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
doom_destroy_a_barrel 8 4 4 50.0% 200,028 5,984 400,056
parcel_redelivery 218 80 138 36.7% 169,996 16,895 451,889

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
29 parcel_redelivery qwen-noreasoning fail preferences 362,284 in / 3,285 out $0.000 8m 44s 2026-09-28 03:16
28 parcel_redelivery scout-gemini fail done 85,205 in / 56,580 out $0.249 4m 30s 2026-09-28 03:16
27 parcel_redelivery deepseek-low fail preferences 242,838 in / 89,943 out $0.162 9m 13s 2026-09-28 03:14
26 parcel_redelivery scout-gpt fail done 53,959 in / 2,725 out $0.033 30s 2026-09-28 03:13
25 parcel_redelivery scout-deepseek fail done 105,988 in / 4,647 out $0.044 43s 2026-09-28 03:13
24 parcel_redelivery scout-gpt fail done 53,959 in / 2,707 out $0.032 29s 2026-09-28 03:13
23 parcel_redelivery scout-deepseek fail done 52,528 in / 3,052 out $0.022 29s 2026-09-28 03:13
22 parcel_redelivery sonnet fail preferences 521,147 in / 33,588 out $1.38 8m 48s 2026-09-28 03:12
21 parcel_redelivery gemini fail preferences 62,678 in / 54,076 out $0.250 4m 26s 2026-09-28 03:12
20 parcel_redelivery gpt pass done 108,979 in / 844 out $1.07 1m 30s 2026-09-28 03:11
19 parcel_redelivery deepseek-noreasoning fail preferences 109,336 in / 3,268 out $0.026 1m 42s 2026-09-28 03:11
18 parcel_redelivery opus fail confirm 148,744 in / 3,077 out $0.657 2m 10s 2026-09-28 03:10
17 parcel_redelivery scout-local fail lookup 8,066 in / 747 out $0.003 8s 2026-09-28 03:07
16 parcel_redelivery scout-local fail lookup 5,479 in / 528 out $0.002 6s 2026-09-28 03:07
15 parcel_redelivery local fail consent 0 in / 0 out $0.000 2s 2026-09-28 03:07
14 parcel_redelivery opus pass done 156,820 in / 3,417 out $0.696 2m 16s 2026-09-28 03:07
13 parcel_redelivery deepseek-noreasoning fail done 366,601 in / 6,776 out $0.072 3m 33s 2026-09-28 03:07
12 parcel_redelivery gpt pass done 309,250 in / 2,660 out $3.23 4m 1s 2026-09-28 03:07
11 parcel_redelivery qwen-noreasoning fail preferences 363,407 in / 4,373 out $0.000 8m 58s 2026-09-28 03:07
10 parcel_redelivery gemini fail preferences 46,875 in / 47,233 out $0.212 4m 17s 2026-09-28 03:07
9 parcel_redelivery local fail consent 0 in / 0 out $0.000 3s 2026-09-28 03:07
8 parcel_redelivery deepseek-noreasoning active — — — — 2026-09-28 03:05
7 parcel_redelivery deepseek-noreasoning fail done 104,133 in / 3,439 out $0.024 1m 33s 2026-09-28 03:03
6 parcel_redelivery deepseek-noreasoning fail done 153,518 in / 3,644 out $0.038 2m 2s 2026-09-28 03:01
5 parcel_redelivery scout+writer-turns-v3-no-captcha fail confirm 279,904 in / 35,978 out $1.19 9m 20s 2026-09-27 17:35
4 parcel_redelivery scout+writer-turns-v2-no-captcha fail confirm 197,821 in / 13,116 out $0.598 2m 51s 2026-09-27 16:25
3 parcel_redelivery scout+writer-turns-no-captcha fail confirm 252,803 in / 32,430 out $1.10 8m 13s 2026-09-27 16:03
2 parcel_redelivery scout+writer-turns fail human 465,984 in / 11,258 out $0.413 2m 10s 2026-09-27 16:00
1 parcel_redelivery scout+writer fail human 56,197 in / 3,067 out $0.037 29s 2026-09-27 15:28