [0.12, 0.163] <0.001 26% 0%
42 ForecastBench LLM Crowd (gpt-4o, claude-3.5-sonnet, gemini-1.5-pro) with news 0.194 0.203 0.063 0.089 0.199 0.142 [0.12, 0.163] <0.001 25% 0%
43 OpenAI GPT-4-Turbo-2024-04-09 (scratchpad) 0.188 0.206 0.071 0.095 0.197 0.142 [0.121, 0.162] <0.001 24% 0%
44 Google Gemini-1.5-Pro (scratchpad) 0.175 0.233 0.081 0.109 0.204 0.142 [0.121, 0.163] <0.001 24% 0%
45 Anthropic Claude-2.1 (zero shot with freeze values) 0.218 0.184 0.041 0.067 0.201 0.142 [0.122, 0.163] <0.001 32% 0%
46 OpenAI GPT-4-Turbo-2024-04-09 (scratchpad with news with freeze values) 0.196 0.157 0.076 0.090 0.177 0.143 [0.117, 0.169] <0.001 32% 0%
47 ForecastBench Imputed Forecaster 0.250 0.107 0.021 0.037 0.179 0.143 [0.129, 0.158] <0.001 35% 100%
48 Mistral AI Mistral-Large-Latest (scratchpad) 0.164 0.230 0.099 0.123 0.197 0.144 [0.124, 0.163] <0.001 24% 0%
49 Meta Llama-3-70b-Chat-Hf (zero shot) 0.171 0.233 0.095 0.120 0.202 0.145 [0.124, 0.167] <0.001 23% 0%
50 Mistral AI Mistral-Large-Latest (zero shot) 0.160 0.195 0.118 0.132 0.178 0.146 [0.121, 0.171] <0.001 23% 0%
51 Mistral AI Mixtral-8x7B-Instruct-V0.1 (zero shot with freeze values) 0.203 0.202 0.065 0.090 0.203 0.147 [0.113, 0.181] 0.001 37% 0%
52 Qwen Qwen1.5-110B-Chat (scratchpad with news with freeze values) 0.194 0.182 0.085 0.103 0.188 0.148 [0.127, 0.169] <0.001 25% 0%
53 OpenAI GPT-4o (superforecaster with news 3) 0.203 0.174 0.076 0.094 0.189 0.148 [0.127, 0.17] <0.001 23% 0%
54 Anthropic Claude-3-Opus-20240229 (zero shot) 0.185 0.244 0.083 0.112 0.214 0.149 [0.122, 0.175] <0.001 26% 0%
55 Google Gemini-1.5-Flash (scratchpad) 0.190 0.202 0.086 0.108 0.196 0.149 [0.126, 0.172] <0.001 21% 0%
56 Mistral AI Mixtral-8x22B-Instruct-V0.1 (scratchpad) 0.183 0.229 0.090 0.116 0.206 0.149 [0.129, 0.169] <0.001 23% 0%
57 Google Gemini-1.5-Pro (scratchpad with news) 0.187 0.174 0.098 0.112 0.180 0.149 [0.127, 0.172] <0.001 24% 0%
58 Meta Llama-3-8b-Chat-Hf (zero shot with freeze values) 0.199 0.246 0.069 0.101 0.222 0.150 [0.123, 0.177] <0.001 26% 0%
59 OpenAI GPT-4o (zero shot) 0.205 0.232 0.067 0.097 0.218 0.151 [0.126, 0.175] <0.001 22% 0%
60 Mistral AI Mixtral-8x22B-Instruct-V0.1 (scratchpad with news with freeze values) 0.198 0.181 0.088 0.105 0.189 0.151 [0.129, 0.173] <0.001 23% 0%
61 Qwen Qwen1.5-110B-Chat (scratchpad with freeze values) 0.205 0.205 0.074 0.098 0.205 0.152 [0.132, 0.171] <0.001 22% 0%
62 Mistral AI Mixtral-8x7B-Instruct-V0.1 (scratchpad) 0.194 0.131 0.104 0.109 0.163 0.152 [0.131, 0.172] <0.001 29% 14%
63 Anthropic Claude-2.1 (scratchpad with news) 0.208 0.190 0.075 0.096 0.199 0.152 [0.131, 0.173] <0.001 26% 8%
64 Anthropic Claude-3-Opus-20240229 (superforecaster with news 1) 0.174 0.272 0.101 0.132 0.223 0.153 [0.128, 0.177] <0.001 24% 0%
65 OpenAI GPT-4-Turbo-2024-04-09 (scratchpad with news) 0.196 0.203 0.090 0.110 0.200 0.153 [0.128, 0.178] <0.001 28% 0%
66 Qwen Qwen1.5-110B-Chat (zero shot) 0.190 0.226 0.092 0.116 0.208 0.153 [0.132, 0.175] <0.001 20% 1%
67 Google Gemini-1.5-Flash (scratchpad with news with freeze values) 0.200 0.232 0.080 0.108 0.216 0.154 [0.128, 0.179] <0.001 24% 0%
68 OpenAI GPT-4-Turbo-2024-04-09 (superforecaster with news 3) 0.207 0.161 0.087 0.101 0.184 0.154 [0.132, 0.175] <0.001 26% 0%
69 Qwen Qwen1.5-110B-Chat (scratchpad with news) 0.194 0.188 0.099 0.115 0.191 0.154 [0.133, 0.176] <0.001 24% 0%
70 Google Gemini-1.5-Pro (superforecaster with news 3) 0.195 0.171 0.101 0.114 0.183 0.155 [0.132, 0.177] <0.001 25% 0%
71 Google Gemini-1.5-Pro (zero shot) 0.191 0.297 0.079 0.119 0.244 0.155 [0.127, 0.183] <0.001 22% 0%
72 Anthropic Claude-2.1 (scratchpad with news with freeze values) 0.208 0.142 0.094 0.103 0.175 0.155 [0.135, 0.176] <0.001 25% 3%
73 Anthropic Claude-3-5-Sonnet-20240620 (superforecaster with news 2) 0.197 0.220 0.090 0.114 0.209 0.155 [0.13, 0.181] <0.001 26% 0%
74 Mistral AI Mixtral-8x22B-Instruct-V0.1 (scratchpad with news) 0.198 0.209 0.092 0.114 0.203 0.156 [0.134, 0.177] <0.001 23% 0%
75 Qwen Qwen1.5-110B-Chat (superforecaster with news 1) 0.193 0.303 0.077 0.118 0.248 0.156 [0.13, 0.181] <0.001 24% 0%
76 Google Gemini-1.5-Flash (zero shot) 0.177 0.228 0.115 0.136 0.203 0.157 [0.13, 0.184] <0.001 24% 0%
77 Meta Llama-3-8b-Chat-Hf (scratchpad with freeze values) 0.219 0.170 0.078 0.095 0.194 0.157 [0.139, 0.174] <0.001 24% 0%
78 OpenAI GPT-4-Turbo-2024-04-09 (superforecaster with news 1) 0.195 0.272 0.087 0.121 0.233 0.158 [0.134, 0.182] <0.001 23% 0%
79 Meta Llama-3-70b-Chat-Hf (scratchpad) 0.180 0.224 0.116 0.136 0.202 0.158 [0.14, 0.176] <0.001 21% 0%
80 OpenAI GPT-4o (superforecaster with news 1) 0.200 0.255 0.086 0.116 0.227 0.158 [0.129, 0.187] <0.001 26% 0%
81 Anthropic Claude-3-Opus-20240229 (superforecaster with news 3) 0.192 0.129 0.126 0.127 0.160 0.159 [0.136, 0.182] <0.001 20% 0%
82 Google Gemini-1.5-Pro (superforecaster with news 1) 0.200 0.267 0.086 0.119 0.233 0.159 [0.134, 0.185] <0.001 26% 0%
83 Qwen Qwen1.5-110B-Chat (scratchpad) 0.205 0.239 0.087 0.115 0.222 0.160 [0.14, 0.18] <0.001 22% 0%
84 Meta Llama-3-8b-Chat-Hf (zero shot) 0.199 0.329 0.075 0.121 0.264 0.160 [0.131, 0.189] <0.001 25% 0%
85 Mistral AI Mixtral-8x22B-Instruct-V0.1 (zero shot) 0.185 0.284 0.105 0.137 0.234 0.161 [0.133, 0.189] <0.001 22% 0%
86 Mistral AI Mistral-Large-Latest (scratchpad with news with freeze values) 0.206 0.200 0.097 0.116 0.203 0.161 [0.137, 0.185] <0.001 24% 0%
87 Anthropic Claude-3-Opus-20240229 (superforecaster with news 2) 0.182 0.243 0.119 0.141 0.212 0.161 [0.136, 0.187] <0.001 23% 0%
88 Google Gemini-1.5-Flash (scratchpad with news) 0.200 0.203 0.108 0.125 0.201 0.162 [0.137, 0.187] <0.001 24% 0%
89 Mistral AI Mixtral-8x22B-Instruct-V0.1 (superforecaster with news 3) 0.213 0.168 0.101 0.113 0.190 0.163 [0.144, 0.182] <0.001 20% 0%
90 Anthropic Claude-3-Opus-20240229 (scratchpad with news with freeze values) 0.204 0.212 0.103 0.123 0.208 0.164 [0.138, 0.189] <0.001 23% 0%
91 Anthropic Claude-3-Opus-20240229 (scratchpad with news) 0.204 0.201 0.106 0.123 0.203 0.164 [0.139, 0.188] <0.001 24% 0%
92 OpenAI GPT-4o (superforecaster with news 2) 0.221 0.202 0.086 0.107 0.212 0.164 [0.135, 0.193] <0.001 26% 0%
93 Mistral AI Mistral-Large-Latest (superforecaster with news 2) 0.182 0.235 0.130 0.149 0.208 0.165 [0.138, 0.192] <0.001 25% 0%
94 Mistral AI Mixtral-8x7B-Instruct-V0.1 (zero shot) 0.203 0.233 0.105 0.128 0.218 0.166 [0.132, 0.2] <0.001 25% 0%
95 Mistral AI Mistral-Large-Latest (scratchpad with news) 0.206 0.164 0.117 0.126 0.185 0.166 [0.143, 0.189] <0.001 23% 0%
96 Mistral AI Mixtral-8x22B-Instruct-V0.1 (superforecaster with news 1) 0.206 0.228 0.103 0.126 0.217 0.166 [0.14, 0.192] <0.001 22% 0%
97 Qwen Qwen1.5-110B-Chat (superforecaster with news 3) 0.218 0.207 0.101 0.121 0.212 0.169 [0.15, 0.189] <0.001 25% 0%
98 Mistral AI Mistral-Large-Latest (superforecaster with news 1) 0.198 0.297 0.106 0.141 0.248 0.170 [0.142, 0.198] <0.001 24% 0%
99 Mistral AI Mixtral-8x7B-Instruct-V0.1 (superforecaster with news 1) 0.236 0.207 0.080 0.103 0.222 0.170 [0.143, 0.196] <0.001 29% 15%
100 Anthropic Claude-2.1 (zero shot) 0.218 0.227 0.104 0.127 0.222 0.172 [0.152, 0.192] <0.001 19% 0%
101 Mistral AI Mixtral-8x7B-Instruct-V0.1 (scratchpad with freeze values) 0.194 0.171 0.147 0.151 0.183 0.173 [0.145, 0.2] <0.001 29% 11%
102 Mistral AI Mixtral-8x22B-Instruct-V0.1 (superforecaster with news 2) 0.226 0.188 0.110 0.124 0.207 0.175 [0.152, 0.198] <0.001 23% 0%
103 Anthropic Claude-2.1 (superforecaster with news 3) 0.216 0.146 0.132 0.135 0.181 0.175 [0.151, 0.199] <0.001 26% 1%
104 Mistral AI Mixtral-8x7B-Instruct-V0.1 (scratchpad with news with freeze values) 0.256 0.155 0.083 0.096 0.205 0.176 [0.15, 0.202] <0.001 29% 13%
105 Google Gemini-1.5-Flash (superforecaster with news 2) 0.203 0.247 0.128 0.150 0.225 0.176 [0.148, 0.204] <0.001 23% 0%
106 OpenAI GPT-4-Turbo-2024-04-09 (superforecaster with news 2) 0.217 0.186 0.126 0.137 0.201 0.177 [0.149, 0.205] <0.001 27% 0%
107 Meta Llama-3-8b-Chat-Hf (scratchpad) 0.219 0.229 0.114 0.135 0.224 0.177 [0.158, 0.196] <0.001 23% 0%
108 Mistral AI Mixtral-8x7B-Instruct-V0.1 (superforecaster with news 2) 0.242 0.185 0.098 0.114 0.213 0.178 [0.146, 0.21] <0.001 32% 21%
109 Google Gemini-1.5-Flash (superforecaster with news 1) 0.213 0.298 0.116 0.149 0.255 0.181 [0.149, 0.212] <0.001 25% 0%
110 Meta Llama-2-70b-Chat-Hf (scratchpad with freeze values) 0.223 0.212 0.125 0.141 0.218 0.182 [0.164, 0.2] <0.001 24% 0%
111 Mistral AI Mistral-Large-Latest (superforecaster with news 3) 0.234 0.191 0.116 0.129 0.213 0.182 [0.159, 0.205] <0.001 23% 0%
112 Qwen Qwen1.5-110B-Chat (superforecaster with news 2) 0.220 0.266 0.117 0.144 0.243 0.182 [0.158, 0.205] <0.001 23% 0%
113 Mistral AI Mixtral-8x7B-Instruct-V0.1 (superforecaster with news 3) 0.245 0.166 0.113 0.123 0.205 0.184 [0.161, 0.207] <0.001 27% 11%
114 Google Gemini-1.5-Flash (superforecaster with news 3) 0.229 0.196 0.126 0.139 0.213 0.184 [0.16, 0.208] <0.001 19% 0%
115 Anthropic Claude-2.1 (superforecaster with news 2) 0.227 0.201 0.129 0.142 0.214 0.184 [0.157, 0.211] <0.001 28% 11%
116 Anthropic Claude-3-Haiku-20240307 (zero shot with freeze values) 0.279 0.152 0.076 0.090 0.216 0.185 [0.161, 0.208] <0.001 26% 0%
117 Meta Llama-2-70b-Chat-Hf (zero shot with freeze values) 0.235 0.160 0.129 0.135 0.198 0.185 [0.157, 0.214] <0.001 24% 0%
118 Mistral AI Mixtral-8x7B-Instruct-V0.1 (scratchpad with news) 0.256 0.197 0.097 0.115 0.226 0.185 [0.158, 0.213] <0.001 29% 13%
119 Anthropic Claude-3-Haiku-20240307 (scratchpad with freeze values) 0.241 0.174 0.131 0.139 0.208 0.190 [0.17, 0.211] <0.001 19% 0%
120 Google Gemini-1.5-Pro (superforecaster with news 2) 0.233 0.280 0.119 0.148 0.256 0.190 [0.157, 0.224] <0.001 22% 0%
121 Meta Llama-2-70b-Chat-Hf (scratchpad) 0.223 0.248 0.149 0.167 0.235 0.195 [0.174, 0.216] <0.001 22% 0%
122 Anthropic Claude-3-Haiku-20240307 (scratchpad) 0.241 0.214 0.135 0.150 0.228 0.195 [0.174, 0.216] <0.001 20% 0%
123 Anthropic Claude-3-Haiku-20240307 (scratchpad with news with freeze values) 0.259 0.173 0.127 0.135 0.216 0.197 [0.176, 0.218] <0.001 23% 0%
124 OpenAI GPT-3.5-Turbo-0125 (scratchpad with freeze values) 0.243 0.274 0.124 0.151 0.258 0.197 [0.176, 0.219] <0.001 22% 0%
125 Anthropic Claude-3-Haiku-20240307 (superforecaster with news 2) 0.245 0.187 0.142 0.150 0.216 0.198 [0.175, 0.221] <0.001 22% 0%
126 Anthropic Claude-3-Haiku-20240307 (scratchpad with news) 0.259 0.202 0.127 0.141 0.231 0.200 [0.179, 0.221] <0.001 22% 0%
127 Anthropic Claude-3-Haiku-20240307 (zero shot) 0.279 0.174 0.116 0.127 0.227 0.203 [0.179, 0.227] <0.001 24% 0%
128 OpenAI GPT-3.5-Turbo-0125 (scratchpad) 0.243 0.274 0.140 0.165 0.259 0.204 [0.182, 0.226] <0.001 21% 0%
129 Anthropic Claude-2.1 (superforecaster with news 1) 0.265 0.258 0.124 0.148 0.262 0.207 [0.181, 0.232] <0.001 24% 3%
130 ForecastBench Always 0.5 0.250 0.250 0.146 0.165 0.250 0.208 [0.198, 0.218] <0.001 18% 0%
131 Meta Llama-2-70b-Chat-Hf (zero shot) 0.235 0.221 0.195 0.200 0.228 0.217 [0.188, 0.247] <0.001 23% 1%
132 Anthropic Claude-3-Haiku-20240307 (superforecaster with news 3) 0.275 0.224 0.168 0.178 0.249 0.227 [0.206, 0.248] <0.001 21% 0%
133 Anthropic Claude-3-Haiku-20240307 (superforecaster with news 1) 0.266 0.243 0.182 0.193 0.254 0.230 [0.201, 0.259] <0.001 22% 0%
134 OpenAI GPT-3.5-Turbo-0125 (zero shot with freeze values) 0.387 0.184 0.067 0.088 0.286 0.238 [0.203, 0.273] <0.001 36% 0%
135 OpenAI GPT-3.5-Turbo-0125 (zero shot) 0.387 0.218 0.163 0.173 0.302 0.280 [0.244, 0.316] <0.001 23% 0%
136 ForecastBench Random Uniform 0.357 0.318 0.207 0.227 0.337 0.292 [0.249, 0.335] <0.001 24% 0%
137 ForecastBench Always 0 0.365 0.500 0.187 0.244 0.433 0.304 [0.242, 0.367] <0.001 26% 0%
138 ForecastBench Always 1 0.635 0.500 0.606 0.587 0.567 0.611 [0.545, 0.676] <0.001 23% 0%