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.
Companies shaping the AI stack.
Public market signals, private AI lab profiles, and provider news are source-labeled when API-synced.
NVIDIA Corp
NVDA | TechnologyGPU acceleration, CUDA ecosystem, data center AI infrastructure
Microsoft Corp
MSFT | TechnologyAzure AI infrastructure, Copilot distribution, OpenAI partnership
Alphabet Inc
GOOGL | Communication ServicesGemini, TPU infrastructure, Search and Workspace AI integration
ASML Holding NV
ASML | TechnologyEUV lithography and advanced chip manufacturing supply chain
Arm Holdings PLC
ARM | TechnologyCPU architecture and low-power AI device ecosystem
Anthropic
Private | Artificial IntelligenceWe're an AI research company that builds reliable, interpretable, and steerable AI systems. Our first product is Claude, an AI assistant for tasks at any scale.
Taiwan Semiconductor Manufacturing Co Ltd
TSM | TechnologyAdvanced AI chip manufacturing and foundry capacity
Alibaba Group Holding Ltd
BABA | Consumer CyclicalAlibaba Cloud, Qwen models and commerce AI workflows
Tencent Holdings Ltd
TCEHY | Communication ServicesCloud AI, gaming, social platforms and model ecosystem
OpenAI
Private | Artificial IntelligenceOpenAI is an AI research and deployment company dedicated to ensuring that general-purpose artificial intelligence benefits all of humanity.
Apple Inc
AAPL | TechnologyOn-device AI, silicon, ecosystem distribution
Advanced Micro Devices Inc
AMD | TechnologyAI accelerators, CPUs, GPUs and data center compute
Intel Corp
INTC | TechnologyCPUs, AI PCs, accelerators and foundry strategy
Tesla Inc
TSLA | Consumer CyclicalAutonomy, robotics, inference compute and fleet data
Meta Platforms Inc
META | Communication ServicesLlama models, recommendation systems and AI products
Amazon.com Inc
AMZN | Consumer CyclicalAWS AI infrastructure, Bedrock, Trainium and retail AI
Broadcom Inc
AVGO | TechnologyNetworking silicon and custom AI accelerator supply chain
Oracle Corp
ORCL | TechnologyOCI GPU clusters, enterprise AI workloads and database AI
SAP SE
SAP | TechnologyEnterprise AI, business applications and data workflows
STMicroelectronics NV
STM | TechnologyIndustrial, automotive and edge-device semiconductor supply
Infineon Technologies AG
IFNNY | TechnologyPower, automotive and industrial chips supporting AI infrastructure
Siemens AG
SIEGY | IndustrialsIndustrial AI, automation software and digital twin systems
Baidu Inc
BIDU | Communication ServicesERNIE models, AI cloud and autonomous driving systems
Lenovo Group Ltd
LNVGY | TechnologyAI PCs, edge devices and enterprise hardware distribution
Samsung Electronics Co Ltd
SSNLF | TechnologyMemory, edge devices, mobile AI and semiconductor supply chain
Perplexity
Private | Artificial IntelligencePerplexity AI unlocks the power of knowledge with information discovery and sharing.
Mistral AI
Private | Artificial IntelligenceThe most powerful AI platform for enterprises. Customize, fine-tune, and deploy AI assistants, autonomous agents, and multimodal AI with open models.
xAI
Private | Artificial IntelligencexAI 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.
Explore benchmark insights Source rankings, available benchmark breakdowns and release dates
Top 10 Artificial Analysis LLM Intelligence rows
- #1 Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback) Anthropic 59.9
- #2 GPT-5.6 Sol (max) OpenAI 58.9
- #3 GPT-5.6 Sol (xhigh) OpenAI 57.7
- #4 GPT-5.6 Sol (high) OpenAI 55.9
- #5 Claude Opus 4.8 (Adaptive Reasoning, Max Effort) Anthropic 55.7
- #6 GPT-5.6 Terra (max) OpenAI 55
- #7 GPT-5.5 (xhigh) OpenAI 54.8
- #8 Grok 4.5 (high) SpaceXAI 53.8
- #9 GPT-5.6 Sol (medium) OpenAI 53.6
- #10 Claude Opus 4.7 (Adaptive Reasoning, Max Effort) Anthropic 53.5
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.
- #1 GLM-5.2 zai-org · Unverified model card 54.7%
- #2 Hy3 tencent · Unverified model card 53.2%
- #3 MiMo-V2.5-Pro XiaomiMiMo · Unverified model card 48%
- #4 DeepSeek-V4-Pro deepseek-ai · Unverified model card 37.7%
- #5 DeepSeek-V4-Flash deepseek-ai · Unverified model card 34.8%
- #6 Kimi-K2.6 moonshotai · Unverified model card 34.7%
- #7 OpenSeeker-v2-30B-SFT PolarSeeker · Unverified model card 34.6%
- #8 GLM-5.1 zai-org · Unverified model card 31%
2026 model releases - through July
Each dot marks a source-provided release date. Hover, focus or tap for the model name.
| Model | Score | Coding | Speed | Input | Output | Source |
|---|---|---|---|---|---|---|
|
Anthropic Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)
General
|
59.9 source-backed | 76.5 | 60.31 tok/s | $10 | $50 | Artificial Analysis |
|
OpenAI GPT-5.6 Sol (max)
General
|
58.9 source-backed | 77.4 | 66.12 tok/s | $5 | $30 | Artificial Analysis |
|
OpenAI GPT-5.6 Sol (xhigh)
General
|
57.7 source-backed | 78.3 | 64.35 tok/s | $5 | $30 | Artificial Analysis |
|
OpenAI GPT-5.6 Sol (high)
General
|
55.9 source-backed | 77.2 | 60.73 tok/s | $5 | $30 | Artificial Analysis |
|
Anthropic Claude Opus 4.8 (Adaptive Reasoning, Max Effort)
General
|
55.7 source-backed | 74.3 | 54.45 tok/s | $5 | $25 | Artificial Analysis |
|
OpenAI GPT-5.6 Terra (max)
General
|
55 source-backed | 76.7 | 137.3 tok/s | $2.5 | $15 | Artificial Analysis |
|
OpenAI GPT-5.5 (xhigh)
General
|
54.8 source-backed | 74.9 | 75.85 tok/s | $5 | $30 | Artificial Analysis |
|
SpaceXAI Grok 4.5 (high)
General
|
53.8 source-backed | 72.4 | 112.66 tok/s | $2 | $6 | Artificial Analysis |
|
OpenAI GPT-5.6 Sol (medium)
General
|
53.6 source-backed | 76.3 | 56.67 tok/s | $5 | $30 | Artificial Analysis |
|
Anthropic Claude Opus 4.7 (Adaptive Reasoning, Max Effort)
General
|
53.5 source-backed | 73.6 | 47.18 tok/s | $5 | $25 | Artificial Analysis |
|
Anthropic Claude Sonnet 5 (Adaptive Reasoning, Max Effort)
General
|
53.4 source-backed | 71.5 | 71.27 tok/s | $2 | $10 | Artificial Analysis |
|
OpenAI GPT-5.5 (high)
General
|
53.1 source-backed | 71.6 | 73.92 tok/s | $5 | $30 | Artificial Analysis |
|
OpenAI GPT-5.6 Terra (xhigh)
General
|
51.6 source-backed | 70.6 | 119.72 tok/s | $2.5 | $15 | Artificial Analysis |
|
OpenAI GPT-5.4 (xhigh)
General
|
51.4 source-backed | 71.1 | 142.3 tok/s | $2.5 | $15 | Artificial Analysis |
|
OpenAI GPT-5.6 Luna (max)
General
|
51.2 source-backed | 71.4 | 216.2 tok/s | $1 | $6 | Artificial Analysis |
|
Z AI GLM-5.2 (max)
General
China
|
51.1 source-backed | 68.8 | 173.55 tok/s | $1.4 | $4.4 | Artificial Analysis |
|
Meta Muse Spark 1.1 (xhigh)
General
|
50.6 source-backed | 71.3 | 118.65 tok/s | $1.25 | $4.25 | Artificial Analysis |
|
OpenAI GPT-5.5 (medium)
General
|
50.4 source-backed | 71.5 | 58.65 tok/s | $5 | $30 | Artificial Analysis |
|
Google Gemini 3.5 Flash (high)
General
|
50.2 source-backed | 70.1 | 161.54 tok/s | $1.5 | $9 | Artificial Analysis |
|
OpenAI GPT-5.6 Sol (low)
General
|
49.4 source-backed | 69.7 | 57.68 tok/s | $5 | $30 | Artificial Analysis |
|
OpenAI GPT-5.6 Luna (xhigh)
General
|
49.1 source-backed | 68.6 | 211.92 tok/s | $1 | $6 | Artificial Analysis |
|
OpenAI GPT-5.6 Terra (high)
General
|
49 source-backed | 67.1 | 107.95 tok/s | $2.5 | $15 | Artificial Analysis |
|
Anthropic Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort)
General
|
47.2 source-backed | 63 | 49.17 tok/s | $3 | $15 | Artificial Analysis |
|
Google Gemini 3.1 Pro Preview
General
|
46.5 source-backed | 68.8 | 127.43 tok/s | $2 | $12 | Artificial Analysis |
|
OpenAI GPT-5.6 Luna (high)
General
|
46.1 source-backed | 63.3 | 191.23 tok/s | $1 | $6 | Artificial Analysis |
|
Alibaba Qwen3.7 Max
General
China
|
46 source-backed | 66 | 194.41 tok/s | $2.5 | $7.5 | Artificial Analysis |
|
OpenAI GPT-5.6 Terra (medium)
General
|
45.6 source-backed | 64.7 | 109.09 tok/s | $2.5 | $15 | Artificial Analysis |
|
Google Gemini 3.5 Flash (medium)
General
|
45.4 source-backed | n/a | 165.44 tok/s | $1.5 | $9 | Artificial Analysis |
|
MiniMax MiniMax-M3
General
China
|
44.4 source-backed | 58.6 | 94.36 tok/s | $0.3 | $1.2 | Artificial Analysis |
|
DeepSeek DeepSeek V4 Pro (Reasoning, Max Effort)
General
China
|
44.3 source-backed | 59.4 | 62.31 tok/s | $0.43 | $0.87 | Artificial Analysis |
|
OpenAI GPT-5.3 Codex (xhigh)
General
|
44.3 source-backed | n/a | 80.99 tok/s | $1.75 | $14 | Artificial Analysis |
|
Kimi Kimi K2.6
General
China
|
44.2 source-backed | 61.8 | 45.25 tok/s | $0.95 | $4 | Artificial Analysis |
|
Anthropic Claude Opus 4.6 (Adaptive Reasoning, Max Effort)
General
|
43.7 source-backed | n/a | 39.74 tok/s | $5 | $25 | Artificial Analysis |
|
OpenAI GPT-5.5 (low)
General
|
43.5 source-backed | 60.9 | 59.61 tok/s | $5 | $30 | Artificial Analysis |
|
Meta Muse Spark
General
|
43.1 source-backed | 58.6 | n/a | n/a | n/a | Artificial Analysis |
|
Anthropic Claude Opus 4.7 (Non-reasoning, High Effort)
General
|
42.7 source-backed | n/a | 44.02 tok/s | $5 | $25 | Artificial Analysis |
|
Xiaomi MiMo-V2.5-Pro
General
China
|
42.2 source-backed | 60.2 | 57.93 tok/s | $0.43 | $0.87 | Artificial Analysis |
|
OpenAI GPT-5.2 (xhigh)
General
|
42.2 source-backed | n/a | 72.89 tok/s | $1.75 | $14 | Artificial Analysis |
|
Kimi Kimi K2.7 Code
General
China
|
41.9 source-backed | 60.8 | 44.42 tok/s | $0.95 | $4 | Artificial Analysis |
|
Anthropic Claude Sonnet 5 (Non-reasoning, High Effort)
General
|
41.7 source-backed | 66.4 | 60.17 tok/s | $2 | $10 | Artificial Analysis |
|
OpenAI GPT-5.6 Sol (Non-reasoning)
General
|
41.2 source-backed | 65.1 | 32.03 tok/s | $5 | $30 | Artificial Analysis |
|
Tencent Hy3
General
China
|
41.2 source-backed | 58.8 | 50.92 tok/s | $0 | $0 | Artificial Analysis |
|
Nex AGI Nex-N2-Pro
General
|
41 source-backed | 59.1 | 141.78 tok/s | $0.5 | $2.5 | Artificial Analysis |
|
Anthropic Claude Opus 4.5 (Reasoning)
General
|
40.8 source-backed | n/a | 44.37 tok/s | $5 | $25 | Artificial Analysis |
|
DeepSeek DeepSeek V4 Pro (Reasoning, High Effort)
General
China
|
40.8 source-backed | n/a | 61.57 tok/s | $0.43 | $0.87 | Artificial Analysis |
|
OpenAI GPT-5.6 Terra (low)
General
|
40.5 source-backed | 58.1 | 108.48 tok/s | $2.5 | $15 | Artificial Analysis |
|
DeepSeek DeepSeek V4 Flash (Reasoning, Max Effort)
General
China
|
40.3 source-backed | 56.2 | 102.6 tok/s | $0.14 | $0.28 | Artificial Analysis |
|
Xiaomi MiMo-V2-Pro
General
China
|
40.3 source-backed | n/a | n/a | n/a | n/a | Artificial Analysis |
|
Z AI GLM-5.1 (Reasoning)
General
China
|
40.2 source-backed | 55.8 | 78.31 tok/s | $1.4 | $4.4 | Artificial Analysis |
|
OpenAI GPT-5.2 Codex (xhigh)
General
|
40.1 source-backed | n/a | 157.58 tok/s | $1.75 | $14 | Artificial Analysis |
How to read the index
What affects it
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.