Source-labeled benchmark reference

AI model and company signals, clearly sourced.

CyberOGZ organizes model benchmarks, company data, market signals and metadata in one place so readers can compare sources faster and spot what still needs verification before making decisions.

Admin database Updated Aug 28, 2026 Company radar
Use every row as a source-labeled signal. Model scores shown here come from labeled external sources; CyberOGZ does not calculate or override the score. See how ›
AI company radar

Companies shaping the AI stack.

Public market signals, private AI lab profiles, and provider news are source-labeled when API-synced.

23Public 5Private labs 28API synced
NVIDIA Corp logo NV

NVIDIA Corp

NVDA | Technology
Public

GPU acceleration, CUDA ecosystem, data center AI infrastructure

Market signal $217.55 -4.58% today
NASDAQ NMS - GLOBAL MARKETExchange 250Provider news USRegion
$217.55Price -4.58%Move $5.5TMarket cap
Latest signal Nvidia Just Validated Micron's Biggest AI Bull Case
Provider data: Finnhub Synced Aug 28 Source
Microsoft Corp logo MI

Microsoft Corp

MSFT | Technology
Public

Azure AI infrastructure, Copilot distribution, OpenAI partnership

Market signal $513.53 +1.68% today
NASDAQ NMS - GLOBAL MARKETExchange 250Provider news Global / USRegion
$513.53Price +1.68%Move $3.8TMarket cap
Latest signal Microsoft: The Rerating Is Probably Over For Now (Rating Downgrade)
Provider data: Finnhub Synced Aug 28 Source
Arm Holdings PLC logo AR

Arm Holdings PLC

ARM | Technology
Public

CPU architecture and low-power AI device ecosystem

Market signal $239.05 -6.33% today
NASDAQ NMS - GLOBAL MARKETExchange 157Provider news EuropeRegion
$239.05Price -6.33%Move $272.6BMarket cap
Latest signal Why Is Arm Stock Surging on Thursday?
Provider data: Finnhub Synced Aug 28 Source
Alibaba Group Holding Ltd logo AL

Alibaba Group Holding Ltd

BABA | Consumer Cyclical
Public

Alibaba Cloud, Qwen models and commerce AI workflows

NEW YORK STOCK EXCHANGE, INC.Exchange 72Provider news China / AsiaRegion
+2.23%Move
Latest signal Alibaba: Three-Year AI CapEx Payback Period Silence Bears
Provider data: Finnhub Synced Aug 28 Source
Tesla Inc logo TE

Tesla Inc

TSLA | Consumer Cyclical
Public

Autonomy, robotics, inference compute and fleet data

Market signal $348.75 -1.71% today
NASDAQ NMS - GLOBAL MARKETExchange 250Provider news Global / USRegion
$348.75Price -1.71%Move $1.4TMarket cap
Latest signal Tesla: Autonomous Monetization Begins, But Not Priced In Yet
Provider data: Finnhub Synced Aug 28 Source
Meta Platforms Inc logo ME

Meta Platforms Inc

META | Communication Services
Public

Llama models, recommendation systems and AI products

Market signal $578.02 +1.21% today
NASDAQ NMS - GLOBAL MARKETExchange 250Provider news Global / USRegion
$578.02Price +1.21%Move $1.5TMarket cap
Latest signal Meta Platforms Beats The Man, Again - We Move To Accumulate Rating
Provider data: Finnhub Synced Aug 28 Source
Broadcom Inc logo BR

Broadcom Inc

AVGO | Technology
Public

Networking silicon and custom AI accelerator supply chain

Market signal $368.79 -0.74% today
NASDAQ NMS - GLOBAL MARKETExchange 250Provider news Global / USRegion
$368.79Price -0.74%Move $1.8TMarket cap
Latest signal Broadcom: I Am Hedging Before Q3, You Should Too
Provider data: Finnhub Synced Aug 28 Source
Oracle Corp logo OR

Oracle Corp

ORCL | Technology
Public

OCI GPU clusters, enterprise AI workloads and database AI

Market signal $150.85 -0.72% today
NEW YORK STOCK EXCHANGE, INC.Exchange 249Provider news Global / USRegion
$150.85Price -0.72%Move $439.7BMarket cap
Latest signal Nvidia Crushed Earnings: Doubling My Oracle Position
Provider data: Finnhub Synced Aug 28 Source
Perplexity logo PE

Perplexity

Private | Artificial Intelligence
Private

Perplexity AI unlocks the power of knowledge with information discovery and sharing.

Global / USRegion
Provider data: Brandfetch Logo Synced Aug 28 Source
xAI logo XA

xAI

Private | Artificial Intelligence
Private

xAI is a company working on building artificial intelligence to accelerate human scientific discovery. We are guided by our mission to advance our collective understanding of the universe.

Global / USRegion
Provider data: Brandfetch Logo Synced Aug 28 Source
Explore benchmark insights Source rankings, available benchmark breakdowns and release dates
Top performers

Top 10 Artificial Analysis LLM Intelligence rows

US / Global Europe China & Asia
  1. #1 Claude Opus 5 (Adaptive Reasoning, Max Effort) Anthropic 63.1
  2. #2 Claude Opus 5 (Adaptive Reasoning, Xhigh Effort) Anthropic 62.5
  3. #3 Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback) Anthropic 62.1
  4. #4 Claude Opus 5 (Adaptive Reasoning, High Effort) Anthropic 61.5
  5. #5 GPT-5.6 Sol (max) OpenAI 60.9
  6. #6 Grok 4.6 (high) SpaceXAI 60.9
  7. #7 Grok 4.6 (xhigh) SpaceXAI 60
  8. #8 Kimi K3 (max) Kimi 59.7
  9. #9 GLM-5.3 (max) Z AI 59.5
  10. #10 GPT-5.6 Sol (xhigh) OpenAI 59
Humanity's Last Exam

Top 8 Hugging Face HLE submissions

Standard HLE model-card results from the CAIS/HLE leaderboard. Hugging Face currently marks these submissions as unverified; tool-assisted variants are excluded.

HLE % correct
  1. #1 GLM-5.3 zai-org · Unverified model card 62.5%
  2. #2 Kimi-K3 moonshotai · Unverified model card 56%
  3. #3 GLM-5.2 zai-org · Unverified model card 54.7%
  4. #4 Hy3 tencent · Unverified model card 53.2%
  5. #5 MiMo-V2.5-Pro XiaomiMiMo · Unverified model card 48%
  6. #6 Inkling thinkingmachines · Unverified model card 46%
  7. #7 Qwen3.8-2.4T-A95B Qwen · Unverified model card 43.6%
  8. #8 DeepSeek-V4-Pro deepseek-ai · Unverified model card 37.7%
Release race

2026 model releases - through August

Each dot marks a source-provided release date. Hover, focus or tap for the model name.

2026 · 50 releases
Jan Feb Mar Apr May Jun Jul Aug
Anthropic
OpenAI
SpaceXAI
Kimi
Z AI
Alibaba
Meta
Region
Type
Model Score Coding Speed Input Output Source
Anthropic Claude Opus 5 (Adaptive Reasoning, Max Effort) General
63.1 source-backed 78 55.38 tok/s $5 $25 Artificial Analysis
Anthropic Claude Opus 5 (Adaptive Reasoning, Xhigh Effort) General
62.5 source-backed 77 53.69 tok/s $5 $25 Artificial Analysis
Anthropic Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback) General
62.1 source-backed 76.5 64.86 tok/s $10 $50 Artificial Analysis
Anthropic Claude Opus 5 (Adaptive Reasoning, High Effort) General
61.5 source-backed 76.5 54.39 tok/s $5 $25 Artificial Analysis
OpenAI GPT-5.6 Sol (max) General
60.9 source-backed 77.4 70.29 tok/s $4 $20 Artificial Analysis
SpaceXAI Grok 4.6 (high) General
60.9 source-backed 76.8 57.75 tok/s $2 $6 Artificial Analysis
SpaceXAI Grok 4.6 (xhigh) General
60 source-backed 75.9 59.56 tok/s $2 $6 Artificial Analysis
Kimi Kimi K3 (max) General
China
59.7 source-backed 76.2 38.46 tok/s $3 $15 Artificial Analysis
Z AI GLM-5.3 (max) General
China
59.5 source-backed 74.8 76.6 tok/s $1.4 $4.4 Artificial Analysis
OpenAI GPT-5.6 Sol (xhigh) General
59 source-backed 78.3 72.92 tok/s $4 $20 Artificial Analysis
SpaceXAI Grok 4.6 (medium) General
59 source-backed 74.4 57.37 tok/s $2 $6 Artificial Analysis
Anthropic Claude Opus 5 (Adaptive Reasoning, Medium Effort) General
58.6 source-backed 74.3 53.76 tok/s $5 $25 Artificial Analysis
Alibaba Qwen3.8 Max General
China
58.1 source-backed 71.8 20.69 tok/s $2 $6 Artificial Analysis
Alibaba Qwen3.8 2.4T A95B General
China
57.7 source-backed 71.9 24.11 tok/s $2 $6 Artificial Analysis
Z AI GLM-5.3-Flash General
China
57.5 source-backed 71.5 50.23 tok/s $0.15 $0.5 Artificial Analysis
OpenAI GPT-5.6 Sol (high) General
57.3 source-backed 77.2 74.79 tok/s $4 $20 Artificial Analysis
Anthropic Claude Opus 4.8 (Adaptive Reasoning, Max Effort) General
57.3 source-backed 74.3 58.45 tok/s $5 $25 Artificial Analysis
Meta Muse Spark 1.2 (xhigh) General
56.8 source-backed 72.2 n/a $1.25 $4.25 Artificial Analysis
OpenAI GPT-5.6 Terra (max) General
56.6 source-backed 76.7 107.72 tok/s $2 $12 Artificial Analysis
OpenAI GPT-5.5 (xhigh) General
56.3 source-backed 74.9 80.72 tok/s $5 $30 Artificial Analysis
Google Gemini 3.7 Flash (high) General
56 source-backed 76.1 321.92 tok/s $0.75 $3.75 Artificial Analysis
Alibaba Qwen3.8-Flash-Next General
China
55.8 source-backed 73.1 73.33 tok/s $0.15 $0.47 Artificial Analysis
SpaceXAI Grok 4.5 (high) General
55.8 source-backed 72.4 51.83 tok/s $2 $6 Artificial Analysis
OpenAI GPT-5.6 Sol (medium) General
55.6 source-backed 76.3 72.69 tok/s $4 $20 Artificial Analysis
Anthropic Claude Sonnet 5 (Adaptive Reasoning, Max Effort) General
55.3 source-backed 71.5 94.92 tok/s $2 $10 Artificial Analysis
Anthropic Claude Opus 4.7 (Adaptive Reasoning, Max Effort) General
55 source-backed 73.6 50.93 tok/s $5 $25 Artificial Analysis
OpenAI GPT-5.5 (high) General
54.7 source-backed 71.6 76.16 tok/s $5 $30 Artificial Analysis
Google Gemini 3.7 Flash (medium) General
53.4 source-backed 71.5 318.23 tok/s $0.75 $3.75 Artificial Analysis
Meta Muse Spark 1.1 (xhigh) General
53.2 source-backed 71.3 205.07 tok/s $1.25 $4.25 Artificial Analysis
DeepSeek DeepSeek V4 Pro 0813 (Reasoning, Max Effort) General
China
53.2 source-backed 68.8 66.33 tok/s $1.32 $3.96 Artificial Analysis
OpenAI GPT-5.4 (xhigh) General
53.1 source-backed 71.1 130.35 tok/s $2.5 $15 Artificial Analysis
OpenAI GPT-5.6 Terra (xhigh) General
52.8 source-backed 70.6 104.88 tok/s $2 $12 Artificial Analysis
Z AI GLM-5.2 (max) General
China
52.6 source-backed 68.8 71.16 tok/s $1.4 $4.4 Artificial Analysis
Anthropic Claude Opus 5 (Adaptive Reasoning, Low Effort) General
52.5 source-backed 66.9 55.01 tok/s $5 $25 Artificial Analysis
OpenAI GPT-5.6 Luna (max) General
52.3 source-backed 71.4 126.22 tok/s $0.2 $1.2 Artificial Analysis
Google Gemini 3.5 Flash (high) General
52 source-backed 70.1 197.42 tok/s $1.5 $9 Artificial Analysis
Alibaba Qwen3.8 27B (xhigh) General
China
52 source-backed 68.1 46.73 tok/s $0.5 $3 Artificial Analysis
DeepSeek DeepSeek V4 Flash 0731 (Reasoning, Max Effort) General
China
51.8 source-backed 69.1 119.38 tok/s $0.44 $1.32 Artificial Analysis
SpaceXAI Grok 4.6 (low) General
51.7 source-backed 66.3 55.37 tok/s $2 $6 Artificial Analysis
Google Gemini 3.6 Flash (high) General
51.6 source-backed 69.2 173.13 tok/s $0.75 $3.75 Artificial Analysis
DeepSeek DeepSeek V4 Flash Vision (Reasoning, Max Effort) General
China
51.5 source-backed 65 119.13 tok/s $0.44 $1.32 Artificial Analysis
OpenAI GPT-5.5 (medium) General
51.4 source-backed 71.5 82.76 tok/s $5 $30 Artificial Analysis
Google Gemini 3.7 Flash (low) General
50.9 source-backed 71 319.58 tok/s $0.75 $3.75 Artificial Analysis
OpenAI GPT-5.6 Sol (low) General
50.7 source-backed 69.7 73.72 tok/s $4 $20 Artificial Analysis
OpenAI GPT-5.6 Luna (xhigh) General
50.1 source-backed 68.6 115.36 tok/s $0.2 $1.2 Artificial Analysis
OpenAI GPT-5.6 Terra (high) General
50.1 source-backed 67.1 103.9 tok/s $2 $12 Artificial Analysis
Sapiens AI Agnes 2.5 Pro Beta General
49.1 source-backed 62.3 159.32 tok/s $0.1 $0.3 Artificial Analysis
Anthropic Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort) General
48.4 source-backed 63 56.78 tok/s $3 $15 Artificial Analysis
Kimi Kimi K3 (low) General
China
48.3 source-backed 72 36.3 tok/s $3 $15 Artificial Analysis
Google Gemini 3.1 Pro Preview General
47.7 source-backed 68.8 115.16 tok/s $2 $12 Artificial Analysis
How to read the index

What affects it

Score imported/admin value Coding source-specific coding metric Reasoning source-specific reasoning metric Speed throughput or latency signal Context provider/API metadata Price provider/API pricing metadata

The index gives more weight to broad model quality, then includes coding, reasoning, speed, context and price efficiency. Treat close numbers as directional rather than absolute.

Overall is not a claim that one model is universally better than another. It is a compact reading aid for CyberOGZ readers, based on imported benchmark, speed, context and pricing signals at the time the data was added.

Use it to scan the field quickly, then compare the specific columns and source notes for the task you care about. A lower-index model can still be the better choice for a specific workflow.

Data sources and confidence

The benchmark feed can come from API-backed sources, imported JSON, and admin-reviewed manual rows. Each row has a source and confidence value. Higher confidence means the row is based on a clearer external source or a cleaner imported feed.

If a model has only metadata but no trusted benchmark data, it should stay inactive or metadata-only in admin. That prevents unscored models from polluting the benchmark lists.

How to read this: Score and ranking come from the linked benchmark source. Speed is source-reported throughput, not a CyberOGZ rating. Missing API fields stay unavailable.