# Mercury 2.5 vs Step 5 Preview

> Side-by-side benchmark comparison for Mercury 2.5 and Step 5 Preview across agentic, coding, multimodal, knowledge, reasoning, multilingual, and math tasks.

- Canonical page: https://benchlm.ai/compare/mercury-2-5-vs-step-5-preview
- Last updated: September 21, 2026

- Shared sourced benchmarks: 2
- HTML indexing: indexable
- Ranking lane: BenchAlign v5

## Quick Verdict

Evidence is too thin for a benchmark verdict: Mercury 2.5 and Step 5 Preview share only 2 sourced benchmark rows.

## Summary

- Only 2 shared sourced benchmark rows are available. That is not enough for a broad capability verdict, so this mirror does not name an overall winner.
- Mercury 2.5 has the lower published output-token price.
- Step 5 Preview has the larger published context window at 1M.

## Model Snapshot

| Property | Mercury 2.5 | Step 5 Preview |
|----------|----------|----------|
| Creator | Inception | StepFun |
| Type | Proprietary | Pending |
| Reasoning | Reasoning | Reasoning |
| Context | 260K | 1M |
| Independent public score (not head-to-head) | null | null |
| Benchmarks Covered | 6 | 22 |
| Pricing (input/output) | $0.04 / $0.15 | $1.00 / $2.70 |

## Category Breakdown

### Agentic

- Winner: Insufficient shared evidence
- Mercury 2.5 public-lane score: 37.4 (Estimated · #131/154)
- Step 5 Preview public-lane score: Coming soon

| Benchmark | Mercury 2.5 | Step 5 Preview | Winner |
|-----------|-----------|-----------|--------|
| τ³-bench results | 96.0% | Coming soon | Coming soon |
| DeepSearchQA | 34.0% | Coming soon | Coming soon |
| Terminal-Bench 2.1 (Vals) | 34.1% | Coming soon | Coming soon |
| Terminal-Bench 2.1 | Coming soon | 85.0% | Coming soon |
| Terminal-Bench 4.0 | Coming soon | 33.30% | Coming soon |
| CyberGym | Coming soon | 84.7% | Coming soon |
| AutomationBench | Coming soon | 44.0% | Coming soon |
| Toolathlon-Verified | Coming soon | 74.1% | Coming soon |
| MCP Atlas | Coming soon | 85.6% | Coming soon |
| JobBench | Coming soon | 59.0% | Coming soon |
| APEX-Agents | Coming soon | 37.8% | Coming soon |
| DRACO | Coming soon | 83.3% | Coming soon |
| BrowseComp | Coming soon | 88.7% | Coming soon |
| Agents' Last Exam | Coming soon | 29.5% | Coming soon |

### Coding

- Winner: Insufficient shared evidence
- Mercury 2.5 public-lane score: 41.6 (Estimated · #113/156)
- Step 5 Preview public-lane score: Coming soon

| Benchmark | Mercury 2.5 | Step 5 Preview | Winner |
|-----------|-----------|-----------|--------|
| SciCode | 38% | 58.9% | Step 5 Preview |
| DeepSWE | Coming soon | 67.7% | Coming soon |
| Terminal-Bench 2.1 | Coming soon | 85.0% | Coming soon |
| ProgramBench | Coming soon | 80.5% | Coming soon |
| sweMarathon | Coming soon | 72.7% | Coming soon |
| MLS-Bench Lite | Coming soon | 40.5% | Coming soon |

### Reasoning

- Winner: Insufficient shared evidence
- Mercury 2.5 public-lane score: 67.7 (Unranked · 1 rankable row)
- Step 5 Preview public-lane score: 78.5 (Unranked · 2 rankable rows)

| Benchmark | Mercury 2.5 | Step 5 Preview | Winner |
|-----------|-----------|-----------|--------|
| CritPt | Coming soon | 20.9% | Coming soon |

### Multimodal & Grounded

- Winner: Insufficient shared evidence
- Mercury 2.5 public-lane score: Coming soon
- Step 5 Preview public-lane score: 61.2 (#28/49)

| Benchmark | Mercury 2.5 | Step 5 Preview | Winner |
|-----------|-----------|-----------|--------|
| OfficeQA Pro | Coming soon | 60.3% | Coming soon |
| MMMU-Pro | Coming soon | 76% | Coming soon |

### Knowledge

- Winner: Insufficient shared evidence
- Mercury 2.5 public-lane score: 47.9 (Estimated · #97/186)
- Step 5 Preview public-lane score: Coming soon

| Benchmark | Mercury 2.5 | Step 5 Preview | Winner |
|-----------|-----------|-----------|--------|
| GPQA-D | 79.0% | 93.5% | Step 5 Preview |
| HLE | Coming soon | 46.5% | Coming soon |

### Instruction Following

- Winner: Insufficient shared evidence
- Mercury 2.5 public-lane score: 77.7 (#56/124)
- Step 5 Preview public-lane score: Coming soon

| Benchmark | Mercury 2.5 | Step 5 Preview | Winner |
|-----------|-----------|-----------|--------|
| IFBench | 77% | Coming soon | Coming soon |

## FAQ

### Is there enough evidence to pick between Mercury 2.5 and Step 5 Preview?

Not yet. The models share only 2 sourced benchmark rows, so this mirror reports the available measurements and metadata without naming a broad winner.

### What can I compare safely on this page?

Published pricing, context windows, model type, and individual shared benchmark rows are directly comparable. Independent overall scores and non-overlapping benchmark coverage are labeled separately and should not be read as a controlled head-to-head result.

## Related Comparisons

- [Mercury 2.5 vs Mercury 2.5 Preview](/compare/mercury-2-5-vs-mercury-2-5-preview)
- [Step 5 Preview vs Mercury 2.5 Preview](/compare/mercury-2-5-preview-vs-step-5-preview)
- [Mercury 2.5 vs Claude Fable 5.1](/compare/claude-fable-5-1-vs-mercury-2-5)
- [Step 5 Preview vs Claude Fable 5.1](/compare/claude-fable-5-1-vs-step-5-preview)

## Explore More

- [Mercury 2.5 profile](/models/mercury-2-5)
- [Step 5 Preview profile](/models/step-5-preview)
- [Compare Pricing](/llm-pricing)
- [Alternative Finder](/tools/alternative-finder)
- [LLM Selector](/tools/llm-selector)
- [Overall Rankings](/best/overall)