RankingStep 5 Preview
Step 5 Preview
Step 5 Preview by StepFun is a Step model. This profile collects the published benchmark results and reported effort settings for this model. Configurations are compared on the effort page. Ranks are on the leaderboard.
6 published benchmark measures · 20 measured effort results · 2 benchmark families contribute across 2 task areas. 1 capability estimates available in the full profile. See all results ↓ · Compare published benchmarks →
Model evidence summary
This profile combines published settings. It is not a runnable configuration or a leaderboard rank. Compare measured configurations →
Performance profile
Capabilities
Filled points are supported; hollow points are preliminary. Lines stop at unknown capabilities. Exact values and sources follow below.
Scores estimate outcomes against a shared reference panel; they are not accuracy percentages. Sparse or disconnected evidence cannot qualify an overall profile. Open a capability to inspect its evidence.
Reported effort · Not specified
Settings reported in this model's published benchmark results, including results outside the aggregate. Effort names are provider-specific. These are not API defaults or equal compute budgets.
- Not specified: 6 observations
Mixed settings means multiple settings occur in the evidence. Best across efforts means the source selected its best reported result across settings; it does not mean Max. Unspecified settings stay unknown. This model-summary chart combines reported settings. The leaderboard keeps identified configurations separate and excludes unknown effort.
Inspect each result and its source ↓ · Download effort evidenceScore contributions and missing evidence
2 contributing families across 2 capabilities. Fixed reference panels do not change when the catalog expands.
Capability is fitted jointly across families. Capability estimates below describe different task areas; their weighted sum is not the Capability score.
Results without reviewed compatibility or a reference match remain in the raw evidence below. Coverage counts only contributing results.
Model information & shareable badge
- Lab
- StepFun
- Catalog status
- api-listed
- Availability
- Publicly documented StepFun API model; create an API key to access. Account restrictions may apply.
- Family
- Step
- Released
- —
- Context
- 1,000,000 tokens
- License
- proprietary
- Model card
- https://platform.stepfun.com/docs/zh/guides/models/step-5-preview
- Default Capability family coverage
/badge/step-5-preview.svg
Step 5 Preview measured results by effort setting
Each row is one published result for one effort setting. Evidence collected 2026-11-22. Compare the effort settings →
| Benchmark | Effort | Score | Source |
|---|---|---|---|
| AA-AnalystAgent | Reasoning | 35.0% | Artificial Analysis |
| AA-Briefcase Elo | Reasoning | 1424 | Artificial Analysis |
| AA-LCR v1.1 | Reasoning | 88.3% | Artificial Analysis |
| AA-Omniscience Accuracy | Reasoning | 36.4% | Artificial Analysis |
| AA-Omniscience Index | Reasoning | 16.4 | Artificial Analysis |
| APEX-Agents-AA | Reasoning | 38.0% | Artificial Analysis |
| Artificial Analysis Cyber Index | Unspecified | 47.7 | Artificial Analysis |
| AutomationBench-AA | Reasoning | 51.0% | Artificial Analysis |
| CritPt | Reasoning | 20.9% | Artificial Analysis |
| EnterpriseOps-Gym-AA | Reasoning | 47.2% | Artificial Analysis |
| FrontierCS 2 | Unspecified | 8.3% | FrontierCS |
| GDP.pdf: All-pass Rate | Reasoning | 14.8% | Artificial Analysis |
| GDPval-AA v2.1 Leaderboard | Reasoning | 1591 | Artificial Analysis |
| Humanity's Last Exam | Reasoning | 46.5% | Artificial Analysis |
| ITBench-AA | Reasoning | 55.6% | Artificial Analysis |
| MLCR-AA | Reasoning | 18.3% | Artificial Analysis |
| MMMU-Pro | Reasoning | 76.4% | Artificial Analysis |
| SciCode | Reasoning | 58.9% | Artificial Analysis |
| Terminal-Bench v4.0 | Reasoning | 33.3% | Artificial Analysis |
| Terminal-Bench-Science 0.1 | Reasoning | 2.4% | Artificial Analysis |
Benchmark scores & sources
Original results, evaluation harnesses, and evidence behind this model.
| Benchmark | Bucket | Score | Harness | Evidence | Source-recorded date |
|---|---|---|---|---|---|
| Artificial Analysis Cyber Index | Supporting evidence | 47.7068149907409 | Artificial Analysis Stirrup · Cyber Index v1.0 · unspecifiedCyber Index source settingsArtificial Analysis Stirrup, v1.0. Display only. This composite measures defensive source-code tasks. Successful capability scores depend on safety refusals, and refusal rates are reported separately. It does not enter weighted Overall. Official Cyber Index board | official board | 2026-11-18 |
| AutomationBench-AA | Supporting evidence | 50.956594190962875% | Artificial Analysis AutomationBench-AA | official board | 2026-11-21 |
| FrontierCS 2 | Supporting evidence | 10.4% | Step Code | official board | 2026-11-20 |
| GDPval-AA | Agentic | 1591 | Artificial Analysis GDPval-AAcontributes to capability | official board | 2026-11-22 |
| LMArena Agent Arena | Supporting evidence | -5.15 | LMArena Agent Arena · unspecified | official board | 2026-11-18 |
| LMArena Text Arena | Human pref | 1449 | LMArena Textcontributes to capability | official board | 2026-11-19 |
| ARC-AGI-2 | Hard reasoning | — | — | — | — |
| DeepSWE v1.1 | Agentic | — | — | — | — |
| GPQA Diamond | Hard reasoning | — | — | — | — |
| Humanity's Last Exam | Hard reasoning | — | — | — | — |
| LiveCodeBench | Coding | — | — | — | — |
| MMLU-Pro | Knowledge | — | — | — | — |
| OSWorld-Verified | Agentic | — | — | — | — |
| SWE-bench Pro | Agentic | — | — | — | — |
| SWE-bench Verified | Agentic | — | — | — | — |
| Terminal-Bench 2.1 | Agentic | — | — | — | — |