Back

Inception

Mercury 2.5

ReasoningClosed weightsModels.dev
Intelligence
12.3
Rank 369 of 744 measured models
Output speed
594 t/s
Rank 2 of 403 measured models
Price/1M
$0.375
Rank 227 of 659 measured models
Context window
260K
Rank 516 of 1199 measured models
Cost per task
$0.117
Rank 56 of 193 measured models

Mercury 2.5 scores 12.3 on the Artificial Analysis Intelligence Index, ranking 369th of 744 measured models. The closest models on this index are Gemini 2.5 Flash Preview (Sep '25) (12.4), o1-pro (12.4), and JT-MINI (12.2). At $0.375 per million tokens (3:1 input/output blended price), it is cheaper than o1-pro ($262.50).

Artificial Analysis Indices
Intelligence12.3
Rank 369 of 744 measured models
Capability indexes
Performance in specific industries, measured by Artificial Analysis
Finance & Accounting11.2
Rank 178 of 218 measured models
Strategy & Ops8.2
Rank 176 of 218 measured models
Legal12.9
Rank 180 of 218 measured models
Engineering15.6
Rank 181 of 217 measured models
Economics18.0
Rank 189 of 225 measured models
Standard Benchmarks
HLE11.8%
Rank 299 of 664 measured models
SciCode38.5%
Rank 185 of 231 measured models
AA-LCR71.7%
Rank 200 of 575 measured models
Terminal-Bench v40.0%
Rank 151 of 218 measured models
Models at a similar level
The closest models on the Intelligence Index, one configuration per family.

Preferences and analytics

Rybbit: visits, performance, clicks, copies, forms and session replay (masked inputs), with your permission. Refusing does not limit the site.

Privacy

Allow navigation analytics?

With your permission, Rybbit measures visits, performance and interactions (clicks, copies, forms), including session replay, to improve BenchSift. Input values are masked in replays. Refusing does not limit the site.

Your choice is stored for 180 days. Change it at any time using “Privacy preferences” in the footer. Withdrawal reloads the page.

No choice stored: Rybbit is disabled.

Privacy