StormEval
  1. StormEval
  2. Models
  3. DeepSeek V4.1 Flash

Daily test results · DeepSeek Harness · effort default

Is DeepSeek V4.1 Flash getting worse?

Building baseline, day 2 of 14

No verdict yet: day 2 of a 14-day baseline.

Runs through
DeepSeek Harness
Effort
default
Provider
dsh-cli
Model id
deepseek-flash
Tasks
New issues in real code
Updated
2026-10-21 04:41 UTC

Rating over time

Higher is better. The band is one standard error either side. The dashed line is the first day. Movement inside the band means nothing.

Was DeepSeek V4.1 Flash nerfed?

No verdict yet

This is day 2 of the 14-day baseline for DeepSeek V4.1 Flash. The baseline began on 5 October 2026. If the model runs every day, the baseline is complete on 19 October 2026 and the first verdict is expected on 20 October 2026.

It is too early to say either way. Until the baseline is complete there is nothing to compare a new day with, and a single day moves by chance.

Rating
1649±200 · one standard error
Change since day 1
−48from 1697 on 5 October 2026
Pass rate, latest graded day
100%latest graded day · 3 graded tasks
Days of data
2since 5 October 2026

What the runs took

Median time per task
5m 23smean 5m 26s · 0 timeouts
Output tokens per task
39k– thinking · 4.68M in
Output tokens per second
116median · mean 118
Estimated cost per task
$0.049at API list prices · $0.222 a day

Estimated cost is tokens at API list prices, not money spent. A dash means no list price is set. Graded counts cover 9 tasks over 2 days; time, tokens and cost can also include finished runs excluded from grading.

Time per task

How long each task took. A task not finished in 15 minutes is a fail, and counts as 15 minutes of time spent.

  • DeepSeek V4.1 Flashmedian 5m 23sslowest 8m 46s · pull-request

By task family

Pass rate, mean time and mean output tokens for each kind of problem.

Modelpull-request
DeepSeek V4.1 Flash100%5m 26s39k

Day by day

DayRatingPassedTimeoutsTime spentMedian timeOutput tokensOutput tokens / sEst. cost
7 Oct1649 ±2003/3012m 07s3m 38s98k145$0.121
5 Oct1697 ±1936/6036m 47s5m 41s253k116$0.322

How this is measured

DeepSeek V4.1 Flash gets the same new tasks as every other model. Each task is an issue in a large, working codebase, and the model writes the change that resolves it with its own coding tool, as it would for a pull request. A program runs the tests to check the change. Only one run per task counts toward this model's results.

The model is compared with itself: the last 7 days against its first 14 days. A verdict is only given when the difference is too large to be chance. A task not finished in 15 minutes counts as a fail.

Read the full method

Not a leaderboard. Models run at different effort settings and through different tools.

Other models