01HTML
MODEL ARCHIVE · M01 · DeepSeek
● 20 archived worksDeepSeek-V4.1-Flash (0910 preview + GA release)
Per the organizer decision of 2026-09-10, the 0910 experimental preview and the subsequent GA release of DeepSeek-V4.1-Flash are treated as **one model**, with results reported in the same table. Every run records its harness-reported model id (its snapshot), and cross-snapshot comparisons must be labelled. The entity id and all run URLs stay stable and are not renamed.
Version basis: Version is recorded per run as a snapshot; no single version number is claimed, to avoid merging two snapshots into an unverified value.SELECTED WORKS
View all tasks →Selected works
Works first, numbers second.
ARCHIVE STATISTICS
Archive statistics
Runs20
Total duration5:24:18
API calls1,620
Tool calls1,675
Failures / retries42
Total tokens64.4M
Batch
Source report ↗DeepSeek V4.1 Flash Exp 0910 · Phase 1
Tasks15
Sessions12
Total duration2:18:02
API calls693
Tool calls735
Failures / retries42
Input tokens334,670
Output tokens1,072,534
Cache read63,042,176
Cost¥9.3
Batch
Source report ↗DeepSeek V4.1 Flash Exp 0910 · Phase 2 (Task 16–20, partial)
本批次为部分汇总：由已归档的 5 个 run 的逐题指标求和，不代表整个 phase-02（Task 16–45）；任一题缺失的指标记 null，不按 0 补齐。
Tasks5
Sessions5
Total duration3:06:16
API calls927
Tool calls940
Failures / retries0
Input tokens457,656
Output tokens1,475,485
Cache read234,301,952
CostNot recorded
PHASE PROGRESS
Phase progress
0102
PHASE-01
Phase 1 · 15 benchmark tasks
SVG illustration, single-file interactive apps, and multi-file web applications.
15 / 15 Tasks · Completed
15 RunsPHASE-02
Phase 2 · advanced creation tasks (Tasks 16–45)
In-browser animation, simulation, engineering and authoring tools. This archive currently covers only the tested and archived Tasks 16–20 (5 tasks × 2 models = 10 runs); the remaining tasks have not been run.
5 / 30 Tasks · In progress
5 RunsSNAPSHOTS
Model snapshots (harness-reported model id)
The model snapshot this run actually used; different snapshots of one model are not the same configuration.
Retired0910 experimental preview (retiring)
deepseek-v4.1-flash-expires-on-0910Harness-reported value, recorded in each Phase 2 submission.json; the Phase 1 archive does not record a model id.CurrentGA release (not yet run)
Not recordedThe GA harness-reported model id will be filled in after the first GA run; not inferred from the brand name.CRITICAL NOTES
Phase assessment
93.6/100
15/15
Quoted from the historical AI assessment; not independently proven or recomputed by this website.Source report ↗
Only one AI phase assessment (93.6/100) 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
16SVG
17SVG
18HTML
19HTML
20HTML
RUN HISTORY
Run history
One row per archived run; open a row for the full record.
ProviderDeepSeek
Works20
AI average93.6/100（1）
Archive commit
5776d3a1d94d…