StormEval
  1. StormEval
  2. Models
  3. Claude Sonnet 5.5

Daily test results · Claude Code · effort high

Is Claude Sonnet 5.5 getting worse?

Building baseline, day 7 of 14

No verdict yet: day 7 of a 14-day baseline.

Runs through
Claude Code
Effort
high
Provider
claude-cli
Model id
claude-sonnet-5-5
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 Claude Sonnet 5.5 nerfed?

No verdict yet

This is day 7 of the 14-day baseline for Claude Sonnet 5.5. The baseline began on 4 October 2026. If the model runs every day, the baseline is complete on 28 October 2026 and the first verdict is expected on 29 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
1529±163 · one standard error
Change since day 1
+115from 1414 on 4 October 2026
Pass rate, latest graded day
67%latest graded day · 3 graded tasks
Days of data
7since 4 October 2026

What the runs took

Median time per task
1m 41smean 2m 54s · 1 timeout
Output tokens per task
9.2k27% thinking · 652k in
Output tokens per second
68median · mean 73
Estimated cost per task
$0.298at API list prices · $0.980 a day

Estimated cost is tokens at API list prices, not money spent. A dash means no list price is set. Graded counts cover 24 tasks over 7 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.

  • Claude Sonnet 5.5median 1m 41sslowest timed out · pull-request

By task family

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

Modelpull-request
Claude Sonnet 5.583%2m 54s9.2k

Day by day

DayRatingPassedTimeoutsTime spentMedian timeOutput tokensOutput tokens / sEst. cost
21 Oct1529 ±1632/309m 25s3m 25s44k86$1.57
17 Oct1657 ±1973/304m 39s1m 17s15k61$0.458
15 Oct1640 ±1993/303m 26s1m 26s21k94$0.512
9 Oct1640 ±1993/306m 11s1m 28s20k55$0.587
8 Oct1611 ±2033/305m 36s1m 41s21k68$0.628
7 Oct1464 ±1672/306m 46s1m 42s26k69$0.777
4 Oct1414 ±1394/6133m 41s3m 34s63k57$2.33

How this is measured

Claude Sonnet 5.5 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