MODEL DETAIL · Inception

Mercury 2.5 Preview

Source-linked record by Inception

RANK N/A

Mercury 2.5 Preview supports text, tools, reasoning workflows. Published fields are kept separate from benchmark evidence and community signals.

Visit Inception ↗Compare model →

Fit scoreN/AContextual · fit-v1

CodingN/ADatabase signal

ReasoningN/ADatabase signal

Context window260000Published limit

Input price$0.04Per 1M tokens

Released2026-08-31Source date

DATABASE MODEL RECORD

What this record says.

Mercury 2.5 Preview is cataloged by Inception with source-linked capabilities, pricing, release metadata, and explicitly separated evaluation evidence.

Source snapshot fetchedConfidence: N/A

TextToolsReasoningLicense N/A

EVALUATION EVIDENCE

Benchmarks

Benchmark library →

Only model-specific published scores are shown here. Missing values remain N/A and are not estimated from a composite score.

Benchmark	Score	Status
AutoBenchPublished Best for Work Automations (AutoBench) scores.	N/A	N/A	View source ↗
BrowseCompPublished Best in Browsing (BrowseComp) scores.	N/A	N/A	View source ↗
SWE-Bench VerifiedPublished Best in Agentic Coding (SWE Bench) scores.	N/A	N/A	View source ↗
OSWorld-VerifiedPublished Best in Computer Use (OSWorld) scores.	N/A	N/A	View source ↗
Humanity's Last ExamPublished Best Overall (Humanity's Last Exam) scores.	N/A	N/A	View source ↗

This record’s overall fit, coding, and reasoning fields are separate catalog signals, not substitutes for benchmark results.

PUBLISHED PRICING

Pricing and limits

Source ↗

Input / 1M tokens$0.04

Output / 1M tokens$0.15

Context window260000

Knowledge cutoffN/A

LicenseN/A

Pricing is shown as published by the catalog record. Confirm provider terms before production use.

FIT CONTEXT

Best suited for

N/A

Capabilities: Text · Tools · Reasoning. This is descriptive metadata, not a guarantee of task performance.

RANK HISTORY

How the record changed

See rankings →

No historical rank snapshots are recorded for this model.

RELATED RECORDS

Compare this model

Open comparison →

EVIDENCE LAYERS

Three kinds of evidence.

Methodology →

Published facts25 canonical fieldsCapabilities, limits, pricing, license, and release metadata.

Published benchmarks0 reported scoresExternal evaluations with their own source and version.

TopLLM evaluationNot availableTopLLM first-party task evaluations will be published separately from external benchmark results.