88Z.ai / RANKINGS
AI model leaderboard 2026
Public evaluations, compiled into verifiable boards. The composite method is public, and missing scores are not filled with zeros.
Last collected by this site: 2026-11-14 06:41 (UTC+8, Asia/Shanghai). Source publication dates are in the table or the citations below.
This board is for people comparing the strongest AI models in 2026: start with the overall list, then use the coding, reasoning, Chinese, vision, generation, open-source, value and speed boards.
Overall
A weighted composite of public benchmarks. Missing scores are omitted and weights are renormalized; they are never filled with zeros.
Coding
Covers coding battles, software-engineering repair, polyglot editing and the LiveBench coding suite.
Reasoning & math
Led by the LiveBench reasoning suite, LMArena math battles and SuperCLUE math-reasoning scores.
Chinese
Centered on SuperCLUE’s general board and LMArena Chinese battles, reflecting relative performance in Chinese-language use.
Vision
LMArena Vision Arena (style-controlled) overall board.
Image generation
LMArena Text-to-Image Arena overall board.
Video generation
LMArena Text-to-Video Arena overall board.
Open source
Models marked open-source or non-proprietary in the source data, ranked with the same composite method. License labels follow the original sources.
Price / value
Quality versus our CNY list price when available, or Artificial Analysis’s published cost per task. Prices and benchmark scores come from different sources and should be read separately.
Speed
Based on Artificial Analysis time-per-task and first-token latency; lower times rank higher.
Arena popularity
Ranked by LMArena Text Arena battle counts. This is not this site’s usage, and it is not a quality score.
Comparisons：Claude vs GPT · DeepSeek vs Qwen · Gemini vs Claude · Grok vs GPT · Methodology
Overall top 20
Coding snapshot
Chinese snapshot
Sources
- LMArena Text Arena (style-controlled) — Official Arena leaderboard dataset, text_style_control / latest. Scores are Arena ratings (Bradley-Terry).
- LMArena WebDev Arena — Official webdev / latest snapshot, measuring front-end and web-app battles.
- LMArena Vision Arena (style-controlled) — Official vision_style_control / latest snapshot.
- LMArena Text-to-Image Arena — Official text_to_image / latest snapshot.
- LMArena Text-to-Video Arena — Official text_to_video / latest snapshot.
- LMArena Agent Arena — Official agent / latest aggregate scores.
- Artificial Analysis Intelligence Index — Intelligence Index, cost per task, time per task and first-token latency from the official public leaderboard page.
- LiveBench 2.0 — Official CSV results. Overall uses the published formula: Long Agentic ×2, Design ×1.5, Coding ×1.5, other suites ×1, then a weighted mean over suites that have a score.
- Aider Polyglot — Official polyglot_leaderboard.yml. The metric is pass_rate_2 on 225 cross-language exercises. Repeated submissions keep the best score.
- SWE-bench Verified (mini-SWE-agent) — Official leaderboards.json, Verified board, resolved % under the mini-SWE-agent protocol so models are compared in a similar scaffold. Scores from other agents are not mixed into the composite coding score.
- SuperCLUE Chinese general board — Total and section scores from the official monthly general-board spreadsheet.
FAQ
- Where do these scores come from?
- Every score comes from a public benchmark or official machine-readable file, with a source link and date. This site does not invent scores, and missing values are not treated as zero.
- How is the overall score calculated?
- Each source is min-max normalized within itself, then weighted: Artificial Analysis 28%, LMArena Text Arena 28%, LiveBench 22%, coding composite 15%, reasoning composite 7%. Missing sources are dropped and the rest are renormalized. A model needs at least two headline sources (or three partials) to enter the overall board. When several variants of one family exist, only the best overall variant is shown.
- Are site prices part of the benchmarks?
- No. Benchmark scores come from third-party public boards. CNY prices are this site’s catalogue reference rates (CNY 1 = 1,000 points) and are settled on actual usage. They are shown separately so billing is not confused with quality.
- How often is this updated?
- A collector runs automatically every day. The upstream boards may not publish a new snapshot daily, so each page shows both this site’s collection time and the source publication date.