step-5-preview-freeeffort: highStepFun · 8 Oct 2026
7.4 / 10Quality v1 · 2/2 pages
Time2h 08m
Output tokens252k
Cost—
Home › Videos › Step-5-Preview Tested: A Rocket Game With No Rocket
9 Oct 2026 · 2 runs · 2 models
Step-5-Preview Tested: A Rocket Game With No Rocket
StepFun's Step 5 Preview scored 6.5 through OpenRouter, from six of the eight core pages, and tied Claude Sonnet 5.5 on two tests. Its rocket game had no rocket. The two tests that failed scored 7.4 each when re-run through OpenCode Go.
The results
The same scores as the leaderboard: a test that failed is left out of its run's score, not counted as zero. Time, tokens and cost cover each whole run, wildcards included.
Ranking
Quality v1 over measured non-wildcard pages. Different workloads: browse the outputs and coverage before comparing models.
0510
Score against output tokens
Quality v1 against full-run tokens. Different workloads and hardware affect this comparison.
StepStepFun
Output tokens include the model's thinking. Like the time, tokens and cost table, it counts every test the model took, wildcards included. A hollow dot is not an exact count: some tests reported none, or the count was worked out from the length of the output. The score axis is zoomed to the data.
Score against time
Quality v1 against full-run time. Different workloads and hardware affect this comparison.
StepStepFun
Time is how long the model took to answer, added up over its tests; judging is not counted. Like the time, tokens and cost table, it counts every test the model took, wildcards included. The score axis is zoomed to the data.
Where each model is strong and weak
One row per model, one column per test and per scoring criterion.
| By test | By what the judges scored | ||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Model | Aero Lab | Jet Odyssey | Blast Island | Launch Day | Alex Optics | Afterburner | Hangar Planner | Rotor Rampage | Working behaviour | Visual quality | Engineering quality | Usability / accessibility | |
| step-5-preview-freeeffort: high | — | — | — | — | 7.4 | 7.4 | — | — | 7.8 | 7.8 | 7.3 | 6.3 | |
| stepfun/step-5-previeweffort: high | 5.8 | 7.2 | 6.4 | 4.7 | failed | failed | 7.2 | 7.7 | 7.3 | 6.3 | 6.6 | 5.5 | |
Violet is strong, orange is weak, on the same 0–10 scale in every cell.Different prompts and protocols: no best-in-column verdict.
Time, tokens and cost
What each model used across all its tests, wildcards included.
| Model | Tests | Time | Output tokens | Speed | Cost | Subscription used |
|---|---|---|---|---|---|---|
| step-5-preview-freeeffort: highStepFun | 2 | 2h 08m | 252k134k of it thinking | 32.8 tok/s | — | — |
| stepfun/step-5-previeweffort: highStepFun | 92 failed | 5h 16m | ≥1.07M | 77.4 tok/s | ≥≈$6.24API price, est. | — |
≈ An estimate: the provider reported no count, so it is worked out from the length of the output (about 4 characters a token).
— Not measured.
Cost says how it was worked out: charged by the provider, at API prices (for a subscription), or no API charge on local hardware. ≥ means some tests had no price.
Read from the account's usage window in whole percentage points, so a short run can show 0 points. It counts everything the account did in that time, not only this run.
Runs in this video
Every run behind the numbers. Scores name their comparison basis.
Model
Score / basis
Time
Output tokens
Cost
6.5 / 10Quality v1 · 6/8 pages
Time5h 16m
Output tokens≥1.07M
Cost≥≈$6.24API price, est.
step-5-preview-freeeffort: high
StepFun · 7.4 / 10 · Quality v1 · 2/2 pages · 2h 08m · —
7.4
Alex Optics
step-5-preview-free · effort: high
44m 11s · 110k tokens · —
Quality v1 · Working behaviour 7.5 · Visual quality 8.0 · Engineering quality 7.0 · Usability / accessibility 6.5scored by claude-code/claude-opus-5-5 (quality-1 rubric)prompt de7c304e41dd3505
Open the pageDetails
7.4
Afterburner
step-5-preview-free · effort: high
1h 24m · 142k tokens · —
Quality v1 · Working behaviour 8.0 · Visual quality 7.5 · Engineering quality 7.5 · Usability / accessibility 6.0scored by claude-code/claude-opus-5-5 (quality-1 rubric)prompt e08d0617005c33f9
Open the pageDetails
stepfun/step-5-previeweffort: high
StepFun · 6.5 / 10 · Quality v1 · 6/8 pages · 5h 16m · ≥≈$6.24 partial quality coverage
5.8
Aero Lab
stepfun/step-5-preview · effort: high
21m 50s · 212k tokens · ≈$1.10
Quality v1 · Working behaviour 7.5 · Visual quality 4.5 · Engineering quality 6.0 · Usability / accessibility 5.0scored by claude-code/claude-opus-5-5 (quality-1 rubric)prompt 1e8e809e8caeb2ba
Open the pageDetails
7.2
Jet Odyssey
stepfun/step-5-preview · effort: high
23m 44s · 174k tokens · ≈$1.42
Quality v1 · Working behaviour 8.0 · Visual quality 7.0 · Engineering quality 7.0 · Usability / accessibility 6.5scored by claude-code/claude-opus-5-5 (quality-1 rubric)prompt 1ce617b6d67089b2
Open the pageDetails
6.4
Blast Island
stepfun/step-5-preview · effort: high
28m 06s · 139k tokens · ≈$0.88
Quality v1 · Working behaviour 7.0 · Visual quality 7.0 · Engineering quality 6.0 · Usability / accessibility 5.0scored by claude-code/claude-opus-5-5 (quality-1 rubric)prompt 28ba22cd0f56ca1e
Open the pageDetails
4.7
Launch Day
stepfun/step-5-preview · effort: high
41m 18s · 258k tokens · ≈$1.49
Quality v1 · Working behaviour 5.0 · Visual quality 3.5 · Engineering quality 6.0 · Usability / accessibility 4.5scored by claude-code/claude-opus-5-5 (quality-1 rubric)prompt d1e76d48a7ac8eb6
Open the pageDetails
Alex Optics
stepfun/step-5-preview · effort: high
1h 00m · — tokens · —
Legacy rubric · Functional 0.0 · Visual 0.0 · Code 0.0 · UX 0.0 · Innovation 0.0prompt de7c304e41dd3505
Details
Afterburner
stepfun/step-5-preview · effort: high
24m 56s · — tokens · —
Legacy rubric · Functional 0.0 · Visual 0.0 · Code 0.0 · UX 0.0 · Innovation 0.0prompt e08d0617005c33f9
Details
7.2
Hangar Planner
stepfun/step-5-preview · effort: high
6m 24s · 41k tokens · ≈$0.18
Quality v1 · Working behaviour 7.5 · Visual quality 7.5 · Engineering quality 7.5 · Usability / accessibility 6.0Fixed 14 of 16 bugs · 14 of 14 features still work · 197 lines changedscored by claude-code/claude-opus-5-5 (quality-1 rubric)prompt 14deca81c8b3a6c9
Open the pageDetails
7.7
Rotor Rampage
stepfun/step-5-preview · effort: high
1h 12m · 213k tokens · ≈$0.98
Quality v1 · Working behaviour 8.5 · Visual quality 8.5 · Engineering quality 7.0 · Usability / accessibility 6.0scored by claude-code/claude-opus-5-5 (quality-1 rubric)prompt d196c18e5127f818
Open the pageDetails
6.4
Cursive Ink Grand Prixwildcard
stepfun/step-5-preview · effort: high
36m 14s · 33k tokens · ≈$0.19
Quality v1 · Working behaviour 7.0 · Visual quality 7.0 · Engineering quality 6.0 · Usability / accessibility 5.0scored by claude-code/claude-opus-5-5 (quality-1 rubric)prompt e1846c1d94dd5759
Open the pageDetails