RankingStep 5 Preview

Step 5 Preview

Compare models

Data updated 22 Nov 2026

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

Adjusted comparison score · 0–100
Step 5 Preview capability radarComparison scores from 0 to 100. Unknown capabilities have no point; lines stop at gaps. Hollow points are preliminary. Exact values and support labels follow the chart.AgenticHard reasoningCodingHuman prefKnowledgeMultimodalLong context50100Step 5 Preview · Agentic: 34.8 · Preliminary

Filled points are supported; hollow points are preliminary. Lines stop at unknown capabilities. Exact values and sources follow below.

Agentic1 families · 1 with independent evidence · Preliminary34.8

1 core families; 42 direct opponents across 17 labs. Needs broader benchmark and opponent support

Estimated against the same complete panel: gpt-5.6-sol claude-opus-4-8 gemini-3.1-pro . Indirect comparisons assume performance can be summarized by one strength within this capability.

Refit without one family: No supported estimate; 13/13 scenarios unsupported. Without one publisher: No supported estimate; 15/15 unsupported. Smoothing check: No supported estimate; 3/3 unsupported. These are sensitivity checks, not confidence intervals.

Audit: family and publisher holdouts improved on neutral predictions within evaluated coverage; source sensitivity still requires inspection. Validation audit.

Matched family win shares below describe source evidence; they are not averaged to produce the adjusted score.

  • GDPval: 81.0 observed win share
    artificialanalysis.ai · Source 1
Hard reasoningNo comparable evidenceUnknown

0 core families; 0 direct opponents across 0 labs. No admitted core comparisons

Estimated against the same complete panel: gpt-5.6-sol claude-opus-4-8 gemini-3.1-pro . Indirect comparisons assume performance can be summarized by one strength within this capability.

Refit without one family: No supported estimate; 6/6 scenarios unsupported. Without one publisher: No supported estimate; 16/16 unsupported. Smoothing check: No supported estimate; 3/3 unsupported. These are sensitivity checks, not confidence intervals.

Audit: family and publisher holdouts improved on neutral predictions within evaluated coverage. Validation audit.

Matched family win shares below describe source evidence; they are not averaged to produce the adjusted score.

    CodingNo comparable evidenceUnknown

    0 core families; 0 direct opponents across 0 labs. No admitted core comparisons

    Estimated against the same complete panel: gpt-5.6-sol claude-opus-4-8 gemini-3.1-pro . Indirect comparisons assume performance can be summarized by one strength within this capability.

    Refit without one family: No supported estimate; 6/6 scenarios unsupported. Without one publisher: No supported estimate; 19/19 unsupported. Smoothing check: No supported estimate; 3/3 unsupported. These are sensitivity checks, not confidence intervals.

    Audit: family and publisher holdouts improved on neutral predictions within evaluated coverage. Validation audit.

    Matched family win shares below describe source evidence; they are not averaged to produce the adjusted score.

      Human pref1 families · 1 with independent evidence · PreliminaryUnknown

      1 core families; 75 direct opponents across 17 labs. No connected comparison to the complete reference panel

      Estimated against the same complete panel: gpt-5.6-sol claude-opus-4-8 gemini-3.1-pro . Indirect comparisons assume performance can be summarized by one strength within this capability.

      Refit without one family: No supported estimate; 1/1 scenarios unsupported. Without one publisher: No supported estimate; 1/1 unsupported. Smoothing check: No supported estimate; 3/3 unsupported. These are sensitivity checks, not confidence intervals.

      Audit: cross-family and cross-publisher predictions could not be evaluated from the available comparison network. Validation audit.

      Matched family win shares below describe source evidence; they are not averaged to produce the adjusted score.

      • Human preference (Arena): 72.0 observed win share
        lmarena.ai · Source 1
      KnowledgeNo comparable evidenceUnknown

      0 core families; 0 direct opponents across 0 labs. No admitted core comparisons

      Estimated against the same complete panel: gpt-5.6-sol claude-opus-4-8 gemini-3.1-pro . Indirect comparisons assume performance can be summarized by one strength within this capability.

      Refit without one family: No supported estimate; 4/4 scenarios unsupported. Without one publisher: No supported estimate; 5/5 unsupported. Smoothing check: No supported estimate; 3/3 unsupported. These are sensitivity checks, not confidence intervals.

      Audit: almost no publisher-held-out comparisons remained estimable. Cross-source validity is unresolved. Validation audit.

      Matched family win shares below describe source evidence; they are not averaged to produce the adjusted score.

        MultimodalNo comparable evidenceUnknown

        0 core families; 0 direct opponents across 0 labs. No admitted core comparisons

        Estimated against the same complete panel: gpt-5.6-sol claude-opus-4-8 gemini-3.1-pro . Indirect comparisons assume performance can be summarized by one strength within this capability.

        Refit without one family: No supported estimate; 8/8 scenarios unsupported. Without one publisher: No supported estimate; 8/8 unsupported. Smoothing check: No supported estimate; 3/3 unsupported. These are sensitivity checks, not confidence intervals.

        Audit: limited publisher-held-out coverage. Cross-source validity is unresolved. Validation audit.

        Matched family win shares below describe source evidence; they are not averaged to produce the adjusted score.

          Long contextNo comparable evidenceUnknown

          0 core families; 0 direct opponents across 0 labs. No admitted core comparisons

          Estimated against the same complete panel: gpt-5.6-sol claude-opus-4-8 gemini-3.1-pro . Indirect comparisons assume performance can be summarized by one strength within this capability.

          Refit without one family: No supported estimate; 5/5 scenarios unsupported. Without one publisher: No supported estimate; 5/5 unsupported. Smoothing check: No supported estimate; 3/3 unsupported. These are sensitivity checks, not confidence intervals.

          Audit: family and publisher holdouts underperformed neutral predictions. Treat this as an exploratory estimate. Validation audit.

          Matched family win shares below describe source evidence; they are not averaged to produce the adjusted score.

            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.

            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 evidence
            Score 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
            Documented-evidence 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 →

            BenchmarkEffortScoreSource
            AA-AnalystAgentReasoning35.0%Artificial Analysis
            AA-Briefcase EloReasoning1424Artificial Analysis
            AA-LCR v1.1Reasoning88.3%Artificial Analysis
            AA-Omniscience AccuracyReasoning36.4%Artificial Analysis
            AA-Omniscience IndexReasoning16.4Artificial Analysis
            APEX-Agents-AAReasoning38.0%Artificial Analysis
            Artificial Analysis Cyber IndexUnspecified47.7Artificial Analysis
            AutomationBench-AAReasoning51.0%Artificial Analysis
            CritPtReasoning20.9%Artificial Analysis
            EnterpriseOps-Gym-AAReasoning47.2%Artificial Analysis
            FrontierCS 2Unspecified8.3%FrontierCS
            GDP.pdf: All-pass RateReasoning14.8%Artificial Analysis
            GDPval-AA v2.1 LeaderboardReasoning1591Artificial Analysis
            Humanity's Last ExamReasoning46.5%Artificial Analysis
            ITBench-AAReasoning55.6%Artificial Analysis
            MLCR-AAReasoning18.3%Artificial Analysis
            MMMU-ProReasoning76.4%Artificial Analysis
            SciCodeReasoning58.9%Artificial Analysis
            Terminal-Bench v4.0Reasoning33.3%Artificial Analysis
            Terminal-Bench-Science 0.1Reasoning2.4%Artificial Analysis
            Benchmark scores & sources

            Original results, evaluation harnesses, and evidence behind this model.

            BenchmarkBucketScoreHarnessEvidenceSource-recorded date
            Artificial Analysis Cyber IndexSupporting evidence47.7068149907409 Artificial Analysis Stirrup · Cyber Index v1.0 · unspecified

            Effort: Unspecified

            Cyber Index source settings

            Artificial 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

            Supporting evidence outside the reviewed capability core

            2026-11-18
            AutomationBench-AASupporting evidence50.956594190962875%Artificial Analysis AutomationBench-AA

            Effort: Not specified

            official board

            Supporting evidence outside the reviewed capability core

            2026-11-21
            FrontierCS 2Supporting evidence10.4%Step Code

            Effort: Not specified

            official board

            Supporting evidence outside the reviewed capability core

            2026-11-20
            GDPval-AAAgentic1591Artificial Analysis GDPval-AA

            Effort: Not specified

            contributes to capability
            official board2026-11-22
            LMArena Agent ArenaSupporting evidence-5.15 LMArena Agent Arena · unspecified

            Effort: Not specified

            official board

            Supporting evidence outside the reviewed capability core

            2026-11-18
            LMArena Text ArenaHuman pref1449LMArena Text

            Effort: Not specified

            contributes to capability
            official board2026-11-19
            ARC-AGI-2Hard reasoning————
            DeepSWE v1.1Agentic————
            GPQA DiamondHard reasoning————
            Humanity's Last ExamHard reasoning————
            LiveCodeBenchCoding————
            MMLU-ProKnowledge————
            OSWorld-VerifiedAgentic————
            SWE-bench ProAgentic————
            SWE-bench VerifiedAgentic————
            Terminal-Bench 2.1Agentic————