Step 5 Preview Benchmark Details
Step 5 Preview currently shows benchmark results led by AA-LCR (2 / 171, score 88.30), HLE (9 / 565, score 59.40), GPQA Diamond (25 / 463, score 93.50). This page also compares it with 3 competitor models and 3 predecessor or same-series models, including performance and pricing views when available.
Benchmark Results
Benchmark Results
General Knowledge
3 evaluationsAI Agent - Tool Usage
6 evaluationsCoding and Software Engineer
6 evaluationsAgent Level Benchmark
4 evaluationsProductivity Knowledge
5 evaluationsMultimodal Understanding
2 evaluationsCompetitor Comparison
Benchmark scores for Step 5 Preview compared against top models in its class
12 benchmarks with comparable scores. Each model shows its best score; mode label is displayed below.
| Benchmark | Step 5 PreviewCurrent | Qwen3.8-27B | DeepSeek-V4.1-Flash | GLM-5.3-Flash |
|---|---|---|---|---|
20.90Thinking Level · High | 5.40Thinking Level · Extra High | 14.30Thinking Level · High | 15.40Thinking Enabled | |
59.40Thinking Level · High ｜ Tools | 33.90Thinking Level · Extra High | 63.90Thinking Level · High ｜ Tools | 55.30Thinking Level · High ｜ Tools | |
93.50Thinking Level · High | 90.50Thinking Level · Extra High | 90.90Thinking Level · High | 91.20Thinking Enabled | |
88.30Thinking Level · High | 82.00Thinking Level · Extra High | 84.00Thinking Level · High | -- | |
51.00Thinking Level · High ｜ Tools | -- | 68.90Thinking Level · High | 60.40Thinking Level · High | |
84.70Thinking Level · High ｜ Tools | -- | 88.10Thinking Level · High ｜ Tools | -- | |
85.00Thinking Level · High ｜ Tools | 79.80Thinking Level · Extra High ｜ Tools | 90.60Thinking Level · High ｜ Tools | 84.30Thinking Level · High ｜ Tools | |
33.30Thinking Level · High ｜ Tools | 5.60Thinking Level · Extra High ｜ Tools | 26.80Thinking Level · High ｜ Tools | 32.80Thinking Enabled ｜ Tools | |
74.10Thinking Level · High ｜ Tools | -- | -- | 78.40Thinking Level · High ｜ Tools | |
67.70Thinking Level · High ｜ Tools | 42.20Thinking Enabled ｜ Tools | 74.20Thinking Level · High ｜ Tools | 63.39Thinking Level · High ｜ Tools | |
80.50Thinking Level · High ｜ Tools | -- | 20.30Thinking Level · High ｜ Tools | -- | |
58.90Thinking Level · High | 46.60Thinking Level · Extra High | 51.90Thinking Level · High | 51.60Thinking Enabled |
Standard API Pricing: Step 5 Preview vs. Peer Models
Shows standard text input and output pricing side by side for each model. If extended-context pricing exists, the chart keeps the base rate and explains the threshold below.
Source: DataLearnerAI. Standard text prices shown here use the default supplier. · USD / 1M tokens
| Model | Supplier | Standard input | Standard output | Base price applies to |
|---|---|---|---|---|
Step 5 Preview | StepFunAI | $1 / 1M tokens | $2.7 / 1M tokens | — |
GLM-5.3-Flash | 智谱AI | $0.075 / 1M tokens | $0.25 / 1M tokens | — |
Version History
How each version of the Step 5 Preview series stacks up on benchmark tests
8 benchmarks with comparable scores. Each model shows its best score; mode label is displayed below.· Click a row to view its trend chart.
| Benchmark | Step 5 PreviewCurrent | Step 3.7 Flash | Step 3.5 Flash | Step3 |
|---|---|---|---|---|
20.90Thinking Level · High | 2.30Thinking Enabled | 2.50Thinking Enabled | -- | |
59.40Thinking Level · High ｜ Tools | 47.20Thinking Enabled ｜ Tools | 24.50Thinking Enabled | -- | |
93.50Thinking Level · High | 80.90Thinking Enabled | 83.10Thinking Enabled | 73.00Standard Mode | |
88.70Thinking Level · High ｜ Tools | 75.82Thinking Enabled ｜ Tools | 69.00Thinking Enabled ｜ Tools | -- | |
85.00Thinking Level · High ｜ Tools | 59.50Thinking Enabled ｜ Tools | -- | -- | |
58.90Thinking Level · High | 43.90Thinking Enabled | -- | -- | |
42.50Thinking Level · High ｜ Tools | 12.00Thinking Enabled ｜ Tools | -- | -- | |
76.00Thinking Level · High | 75.30Thinking Enabled | -- | -- |
Single-Benchmark Version Trend
Viewing: CritPt · 综合评估
Standard API Pricing Across the Step 5 Preview Series
Shows standard text input and output pricing side by side for each model. If extended-context pricing exists, the chart keeps the base rate and explains the threshold below.
Source: DataLearnerAI. Standard text prices shown here use the default supplier.
These models use different currencies or billing units, so the page falls back to raw price values instead of a shared bar chart.
| Model | Supplier | Standard input | Standard output | Base price applies to |
|---|---|---|---|---|
Step 5 Preview | StepFunAI | $1 / 1M tokens | $2.7 / 1M tokens | — |
Step 3.7 Flash | StepFunAI | ¥1.35 / 1M tokens | ¥8.1 / 1M tokens | — |