readable AI benchmarks (simplified)

updated on: Nov 5, 2026, 6:37 AM UTC · 775 models

readable AI benchmarks

Tencent

Tencent Hy4

reasoning · closed weights · Nov 4, 2026

Tencent Hy4 has a Quality Score of 43.6, ranking 74th among 235 scored models. It accepts text and image input, outputs text, and has a 1,048,576 token context window. Its Reliability Score is 52.7, ranking 85th among 242 scored models, above average (total average: 46.3).

Quality Score43.6coverage 100.0%: AA Intelligence and AA-Omniscience outcomes available
Value Scorenot available
Factual reliability52.7
Cache Discountnot available

Model specification

Reasoning
reasoning
Input modalities
text, image
Output modalities
text
Context window
1,048,576 tokens
Weights
closed weights

Token prices USD per 1M tokens

Input
not available
Output
not available
Cached Input
not available
Cache write
not available
Cost per task
not available

Capability

Intelligence
34.6
Omniscience (native net)
5.4
Correct
50.0%
Blended price
not available

Answer outcomes

Fully graded outcomes (Correct + Incorrect): 94.5%

Correct 50.0%Incorrect 44.6%Partial / not attempted 5.5%

Artificial Analysis benchmarks aa-v5

Current Intelligence Index components

AA-Briefcase v1.1
1446.5 Elo
AutomationBench-AA
65.6%
private 657-task split from dataset v1.0.6
GDP.pdf
21.6%
FrontierCode v2.0
31.4%
AA Stirrup · 132 tasks, 3 attempts per task
Terminal-Bench v4.0
37.4%
AA mini-swe-agent standardized runs · 66 tasks, pass@1 averaged over 3 repeats per task
AA-Omniscience v1.1
5.4 native net
HLE-Diamond
32.7%
CritPt v2 Hard
39.0%
AA Stirrup · hard subset, 40 of 70 problems
Terminal-Bench-Science v0.1.0
12.9%

Similar models

GraphOpen on Artificial Analysis

Support me! Patreon