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

Daily test results · Claude Code · effort default

Is Claude Haiku 5.5 getting worse?

Building baseline, day 3 of 14

No verdict yet: day 3 of a 14-day baseline.

Runs through
Claude Code
Effort
default
Provider
claude-cli
Model id
claude-haiku-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 Haiku 5.5 nerfed?

No verdict yet

This is day 3 of the 14-day baseline for Claude Haiku 5.5. The baseline began on 8 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
1657±197 · one standard error
Change since day 1
+19from 1638 on 8 October 2026
Pass rate, latest graded day
100%latest graded day · 3 graded tasks
Days of data
3since 8 October 2026

What the runs took

Median time per task
3m 32smean 4m 42s · 1 timeout
Output tokens per task
29k55% thinking · 1.92M in
Output tokens per second
120median · mean 121
Estimated cost per task
$0.041at API list prices · $0.230 a day

Estimated cost is tokens at API list prices, not money spent. A dash means no list price is set. Graded counts cover 18 tasks over 3 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 Haiku 5.5median 3m 32sslowest timed out · pull-request

By task family

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

Modelpull-request
Claude Haiku 5.594%4m 42s29k

Day by day

DayRatingPassedTimeoutsTime spentMedian timeOutput tokensOutput tokens / sEst. cost
17 Oct1657 ±1973/307m 15s2m 28s49k117$0.067
9 Oct1640 ±1993/308m 21s2m 14s65k137$0.083
8 Oct1638 ±13811/1211h 09m3m 58s384k120$0.540

How this is measured

Claude Haiku 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