AI Benchmarks Compared

611 articles · Page 1 of 31
AI model benchmarks are the foundation of model selection. Major benchmarks include MMLU, HumanEval, Chatbot Arena (LMSYS), SuperCLUE, and OpenCompass — but most rely on multiple-choice or model-as-judge approaches that cannot detect real execution capability or hallucination risks. The YZ Index is an independent third-party benchmark featuring real code sandbox execution, 42-probe integrity rating for hallucination detection, and the WDCD (Winzheng Dynamic Contextual Decay) test measuring instruction compliance decay over multi-turn dialogue. This topic compares benchmark methodologies, tracks ranking changes, and provides in-depth analysis.

In-depth Guides

Review Doubao Pro Code Execution Plummets 26.2 Points, Main Leaderboard Rises Only 0.03 Points
In today’s Smoke evaluation, Doubao Pro’s code execution score fell 26.2 points to 48.80, while its material constraint score rose 32.1 points to 100.
Nov 19, 2026
Review GPT-o3 Material Constraint Plunges 16.7 Points, Code Execution Gains 23.8, Main Leaderboard Rises 5.6
In today's Smoke evaluation, GPT-o3's material constraint score fell from 100.00 to 83.30 while code execution rose from 50.00 to 73.80, lifting the m
Nov 19, 2026
Review GPT-6 Sol Leads with 80.54 Points: 2026-11-19 Smoke Quick Test Data Brief
The 2026-11-19 YZ Index Smoke Quick Test covered 13 models, with GPT-6 Sol ranking first at 80.54. The single-day small-sample results highlight short
Nov 19, 2026
Astra for Law Tops Legal AI Benchmark with 20.8% Full-Pass Rate
OpenAI's Astra for Law 6.2 achieved a 20.8% full-task pass rate on Harvey LAB-AA v1.1, ranking first among evaluated models, while the general-purpose
Nov 18, 2026
Review GLM-4.6 Tops WDCD Constraint Adherence Leaderboard with 88.6 Points, Doubao Pro Bottom at 65.4
GLM-4.6 ranks first on the WDCD v3.1 constraint adherence leaderboard with 88.60 points, while Doubao Pro finishes last at 65.40 points, with a 23.2-p
Nov 18, 2026
Review GPT-5.5 Code Execution Plunges 24.8 Points; Main Leaderboard Drops Only 2.8 Points
In today's Smoke evaluation, GPT-5.5's code execution score fell from 99.80 to 75.00, a 24.8-point drop, while its overall main leaderboard score decl
Nov 18, 2026
Review GPT-6 Luna Code Execution Plunges 24.1 Points as Material Constraint Climbs 32
In today's Smoke evaluation, GPT-6 Luna's code execution score fell from 99.10 to 75.00 while its material constraint score rose from 62.80 to 94.80,
Nov 18, 2026
Review GPT-6 Astra Tops with 91.14 Points: 2026-11-18 Smoke Quick Test Data Brief
The 2026-11-18 YZ Index Smoke quick test covered 14 models, with GPT-6 Astra ranking first at 91.14 points. As a daily 10-question quick test covering
Nov 18, 2026
Review GPT-6 Luna Tops the List with 82.77 Points: 2026-11-17 Smoke Quick-Test Data Brief
The 2026-11-17 YZ Index Smoke quick test covered 14 models, with GPT-6 Luna ranking first for the day at 82.77 points. The Smoke test is a daily 10-qu
Nov 17, 2026
Lab Four-Model Translation Showdown: Week 47 Quality Review, claude-sonnet-4.6 Leads with 9 Points
This week 442 translation tasks were completed by 4 models, with 3 sampled for a multi-model blind evaluation. Best overall: claude-sonnet-4.6 (averag
Nov 16, 2026
Review GPT-6.1 Sol Code Execution Plunges 27.3 Points as Overall Ranking Slips to 78.69
In today's Smoke evaluation, GPT-6.1 Sol's code execution score fell from 97.30 to 70.00, dragging its overall ranking down from 84.70 to 78.69. The d
Nov 16, 2026
Review GPT-6 Astra Code Execution Plunges 27.3 Points as Main Leaderboard Falls from 84.70 to 78.69
In today's Smoke evaluation, GPT-6 Astra's code execution score dropped from 97.30 to 70.00, pulling the main leaderboard down from 84.70 to 78.69, wh
Nov 16, 2026
Review GPT-5.5 and GPT-6 Sol Tie at 92.44 Points: 2026-11-16 Smoke Quick Test Data Brief
The 2026-11-16 YZ Index Smoke quick test covered 14 models, with GPT-5.5 and GPT-6 Sol tied for first at 92.44 points. The single-day results are usef
Nov 16, 2026
Review Claude Opus 4.7 Code Execution Drops 19.5 Points as Material Constraints Rise 19.3 Points
In today's Smoke evaluation, Claude Opus 4.7's code execution score fell 19.5 points while its material constraints score rose 19.3 points, leaving th
Nov 15, 2026
Review GPT-5.5 Trends Up 10 Points, Gemini 2.5 Pro Drops 30.9 Points: 2026-W46 Weekly Data Analysis
Smoke evaluation data from November 9–15, 2026 shows GPT-5.5 rising from 78.74 on the first day to 88.75 on the last, with a trend value of +10, makin
Nov 15, 2026
Review Claude Sonnet 4.6 and GPT-6 Luna Tie at 95.19 Points: 2026-11-15 Smoke Quick Test Data Brief
The 2026-11-15 YZ Index Smoke quick test covered 13 models, with Claude Sonnet 4.6 and GPT-6 Luna tied at 95.19 points for the daily lead. Smoke is a
Nov 15, 2026
Review Claude Sonnet 4.6 Smoke Evaluation Main Leaderboard Plunges 11.7 Points; Material Constraint Falls 19.9 in a Single Day
In today's Smoke evaluation, Claude Sonnet 4.6's main leaderboard score dropped from 82.31 to 70.61, a decline of 11.7 points. The material constraint
Nov 14, 2026
Review Claude Opus 4.7 Main Leaderboard Plunges 11.4 Points, Material Constraint Drops 19.3 in a Single Day
Claude Opus 4.7's main leaderboard score fell from 94.91 to 83.48 in today's Smoke evaluation, a drop of 11.4 points, while the material constraint di
Nov 14, 2026
Review Claude Opus 4.7 Leads with 83.48 Points: 2026-11-14 Smoke Quick Test Data Brief
The 2026-11-14 YZ Index Smoke Quick Test covered 13 models, with Claude Opus 4.7 ranking first at 83.48 points. As a daily 10-question quick test, Smo
Nov 14, 2026
Review Claude Opus 4.7 Leads at 94.91: 2026-11-13 Smoke Quick Test Data Brief
The 2026-11-13 YZ Index Smoke quick test covered 13 models, with Claude Opus 4.7 taking the top spot for the day at 94.91 points on a main leaderboard
Nov 13, 2026