What is the IQ of mercury-2?

mercury-2 has an estimated IQ of 96, which ranks #121 out of 143 public models on the AI IQ leaderboard. The score combines six equally weighted reasoning dimensions using measured benchmark results and conservative estimates for missing coverage.

How much does mercury-2 cost?

mercury-2 costs $0.25 per million input tokens and $0.75 per million output tokens. Adjusted for how many tokens it actually consumes on real tasks, its effective cost works out to $0.8491 per million input-plus-output tokens.

Is mercury-2 open source?

No — mercury-2 is a proprietary model. Its weights are not publicly available, so it is used through hosted APIs and products.

When was mercury-2 released?

mercury-2 was publicly released on February 24, 2026.

How large is the context window of mercury-2?

mercury-2 supports a context window of 128,000 tokens — the amount of text it can consider in a single request.

How fast is mercury-2?

In independent measurements, mercury-2 generates about 1076 tokens per second, with a typical response time of about 5.5 seconds.

Inception

mercury-2

Public AI IQ model profile with source-backed benchmark results and derived ranking context.

IQ

96

EQ

n/a

Effective Cost

$0.8491

IQ Rank

#121

mercury-2 API pricing — full price table, workload cost examples, and cheaper alternatives.

IQ Dimensions

Dimension	IQ	Coverage
Abstract Reasoning	77	0/3
Mathematical Reasoning	92	0/5
Academic Reasoning	113	4/6
Programmatic Reasoning	101	1/5
Computer Use	90	0/5
Reliability	103	3/6

Benchmark Results

Benchmark	Score	Dimension
AA Long Context Reasoning v1.1	43.6667	Reliability
AA Omniscience	-50.7167	Reliability
CritPt	0.849	Academic Reasoning
GPQA Diamond	76.9697	Academic Reasoning
Humanity's Last Exam	17.1455	Academic Reasoning
IFBench	69.7959	Reliability
SciCode	37.7315	Academic Reasoning
Terminal-Bench 4.0	0	Programmatic Reasoning

Compare

Frequently Asked Questions

What is the IQ of mercury-2?: mercury-2 has an estimated IQ of 96, which ranks #121 out of 143 public models on the AI IQ leaderboard. The score combines six equally weighted reasoning dimensions using measured benchmark results and conservative estimates for missing coverage.
How much does mercury-2 cost?: mercury-2 costs $0.25 per million input tokens and $0.75 per million output tokens. Adjusted for how many tokens it actually consumes on real tasks, its effective cost works out to $0.8491 per million input-plus-output tokens.
Is mercury-2 open source?: No — mercury-2 is a proprietary model. Its weights are not publicly available, so it is used through hosted APIs and products.
When was mercury-2 released?: mercury-2 was publicly released on February 24, 2026.
How large is the context window of mercury-2?: mercury-2 supports a context window of 128,000 tokens — the amount of text it can consider in a single request.
How fast is mercury-2?: In independent measurements, mercury-2 generates about 1076 tokens per second, with a typical response time of about 5.5 seconds.