AI · LEADERBOARD

The AI Leaderboard

Q: What is the best AI model right now?

As of 17 July 2026, Claude Fable 5 (with fallback) by Anthropic is the highest-ranked model on our daily intelligence index. The leaderboard re-ranks every day, so check back for the current pick.

Q: What is the best open-source AI model?

GLM-5.2 (max) is currently the strongest open-source model in our ranking, the top pick for teams that want to self-host or keep data sovereign.

Q: Which AI model has the best price-to-performance?

DeepSeek V4 Flash (max) currently scores highest on our value metric, which weighs intelligence and speed against the cost per million tokens.

Q: Which AI model has the largest context window?

Kimi K3 leads on context window at 1M tokens, useful for long documents, large codebases and extended conversations.

Q: How often is the leaderboard updated?

Every day at 04:00 Europe/Amsterdam. We pull fresh public benchmark data and re-rank, with no smoothing and no manual edits.

Q: How are the AI models ranked?

We aggregate public benchmarks into an intelligence index, then score value as intelligence weighed against output speed and cost per million tokens. Output cost is weighted more heavily because real usage is output-heavy.

Q: Is the SevenLab AI leaderboard free and independent?

Yes. The ranking is free, published under Creative Commons, and fully independent. We take no vendor payments to place models, these are the picks our own teams ship with.

Daily ranking of the strongest AI models. No vendor spin, no marketing pages, just the picks teams actually ship with.

As of 17 July 2026, the top-ranked AI model is Claude Fable 5 (with fallback) by Anthropic. The strongest open-source model is GLM-5.2 (max), and DeepSeek V4 Flash (max) offers the best price-to-performance. Rankings refresh every day at 04:00 Europe/Amsterdam.

Best closed model

Claude Fable 5 (with fallback)

Anthropic

Intel: 59.9
Speed: 69t/s
Cost in/out: €8.72 / €43.6

State-of-the-art reasoning and complex agentic workflows requiring maximum intelligence

Best open model

GLM-5.2 (max)

Z AI

Intel: 51.1
Speed: 164t/s
Cost in/out: Provider€1.22 / €3.84Sovereign~€66 / hr*

Top-tier open-source intelligence for sovereign enterprise deployments

Best value278.7

DeepSeek V4 Flash (max)

DeepSeek

Intel: 40.3
Speed: 122t/s
Cost in/out: Provider€0.12 / €0.24Sovereign~€33 / hr*

Extremely low-cost value workflows with a large context

Top 10, side by side

#↑	Model	Vendor	Intelligence	Speed (tok/s)	Cost (€/Mtok)	Context	Best for
1	Claude Fable 5 (with fallback)	Anthropic	59.9	69	€8.72 / €43.6	1.0M	State-of-the-art reasoning and complex agentic workflows requiring maximum intelligence
2	GPT-5.6 Sol (max)	OpenAI	58.9	66	€4.36 / €26.16	1.0M	High-end proprietary reasoning and complex problem solving
3	KiKimi K3	Kimi	57.1	59	€2.62 / €13.08	1.0M	Ultra-long context tasks requiring high intelligence and proprietary reliability
4	Claude Opus 4.8 (max)	Anthropic	55.7	57	€4.36 / €21.8	1.0M	Deep analytical tasks and long-context research
5	GPT-5.6 Terra (max)	OpenAI	55.0	170	€2.18 / €13.08	1.0M	High-speed, high-intelligence proprietary workflows
6	GPT-5.5 (xhigh)	OpenAI	54.8	78	€4.36 / €26.16	922K	Advanced proprietary reasoning with a large context window
7	Grok 4.5 (high)	SpaceXAI	53.8	131	€1.74 / €5.23	500K	Fast, cost-effective proprietary reasoning and analysis
8	Claude Opus 4.7 (max)	Anthropic	53.5	51	€4.36 / €21.8	1.0M	Complex analysis and long-context document processing
9	Claude Sonnet 5 (max)	Anthropic	53.4	89	€1.74 / €8.72	1.0M	Balanced high-speed reasoning and cost-effective proprietary workflows
10	GPT-5.6 Luna (max)	OpenAI	51.2	249	€0.87 / €5.23	1.0M	Ultra-fast, low-cost customer support and high-volume chat

#1 · proprietary

Claude Fable 5 (with fallback)

Anthropic

Intel: 59.9
Speed: 69 t/s
Cost: €8.72 / €43.6
Ctx: 1.0M

State-of-the-art reasoning and complex agentic workflows requiring maximum intelligence

#2 · proprietary

GPT-5.6 Sol (max)

OpenAI

Intel: 58.9
Speed: 66 t/s
Cost: €4.36 / €26.16
Ctx: 1.0M

High-end proprietary reasoning and complex problem solving

#3 · proprietary

Kimi K3

Kimi

Intel: 57.1
Speed: 59 t/s
Cost: €2.62 / €13.08
Ctx: 1.0M

Ultra-long context tasks requiring high intelligence and proprietary reliability

#4 · proprietary

Claude Opus 4.8 (max)

Anthropic

Intel: 55.7
Speed: 57 t/s
Cost: €4.36 / €21.8
Ctx: 1.0M

Deep analytical tasks and long-context research

#5 · proprietary

GPT-5.6 Terra (max)

OpenAI

Intel: 55.0
Speed: 170 t/s
Cost: €2.18 / €13.08
Ctx: 1.0M

High-speed, high-intelligence proprietary workflows

#6 · proprietary

GPT-5.5 (xhigh)

OpenAI

Intel: 54.8
Speed: 78 t/s
Cost: €4.36 / €26.16
Ctx: 922K

Advanced proprietary reasoning with a large context window

#7 · proprietary

Grok 4.5 (high)

SpaceXAI

Intel: 53.8
Speed: 131 t/s
Cost: €1.74 / €5.23
Ctx: 500K

Fast, cost-effective proprietary reasoning and analysis

#8 · proprietary

Claude Opus 4.7 (max)

Anthropic

Intel: 53.5
Speed: 51 t/s
Cost: €4.36 / €21.8
Ctx: 1.0M

Complex analysis and long-context document processing

#9 · proprietary

Claude Sonnet 5 (max)

Anthropic

Intel: 53.4
Speed: 89 t/s
Cost: €1.74 / €8.72
Ctx: 1.0M

Balanced high-speed reasoning and cost-effective proprietary workflows

#10 · proprietary

GPT-5.6 Luna (max)

OpenAI

Intel: 51.2
Speed: 249 t/s
Cost: €0.87 / €5.23
Ctx: 1.0M

Ultra-fast, low-cost customer support and high-volume chat

Efficient customer support chat
- Blazing speed of 249 tok/s ensures instant chat responses
- Highly economical pricing at €0.87 per million input tokens
- Generous 1,000,000 token context window handles long chat histories
GPT-5.6 Luna (max)
Sovereign code generation
- Dedicated code-tuned variant with 41.9 intelligence index
- Open-source model with 1000B parameters for local deployment
- Cost-effective at €0.83 per million input tokens
Kimi K2.7 Code
High-volume document extraction
- Massive 1,048,576 token context window for huge document batches
- Strong 50.6 intelligence index ensures highly accurate extraction
- Value category pricing at €1.09 per million input tokens
Muse Spark 1.1 (xhigh)
Deep long-context analysis
- Massive 1,048,576 token context window handles entire books
- Solid 50.6 intelligence index for deep semantic understanding
- Fast 121 tok/s speed enables rapid analysis of large datasets
Muse Spark 1.1 (xhigh)
Sovereign on-premises deployment
- Leading open-source intelligence index of 51.1
- Permissive MIT licence allows flexible enterprise deployment
- 753B parameters offer a great balance of power and infra cost
GLM-5.2 (max)
Advanced multimodal vision tasks
- Top-tier intelligence index of 59.9 for complex visual reasoning
- Massive 1,000,000 token context window for multi-image analysis
- Anthropic's premier proprietary model ensures robust vision support
Claude Fable 5 (with fallback)
Complex agentic automation
- Highest intelligence index of 59.9 for complex multi-step planning
- Massive 1,000,000 token context window for long execution traces
- Anthropic's premier model offers reliable tool-use capabilities
Claude Fable 5 (with fallback)
High-speed multilingual translation
- High 50.2 intelligence index from Google's proven translation stack
- Extremely fast 242 tok/s speed for real-time translation
- Value category pricing at €1.31 per million input tokens
Gemini 3.5 Flash
Reliable structured data extraction
- Massive 1,048,576 token context window for complex schema mapping
- Strong 50.6 intelligence index ensures reliable JSON output
- Value category pricing at €1.09 per million input tokens
Muse Spark 1.1 (xhigh)

How we rank

Snapshot taken 7/17/2026, 2:00:59 AM
Value score = (intelligence − 25)² × min(1, speed ÷ 30) ÷ (input cost + output cost × 3). Output is weighted ×3 because real usage is output-heavy; intelligence is squared so cheap-but-weak models can't dominate.
Intelligence, price and speed data by Artificial Analysis.

Daily refresh at 04:00 Europe/Amsterdam. Numbers move; we don't smooth them.

What is the best AI model right now?

What is the best open-source AI model?

Which AI model has the best price-to-performance?

Which AI model has the largest context window?

How often is the leaderboard updated?

How are the AI models ranked?

Is the SevenLab AI leaderboard free and independent?

A new model just dropped?We track every major release in our daily AI news feed.Read the latest AI news

We pick the model. Then we build the thing.

Building or buying with AI?

Talk directly with our AI specialists

15 min, no strings

No sales pressure

Prototype in 7 days

The AI Leaderboard

Claude Fable 5 (with fallback)

GLM-5.2 (max)

DeepSeek V4 Flash (max)

Top 10, side by side

Claude Fable 5 (with fallback)

GPT-5.6 Sol (max)

Kimi K3

Claude Opus 4.8 (max)

GPT-5.6 Terra (max)

GPT-5.5 (xhigh)

Grok 4.5 (high)

Claude Opus 4.7 (max)

Claude Sonnet 5 (max)

GPT-5.6 Luna (max)

Which model for which job

Efficient customer support chat

Sovereign code generation

High-volume document extraction

Deep long-context analysis

Sovereign on-premises deployment

Advanced multimodal vision tasks

Complex agentic automation

High-speed multilingual translation

Reliable structured data extraction

How we rank

AI leaderboard FAQ

We pick the model. Then we build the thing.

The AI Leaderboard

Claude Fable 5 (with fallback)

GLM-5.2 (max)

DeepSeek V4 Flash (max)

◈ Top 10, side by side

Efficient customer support chat

Sovereign code generation

High-volume document extraction

Deep long-context analysis

Sovereign on-premises deployment

Advanced multimodal vision tasks

Complex agentic automation

High-speed multilingual translation

Reliable structured data extraction

▣ How we rank

AI leaderboard FAQ

We pick the model. Then we build the thing.

Top 10, side by side

How we rank