Skip to content
Bencher

Models · StepFun

Step 5 Preview#8 for research and analysis.#8 for research and analysis, best at its default setting.

Only from the makerNot on OpenRouterEarly accessPreviewClosed (can't be downloaded)Proprietary

Step 5 Preview is made by StepFun. Among the models we track it ranks #8 for research and analysis.

Seen on Artificial Analysis; not on OpenRouter as of 2026-10-01.

Writing & creativity
—
Research & analysis
76.0 / 100 · #8
Coding
—
Price
Price unknown— / —
Price per 1M (blended)Blended / 1M
—
MemoryContext
—
Longest answerMax output
—
Test resultsResults
13 (13 independent13 indep.)
Out sinceReleased
—
Made byVendor
StepFun
UnderstandsInputs
—

Scores are out of 100 for each area, compared with every model we track; “#” is its rank. Context is how much text it can read at once (1M is roughly 700,000 words). Blended price mixes the cost of what you send and what it writes back.

Thinking levels

Reasoning settings

You can't choose how long this one thinks.

No adjustable reasoning setting listed.

Read more

Links

—

Every test result

Every result

All the numbers,with where they came from.

Every result we've found for this model, with who measured it and a link to where we read it.

All raw rows (vendor and independent kept separate), with setting label, source, date, harness and notes.

All results for this model
NotesNotes
AA Analyst Agent35.0%DefaultStep 5 PreviewIndependent testIndependentArtificial Analysis ↗1 Oct 2026—AA-run; scores move in 1.25-pt steps (small task set)
AA-Briefcase v1.11432DefaultStep 5 PreviewIndependent testIndependentArtificial Analysis ↗1 Oct 2026—
AA-LCR88.3%DefaultStep 5 PreviewIndependent testIndependentArtificial Analysis ↗1 Oct 2026—AA-LCR accuracy, AA-run (long multi-document reasoning)
AA-Omniscience Accuracy41.5%DefaultStep 5 PreviewIndependent testIndependentArtificial Analysis ↗1 Oct 2026—
AA-Omniscience Hallucination Rate43.0%DefaultStep 5 PreviewIndependent testIndependentArtificial Analysis ↗1 Oct 2026—share of non-correct answers that were wrong instead of abstaining; = 1 - AA 'omniscienceNonHallucination' field (equals breakdown.hallucinationRate on the eval page)
AA-Omniscience Index16.4DefaultStep 5 PreviewIndependent testIndependentArtificial Analysis ↗1 Oct 2026—AA-Omniscience Index (-100..100): correct minus incorrect, abstentions not penalised
Artificial Analysis Intelligence Index43.7DefaultStep 5 PreviewIndependent testIndependentArtificial Analysis ↗1 Oct 2026—AA slug step-5; list price $1/2.7 per 1M in/out; cost to run AA Intelligence Index $0.72/task
Artificial Analysis output speed85 tok/sDefaultStep 5 PreviewIndependent testIndependentArtificial Analysis ↗1 Oct 2026—tokens/sec (median output speed, first-party API); TTFT 3.2s; list price $1/2.7 per 1M in/out
GDPval-AA v2.11566DefaultStep 5 PreviewIndependent testIndependentArtificial Analysis ↗1 Oct 2026—95% CI 1534.76-1597.48
Harvey LAB-AA93.4%DefaultStep 5 PreviewIndependent testIndependentArtificial Analysis ↗1 Oct 2026—criteria pass rate, AA-run
Humanity's Last Exam46.5%DefaultStep 5 PreviewIndependent testIndependentArtificial Analysis ↗1 Oct 2026—AA-run evaluation (AA slug step-5)
SciCode58.9%DefaultStep 5 PreviewIndependent testIndependentArtificial Analysis ↗1 Oct 2026—AA-run evaluation (AA slug step-5)
Terminal-Bench 4.033.3%DefaultStep 5 PreviewIndependent testIndependentArtificial Analysis ↗1 Oct 2026—AA-run evaluation (AA slug step-5)