Step 5 Preview
Not enough verified architecture information for a reliable VRAM estimate.
GeekRadar / The comparison desk
COMPARE.
AI modelsStep 5 Preview
AI model Released
- Context window
- 1,000,000 tokens
- Maximum output
- 1,000,000 tokens
- Open weights
- Yes
Capability & preference
Human preference · Arena
Overall text preferences from head-to-head votes. Not factual accuracy or a task-success rate.
Recorded results
Only the same benchmark, version, workload, scenario and unit share a row. Missing results are not zero. System results include the full submitted hardware and software configuration.
Arena text preference / chinesehuman preference · 2026-10-28 · rating
Step 5 Preview
1,501.77 rating
Confidence interval: 1,482.52 – 1,521.01
921 votes
- Category
- chinese
- Evaluated configuration
- Step 5 Preview
- Evaluation type
- human preference
Arena text preference / codinghuman preference · 2026-10-28 · rating
Step 5 Preview
1,482.24 rating
Confidence interval: 1,470.71 – 1,493.77
2721 votes
- Category
- coding
- Evaluated configuration
- Step 5 Preview
- Evaluation type
- human preference
Arena text preference / creative_writinghuman preference · 2026-10-28 · rating
Step 5 Preview
1,413.03 rating
Confidence interval: 1,399.93 – 1,426.13
2359 votes
- Category
- creative_writing
- Evaluated configuration
- Step 5 Preview
- Evaluation type
- human preference
Arena text preference / englishhuman preference · 2026-10-28 · rating
Step 5 Preview
1,453.69 rating
Confidence interval: 1,443.93 – 1,463.44
4072 votes
- Category
- english
- Evaluated configuration
- Step 5 Preview
- Evaluation type
- human preference
Arena text preference / exclude_tieshuman preference · 2026-10-28 · rating
Step 5 Preview
1,436.72 rating
Confidence interval: 1,428.02 – 1,445.42
8057 votes
- Category
- exclude_ties
- Evaluated configuration
- Step 5 Preview
- Evaluation type
- human preference
Arena text preference / experthuman preference · 2026-10-28 · rating
Step 5 Preview
1,478.09 rating
Confidence interval: 1,460.74 – 1,495.44
1142 votes
- Category
- expert
- Evaluated configuration
- Step 5 Preview
- Evaluation type
- human preference
Arena text preference / frenchhuman preference · 2026-10-28 · rating
Step 5 Preview
1,439.84 rating
Confidence interval: 1,412.06 – 1,467.62
485 votes
- Category
- french
- Evaluated configuration
- Step 5 Preview
- Evaluation type
- human preference
Arena text preference / germanhuman preference · 2026-10-28 · rating
Step 5 Preview
1,453.59 rating
Confidence interval: 1,414.35 – 1,492.83
193 votes
- Category
- german
- Evaluated configuration
- Step 5 Preview
- Evaluation type
- human preference
Arena text preference / hard_promptshuman preference · 2026-10-28 · rating
Step 5 Preview
1,462.61 rating
Confidence interval: 1,454.97 – 1,470.26
7107 votes
- Category
- hard_prompts
- Evaluated configuration
- Step 5 Preview
- Evaluation type
- human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-28 · rating
Step 5 Preview
1,461.07 rating
Confidence interval: 1,449.18 – 1,472.96
2648 votes
- Category
- hard_prompts_english
- Evaluated configuration
- Step 5 Preview
- Evaluation type
- human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-28 · rating
Step 5 Preview
1,442.85 rating
Confidence interval: 1,429.07 – 1,456.63
1939 votes
- Category
- industry_business_and_management_and_financial_operations
- Evaluated configuration
- Step 5 Preview
- Evaluation type
- human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-28 · rating
Step 5 Preview
1,412.04 rating
Confidence interval: 1,400.25 – 1,423.82
2880 votes
- Category
- industry_entertainment_and_sports_and_media
- Evaluated configuration
- Step 5 Preview
- Evaluation type
- human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-28 · rating
Step 5 Preview
1,440.90 rating
Confidence interval: 1,421.43 – 1,460.36
931 votes
- Category
- industry_legal_and_government
- Evaluated configuration
- Step 5 Preview
- Evaluation type
- human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-28 · rating
Step 5 Preview
1,458.77 rating
Confidence interval: 1,444.77 – 1,472.78
1825 votes
- Category
- industry_life_and_physical_and_social_science
- Evaluated configuration
- Step 5 Preview
- Evaluation type
- human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-28 · rating
Step 5 Preview
1,461.99 rating
Confidence interval: 1,439.33 – 1,484.66
643 votes
- Category
- industry_mathematical
- Evaluated configuration
- Step 5 Preview
- Evaluation type
- human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-28 · rating
Step 5 Preview
1,438.78 rating
Confidence interval: 1,417.23 – 1,460.33
787 votes
- Category
- industry_medicine_and_healthcare
- Evaluated configuration
- Step 5 Preview
- Evaluation type
- human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-28 · rating
Step 5 Preview
1,471.58 rating
Confidence interval: 1,462.08 – 1,481.08
4170 votes
- Category
- industry_software_and_it_services
- Evaluated configuration
- Step 5 Preview
- Evaluation type
- human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-28 · rating
Step 5 Preview
1,427.44 rating
Confidence interval: 1,416.16 – 1,438.73
3108 votes
- Category
- industry_writing_and_literature_and_language
- Evaluated configuration
- Step 5 Preview
- Evaluation type
- human preference
Arena text preference / instruction_followinghuman preference · 2026-10-28 · rating
Step 5 Preview
1,440.81 rating
Confidence interval: 1,430.92 – 1,450.70
3960 votes
- Category
- instruction_following
- Evaluated configuration
- Step 5 Preview
- Evaluation type
- human preference
Arena text preference / japanesehuman preference · 2026-10-28 · rating
Step 5 Preview
1,397.68 rating
Confidence interval: 1,359.09 – 1,436.27
237 votes
- Category
- japanese
- Evaluated configuration
- Step 5 Preview
- Evaluation type
- human preference
Arena text preference / koreanhuman preference · 2026-10-28 · rating
Step 5 Preview
1,414.92 rating
Confidence interval: 1,374.44 – 1,455.40
202 votes
- Category
- korean
- Evaluated configuration
- Step 5 Preview
- Evaluation type
- human preference
Arena text preference / longer_queryhuman preference · 2026-10-28 · rating
Step 5 Preview
1,452.09 rating
Confidence interval: 1,442.80 – 1,461.37
4752 votes
- Category
- longer_query
- Evaluated configuration
- Step 5 Preview
- Evaluation type
- human preference
Arena text preference / mathhuman preference · 2026-10-28 · rating
Step 5 Preview
1,456.97 rating
Confidence interval: 1,433.20 – 1,480.73
574 votes
- Category
- math
- Evaluated configuration
- Step 5 Preview
- Evaluation type
- human preference
Arena text preference / multi_turnhuman preference · 2026-10-28 · rating
Step 5 Preview
1,436.75 rating
Confidence interval: 1,421.60 – 1,451.91
1618 votes
- Category
- multi_turn
- Evaluated configuration
- Step 5 Preview
- Evaluation type
- human preference
Arena text preference / non_englishhuman preference · 2026-10-28 · rating
Step 5 Preview
1,428.91 rating
Confidence interval: 1,421.43 – 1,436.40
7277 votes
- Category
- non_english
- Evaluated configuration
- Step 5 Preview
- Evaluation type
- human preference
Arena text preference / overallhuman preference · 2026-10-28 · rating
Step 5 Preview
1,442.72 rating
Confidence interval: 1,436.40 – 1,449.04
11355 votes
- Category
- overall
- Evaluated configuration
- Step 5 Preview
- Evaluation type
- human preference
Arena text preference / polishhuman preference · 2026-10-28 · rating
Step 5 Preview
1,390.26 rating
Confidence interval: 1,346.04 – 1,434.48
179 votes
- Category
- polish
- Evaluated configuration
- Step 5 Preview
- Evaluation type
- human preference
Arena text preference / russianhuman preference · 2026-10-28 · rating
Step 5 Preview
1,430.66 rating
Confidence interval: 1,416.23 – 1,445.10
1693 votes
- Category
- russian
- Evaluated configuration
- Step 5 Preview
- Evaluation type
- human preference
Arena text preference / spanishhuman preference · 2026-10-28 · rating
Step 5 Preview
1,443.97 rating
Confidence interval: 1,415.93 – 1,472.01
417 votes
- Category
- spanish
- Evaluated configuration
- Step 5 Preview
- Evaluation type
- human preference
Run it locally
API cost
Standard text-token estimate. Excludes taxes, caching, batch discounts, reasoning and multimodal surcharges. Provider limits and regional availability may differ.
Step 5 Preview
Step 5 Preview / Pricing tiers
| Provider / scope | Rate | Currency | Amount / unit |
|---|---|---|---|
| DeepInfrastepfun-ai/Step-5-PreviewStandard | Cached input | USD | 0.05 / 1M tokens |
| Input | USD | 1 / 1M tokens | |
| Output | USD | 2.7 / 1M tokens | |
| StepFunstep-5-previewStandard | Cached input | CNY | 0.7 / 1M tokens |
| Input | CNY | 7 / 1M tokens | |
| Output | CNY | 20 / 1M tokens |
Capabilities
- Context window
- 1,000,000 tokens
- Maximum output
- 1,000,000 tokens
- Reasoning
- Yes
- Tool calling
- Yes
- Open weights
- Yes
- Model license
- Proprietary
Input modalities
- text
- image
- video
Output modalities
- text
0 selected Compare 0