readable AI benchmarks

Sapiens AI

Agnes 2.5 Pro Alpha

reasoning · closed weights · Jul 24, 2026

Quality Score41.1
Value Score40.2
Reliability37.5
Cache Discount99%

Model specification

Reasoning
reasoning
Input modalities
text, image, video
Output modalities
text
Context window
1M tokens
Weights
closed weights

Token prices USD per 1M tokens

Input
$0.450
Output
$0.900
Cached Input
$0.0038
Cached Output
not available
Cost per task
not available

Capability

Intelligence
39.7
Coding
58.8
Agentic
25.4
Omniscience
-25.1
Correct
33.5%
Blended price
$0.183

Answer outcomes

Correct 33.5%Incorrect 58.6%Abstained 7.9%

Artificial Analysis benchmarks

GDPval-AA v2
34%
τ³-Banking
12%
Terminal-Bench v2.1
67%
SciCode
42%
Humanity’s Last Exam
34%
GPQA Diamond
88%
CritPt
11%
AA-Omniscience
37%
AA-LCR
73%

Similar models