# StepFun Step 5 Preview

As of October 22, 2026, StepFun Step 5 Preview ranks #41 of 123 models overall with 60.5 ±10.7 on the LLMBenchmark Index. Step 5 Preview ranks #36 of 122 in reasoning, its strongest category. StepFun Step 5 Preview costs $1.00 per million input tokens and $2.70 per million output tokens. Step 5 Preview was released on October 8, 2026.

Page: https://llmbenchmark.ai/models/stepfun-step-5-preview
Data from October 22, 2026. Every figure below names the board it was read from and the day.

- Maker: StepFun
- Released: October 8, 2026
- Price per million input tokens: $1.00
- Price per million output tokens: $2.70
- Context window: 1.05M tokens
- Overall rank: 41 of 123, by the LLMBenchmark Index
- LLMBenchmark Index: 60.5 ±10.7 (90% margin, from 5 of 7 inputs)
- Artificial Analysis Intelligence Index: 43.7
- Vibe Coding Index: 61.1 (from 4 of 6 coding benchmarks)

Benchmark results (61 of 195):

- LiveBench coding: 85.6% (source: LiveBench, read October 22, 2026)
- LMArena WebDev: 1567 Elo (source: LMArena WebDev, read October 22, 2026)
- AA Intelligence Index: 43.7 (source: Artificial Analysis (via OpenRouter), read October 22, 2026)
- LiveBench reasoning: 83.8% (source: LiveBench, read October 22, 2026)
- LiveBench data analysis: 63.5% (source: LiveBench, read October 22, 2026)
- LiveBench research: 72.8% (source: LiveBench, read October 22, 2026)
- LiveBench browser: 24.0% (source: LiveBench, read October 22, 2026)
- LiveBench long agentic: 27.5% (source: LiveBench, read October 22, 2026)
- LiveBench design: 76.9% (source: LiveBench, read October 22, 2026)
- Terminal-Bench 4 (Vals AI): 31.8% (source: Vals AI boards, read October 22, 2026)
- Vibe Code Bench (Vals AI): 70.4% (source: Vals AI boards, read October 22, 2026)
- Code migration (Vals AI): 39.0% (source: Vals AI boards, read October 22, 2026)
- SREBench (Vals AI): 0.4% (source: Vals AI boards, read October 22, 2026)
- IOI (Vals AI): 38.1% (source: Vals AI boards, read October 22, 2026)
- SWE-bench Multimodal (Vals AI): 40.8% (source: Vals AI boards, read October 22, 2026)
- Finance Agent (Vals AI): 50.7% (source: Vals AI boards, read October 22, 2026)
- Tax Agent Bench (Vals AI): 27.3% (source: Vals AI boards, read October 22, 2026)
- Legal Research Bench (Vals AI): 40.4% (source: Vals AI boards, read October 22, 2026)
- Excel Modeling Benchmark (Vals AI): 57.1% (source: Vals AI boards, read October 22, 2026)
- BioMysteryBench (Vals AI): 67.4% (source: Vals AI boards, read October 22, 2026)
- Terminal-Bench-Science (Vals AI): 2.9% (source: Vals AI boards, read October 22, 2026)
- Vals Science Index: 29.6% (source: Vals AI boards, read October 22, 2026)
- Public Benefits Bench (Vals AI): 58.1% (source: Vals AI boards, read October 22, 2026)
- MysteryMechanism (Vals AI): 18.5% (source: Vals AI boards, read October 22, 2026)
- Humanity's Last Exam (Artificial Analysis run): 46.5% (source: Artificial Analysis, read October 22, 2026)
- SciCode: 58.9% (source: Artificial Analysis, read October 22, 2026)
- Long context reasoning (AA-LCR): 88.3% (source: Artificial Analysis, read October 22, 2026)
- ProofBench: 42.0% (source: Epoch AI benchmarking hub, read October 22, 2026)
- LMArena Text: 1440 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: coding: 1485 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: hard prompts: 1461 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: math: 1458 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: instruction following: 1438 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: creative writing: 1409 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Vision: 1265 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: English: 1447 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: non-English: 1428 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: Chinese: 1500 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: Japanese: 1383 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: French: 1438 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: Spanish: 1441 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: Russian: 1433 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: multi-turn: 1437 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: longer queries: 1449 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: expert: 1485 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: hard prompts in English: 1454 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: software and IT: 1473 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: mathematical work: 1460 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: science: 1454 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: medicine and healthcare: 1439 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: legal and government: 1437 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: business and finance: 1435 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: writing and language: 1425 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: entertainment and media: 1412 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena WebDev: React: 1583 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena WebDev: HTML: 1556 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena WebDev: from an image: 1550 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Vision: English: 1290 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Vision: reading text: 1282 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Vision: diagrams: 1308 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Vision: homework: 1265 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)