01HTML
MODEL ARCHIVE · M03 · OpenAI
● 15 archived worksGPT-5.6 Sol
The 15 phase-1 tasks were run by Codex CLI 0.147.0 at medium effort, one independent session per task. Tool-call telemetry is complete, so the runs went through the normal dimension-by-dimension audit (not the no-telemetry default).
Version basis: Version is recorded per run as a snapshot (`environment.reportedModelId`); no single version number is claimed.SELECTED WORKS
View all tasks →Selected works
Works first, numbers second.
ARCHIVE STATISTICS
Archive statistics
Runs15
Total duration1:16:46
API calls120
Tool calls76
Failures / retries1
Total tokens4.3M
Batch
Source report ↗GPT-5.6 Sol · Phase 1
由 15 个 run 的逐题指标求和；每题一个独立会话；任一题缺失的指标记 null，不按 0 补齐。
Tasks15
Sessions15
Total duration1:16:46
API calls120
Tool calls76
Failures / retries1
Input tokens4,187,022
Output tokens129,130
Cache read3,650,560
CostNot recorded
PHASE PROGRESS
Phase progress
SNAPSHOTS
Model snapshots (harness-reported model id)
The model snapshot this run actually used; different snapshots of one model are not the same configuration.
Currentmedium effort (Codex CLI 0.147.0)
gpt-5.6-solModel id reported by the harness (Codex `turn_context`) and recorded in each phase-01 submission.json; the provider-side snapshot is not independently confirmed.CRITICAL NOTES
Phase assessment
82.9/100
AI 评价，非盲评（评价者已读题目文档、本阶段归档与各模型同题档案）
Maintenance agent v3 — non-blind, own five-dimension rubric; not comparable to other reviewers, models or phases, and never combined into a ranking.Source report ↗
Only one AI phase assessment (82.9/100) is archived for this model, so no average is computed; rubrics differ and are not compared across models.
ALL WORKS
All works
01HTML
02SVG
03SVG
04SVG
05SVG
06SVG
07SVG
08HTML
09HTML
10HTML
11HTML
12HTML
13HTML
14HTML
15HTML
RUN HISTORY
Run history
One row per archived run; open a row for the full record.
| RUN ID | Tasks | Runtime | API calls | Tool calls | Token throughput | |
|---|---|---|---|---|---|---|
| 01.C.01 | Aevum Luxury Watch Landing Page | 6:06 | 4 | 3 | 134.5K | View archive record → |
| 02.C.01 | Pelican Riding a Bicycle | 2:06 | 3 | 2 | 87.6K | View archive record → |
| 03.C.01 | Analog Clock at 6:25 | 2:15 | 8 | 6 | 198.6K | View archive record → |
| 04.C.01 | Analog Clock at 11:52:30 | 2:02 | 3 | 2 | 86K | View archive record → |
| 05.C.01 | Side-View Bicycle Rider | 2:19 | 4 | 3 | 113.2K | View archive record → |
| 06.C.01 | Hand Cutting Paper with Scissors | 2:22 | 4 | 3 | 114.8K | View archive record → |
| 07.C.01 | Person Pushing a Wheelbarrow | 3:09 | 12 | 11 | 363.4K | View archive record → |
| 08.C.01 | Single-File Breakout Game | 7:03 | 13 | 6 | 546.2K | View archive record → |
| 09.C.01 | Single-File Top-Down Farming Game | 5:10 | 4 | 3 | 129.9K | View archive record → |
| 10.C.01 | Pixel-Art Editor | 6:14 | 7 | 6 | 220.6K | View archive record → |
| 11.C.01 | 2D Floor-Plan Editor | 9:04 | 22 | 7 | 1M | View archive record → |
| 12.C.01 | Calculator App | 6:04 | 16 | 8 | 609.3K | View archive record → |
| 13.C.01 | Weather Dashboard | 6:29 | 6 | 5 | 190.4K | View archive record → |
| 14.C.01 | Bank Website | 9:31 | 6 | 5 | 216.3K | View archive record → |
| 15.C.01 | Book-Tracking App | 6:52 | 8 | 6 | 273.7K | View archive record → |
ProviderOpenAI
Works15
AI average82.9/100（1）
Archive commit
92815760057a…