Loading benchmark catalogue
Compare performance benchmarks, coding intelligence, reasoning evaluations, context limits, and API economics between Step 5 Preview (StepFun) and Beam 1.0 501B A23B (Reflection AI).
| Metric / Capability | Step 5 Preview | Beam 1.0 501B A23B |
|---|---|---|
| Developer / Organization | StepFun | Reflection AI |
| Release Date | 2026-10-08 | 2026-10-16 |
| Deployment / Weights | Open Weights | Open Weights |
| Context Window | 1.0M tokens (1,048,576 tokens) | 1.0M tokens (1,048,576 tokens) |
| Input Pricing (/1M Tokens) | Free (Open Weights) | Free (Open Weights) |
| Output Pricing (/1M Tokens) | Free (Open Weights) | Free (Open Weights) |
| Benchmark / Domain | Step 5 Preview | Beam 1.0 501B A23B | Advantage |
|---|---|---|---|
Artificial Analysis Intelligence Index Composite index aggregating 10+ evaluations of general reasoning and knowledge. | 43.7% | — | — |
Artificial Analysis Coding Agent Index v2.0 Composite index of coding-agent systems (model + harness) across FrontierCode v1.1, SWE-Atlas-QnA, and Terminal-Bench v4. | 43.1% | — | — |
SWE-bench Pro Harder, contamination-resistant successor to SWE-bench spanning multiple languages. | — | 66.1% | — |
Terminal-Bench 4.0 Sandboxed command-line tasks requiring shell and file-system operation. | 33.3% | — | — |
GPQA Diamond Graduate-level physics, chemistry, and biology questions written by domain experts. | 93.5% | 90.6% | Step 5 Preview (+3%) |
Humanity's Last Exam Expert-written questions across hundreds of disciplines designed to resist saturation. | 46.5% | 36.0% | Step 5 Preview (+29%) |
Design Arena ELO Human-preference ELO across UI, 3D, data-visualization, and game-dev generations. | — | 1227 | — |
Step 5 Preview leads across 2 evaluated benchmarks compared to 0 for Beam 1.0 501B A23B, showing notable advantages in GPQA Diamond, Humanity's Last Exam.
Both models feature equivalent context windows of 1.0M tokens (1,048,576 tokens).
Both models have comparable pricing structures or open weight deployment options.
Step 5 Preview is an open-weights model. Beam 1.0 501B A23B is an open-weights model.
Analyze 130+ models side-by-side using interactive radar charts, cost-efficiency quadrant plots, and live dataset filters on the full NeuBench index.
Open Interactive Comparator