ZShot Gym

ZShot Gym Scoreboard

Testing platform for ZShot

Template Summary

Template Total Runs Pass Fail Pass Rate Avg Tokens In Avg Tokens Out Tokens In per Pass
benefits_hardship_claim 32 16 16 50.0% 898,848 19,789 1,235,917
doom_destroy_a_barrel 15 7 8 46.7% 208,211 5,319 446,166
parcel_redelivery 281 116 165 41.3% 181,211 15,199 412,846
recipe_site_favorite_a_recipe 16 8 8 50.0% 15,315 609 15,315

Token figures count runs recorded with --llm-usage. Tokens in per pass is every metered run's input over the metered runs that passed.

Recent Sessions

ID Template Label Result Furthest Tokens Est. Cost Took Created
250 doom_destroy_a_barrel haiku@doomrec pass — 208,747 in / 16,340 out $0.029 2m 16s 2026-10-12 12:21
249 doom_destroy_a_barrel haiku@doomrec pass — 119,787 in / 8,628 out $0.016 1m 22s 2026-10-12 12:21
248 doom_destroy_a_barrel haiku@doomrec pass — 104,561 in / 6,947 out $0.014 1m 7s 2026-10-12 12:21
247 doom_destroy_a_barrel clef@timed-1012 fail — 361,668 in / 0 out $0.087 2m 20s 2026-10-12 12:11
246 doom_destroy_a_barrel decisions-vision@timed-1012 fail — 32,154 in / 0 out $0.003 11s 2026-10-12 12:11
245 doom_destroy_a_barrel decisions-vision@timed-1012 fail — 334,410 in / 0 out $0.033 1m 5s 2026-10-12 12:11
244 doom_destroy_a_barrel clef@timed-1012 fail — 361,612 in / 0 out $0.087 2m 27s 2026-10-12 12:11
243 parcel_redelivery scout-clef@regress-1011 pass done 335,354 in / 3,963 out $0.350 2m 7s 2026-10-11 18:29
242 parcel_redelivery scout-decisions@regress-1011 fail confirm 709,826 in / 2,027 out $0.199 1m 52s 2026-10-11 18:29
241 parcel_redelivery scout-sonnet-opus@regress-1011 fail human 189,056 in / 9,129 out $0.200 56s 2026-10-11 18:29
240 parcel_redelivery scout-sonnet@regress-1011 fail preferences 737,057 in / 18,891 out $0.508 2m 3s 2026-10-11 18:25
239 parcel_redelivery gemini@regress-1011 fail human 30,782 in / 8,866 out $0.056 2m 18s 2026-10-11 18:25
238 parcel_redelivery deepseek@regress-1011 fail preferences 123,990 in / 33,166 out $0.070 4m 8s 2026-10-11 18:25
237 parcel_redelivery luna@regress-1011 fail done 104,710 in / 3,589 out $0.012 1m 25s 2026-10-11 18:25
236 parcel_redelivery gpt@regress-1011 pass done 520,743 in / 4,664 out $5.41 4m 47s 2026-10-11 18:20
235 parcel_redelivery sonnet@regress-1011 pass done 179,916 in / 5,634 out $0.386 1m 37s 2026-10-11 18:20
234 parcel_redelivery haiku@regress-1011 fail human 289,764 in / 28,773 out $0.041 3m 34s 2026-10-11 18:20
233 parcel_redelivery opus@regress-1011 pass done 174,059 in / 5,059 out $0.736 2m 38s 2026-10-11 18:20
232 parcel_redelivery scout-decisions@rel5-1011 pass done 192,949 in / 2,471 out $0.227 1m 5s 2026-10-11 12:27
231 parcel_redelivery scout-decisions@rel5-1011 pass done 300,562 in / 1,887 out $0.173 1m 7s 2026-10-11 12:26
230 parcel_redelivery scout-decisions@rel5-1011 fail done 94,405 in / 800 out $0.062 37s 2026-10-11 12:25
229 parcel_redelivery luna-openrouter@rel5-1010 pass done 256,487 in / 11,675 out $0.031 4m 0s 2026-10-11 02:07
228 parcel_redelivery scout-decision1@rel5-1010 fail done 86,997 in / 1,583 out $0.095 52s 2026-10-11 02:06
227 parcel_redelivery luna-openrouter@rel5-1010 fail done 80,342 in / 2,914 out $0.009 1m 28s 2026-10-11 02:05
226 parcel_redelivery scout-decision1@rel5-1010 fail confirm 280,791 in / 7,796 out $0.636 2m 24s 2026-10-11 02:03
225 parcel_redelivery scout-jev-1.13-openrouter@rel5-1010 pass done 246,675 in / 10,020 out $0.286 1m 30s 2026-10-11 01:44
224 parcel_redelivery scout-microsoft-decision-1-openrouter@rel5-1010 fail done 81,497 in / 1,294 out $0.086 43s 2026-10-11 01:44
223 parcel_redelivery scout-jev-1.13-openrouter@rel5-1010 pass done 239,810 in / 9,647 out $0.269 1m 24s 2026-10-11 01:42
222 parcel_redelivery scout-microsoft-decision-1-openrouter@rel5-1010 pass done 151,508 in / 3,745 out $0.271 1m 20s 2026-10-11 01:41
221 parcel_redelivery luna@rel5-1010 pass done 194,819 in / 5,217 out $0.021 2m 25s 2026-10-10 20:10
220 parcel_redelivery scout-clef@rel5-1010 pass done 397,084 in / 14,192 out $0.657 3m 27s 2026-10-10 20:06
219 parcel_redelivery scout-sonnet-opus@rel5-1010 pass done 221,811 in / 8,855 out $0.274 1m 13s 2026-10-10 20:05
218 parcel_redelivery haiku@rel5-1010 pass done 435,817 in / 28,254 out $0.058 3m 31s 2026-10-10 20:02
217 parcel_redelivery deepseek@rel5-1010 fail preferences 131,763 in / 38,726 out $0.078 4m 10s 2026-10-10 19:57
216 parcel_redelivery gpt@rel5-1010 pass done 298,469 in / 2,710 out $3.08 3m 10s 2026-10-10 19:54
215 parcel_redelivery opus@rel5-1010 pass done 101,085 in / 2,978 out $0.464 1m 17s 2026-10-10 19:53
214 parcel_redelivery sonnet@rel5-1010 pass done 147,774 in / 4,359 out $0.339 1m 18s 2026-10-10 19:52
213 parcel_redelivery luna@rel5-1010 fail done 138,757 in / 2,617 out $0.015 1m 35s 2026-10-10 19:50
212 parcel_redelivery scout-clef@rel5-1010 fail slot 680,932 in / 13,012 out $1.10 4m 52s 2026-10-10 19:45
211 parcel_redelivery scout-sonnet-opus@rel5-1010 pass done 176,649 in / 6,708 out $0.218 58s 2026-10-10 19:44
210 parcel_redelivery haiku@rel5-1010 pass done 107,090 in / 6,913 out $0.014 1m 8s 2026-10-10 19:43
209 parcel_redelivery deepseek@rel5-1010 fail preferences 72,692 in / 11,205 out $0.031 1m 51s 2026-10-10 19:41
208 parcel_redelivery gpt@rel5-1010 pass done 263,726 in / 2,028 out $2.71 2m 30s 2026-10-10 19:39
207 parcel_redelivery opus@rel5-1010 pass done 131,895 in / 3,310 out $0.594 1m 27s 2026-10-10 19:37
206 parcel_redelivery sonnet@rel5-1010 pass done 157,037 in / 4,630 out $0.360 1m 21s 2026-10-10 19:36
205 parcel_redelivery luna@rel-1010 fail done 222,609 in / 7,136 out $0.026 3m 11s 2026-10-10 19:19
204 parcel_redelivery scout-clef@rel-1010 fail human 108,753 in / 2,273 out $0.149 1m 5s 2026-10-10 19:18
203 parcel_redelivery scout-sonnet-opus@rel-1010 fail human 64,405 in / 4,139 out $0.092 34s 2026-10-10 19:18
202 parcel_redelivery haiku@rel-1010 fail human 31,279 in / 2,111 out $0.004 24s 2026-10-10 19:17
201 parcel_redelivery deepseek@rel-1010 fail human 42,722 in / 9,394 out $0.020 1m 40s 2026-10-10 19:15