Mercury — Retired model

Retired modelThis model has reached end of life and is no longer available through BazaarLink. Historical specifications and independent benchmarks remain below. Retired on May 1, 2026.

Mercury is the first diffusion large language model (dLLM). Applying a breakthrough discrete diffusion approach, the model runs 5-10x faster than even speed optimized models like GPT-4.1 Nano and Claude 3.5 Haiku while matching their performance. Mercury's speed enables developers to provide responsive user experiences, including with voice agents, search interfaces, and chatbots. Read more in the [blog post] (https://www.inceptionlabs.ai/blog/introducing-mercury) here.

Provider	inception
Released	June 2025
Model ID	`inception/mercury`

Technical specifications

Context window

128K tokens

Reasoning

—

Input

Text

Output

Text

Independent benchmarks

Scores below come from Artificial Analysis, an independent third party. BazaarLink does not participate in the testing.

Intelligence 21

Coding 31

Math

MMLU

GPQA 77

This modelCategory leader

Coding ability

#111out of 198 models

LiveCodeBench / SciCode and similar

Overall intelligence

#209out of 573 models

Aggregated across academic benchmarks

Time to first token

#541out of 586 models

AA 全球 p50：3.79 秒

Intelligence

Mid-tier

This model

Category leader

Median

Coding

Mid-tier

This model

Category leader

Median

GPQA

77%

—

This model

77%

Category leader

94%

Median

69%

HLE

16%

—

This model

16%

Category leader

53%

Median

SciCode

39%

—

This model

39%

Category leader

60%

Median

33%

IFBench

70%

—

This model

70%

Category leader

83%

Median

44%

τ²-Bench Telecom

71%

—

This model

71%

Category leader

99%

Median

46%

AA-LCR

36%

—

This model

36%

Category leader

76%

Median

40%

Terminal-Bench Hard

27%

—

This model

27%

Category leader

66%

Median

14%

Top 5 — CodingCoding Index leaderboard

1GPT-5.6 Sol (xhigh)openai/gpt-5-6-sol-xhigh78$5 / $30

2Claude Opus 5 (Adaptive Reasoning, Max Effort)anthropic/claude-opus-578$5 / $25

3GPT-5.6 Sol (max)openai/gpt-5-6-sol77$5 / $30

4GPT-5.6 Sol (high)openai/gpt-5-6-sol-high77$5 / $30

5Claude Opus 5 (Adaptive Reasoning, Xhigh Effort)anthropic/claude-opus-5-xhigh77$5 / $25

AASource: Artificial Analysis · Independent third-party evaluation; not influenced by BazaarLinkView full evaluation on AA →

← All Models

Frequently Asked Questions

Can I still use the retired Mercury model?

No. Mercury has been retired and is retained here only as a historical reference. See the active alternatives linked on this page.

Relay integrity checks

No integrity-check data is available for this model yet.

BazaarLink Probe verifies endpoints that claim to serve this model and flags behavior that differs from the reference baseline.

View the full integrity report →

Mercury — Retired model

Technical specifications

Independent benchmarks

Top 5 — CodingCoding Index leaderboard

Frequently Asked Questions

Relay integrity checks

Related models and links