readable AI benchmarks (simplified)

readable AI benchmarks

Inception

Mercury 2.5

reasoning · closed weights · Sep 8, 2026

Mercury 2.5 has a Quality Score of 24.6, ranking 313th among 551 scored models. Per 1M tokens, pricing is $0.250 input, $0.750 output, and $0.025 cached input. It has a 260k token context window. Its Reliability Score is 30.3, ranking 302nd among 553 scored models, below average (total average: 35.6). Its Value Score is 21.4, low compared with the total Value average of 30.7.

Quality Score24.6coverage 100.0%: AA Intelligence and AA-Omniscience outcomes available
Value Score21.4
Factual reliability30.3
Cache Discount90%

Model specification

Reasoning
reasoning
Input modalities
none
Output modalities
none
Context window
260k tokens
Weights
closed weights

Token prices USD per 1M tokens

Input
$0.250
Output
$0.750
Cached Input
$0.025
Cache write
not available
Cost per task
$0.064

Capability

Intelligence
12.3
Coding
not available
Agentic
not available
Omniscience
-39.5
Correct
22.7%
Blended price
$0.143

Answer outcomes

Fully graded outcomes (Correct + Incorrect): 84.8%

Correct 22.7%Incorrect 62.1%Partial / not attempted 15.2%

Artificial Analysis benchmarks

GDPval-AA v2
0%
SciCode
39%
Humanity’s Last Exam
12%
CritPt
0%
AA-Omniscience
30%
AA-LCR
72%

Similar models

Support me! Patreon