AI · LEADERBOARD

The AI Leaderboard

Q: What is the best AI model right now?

As of 31 August 2026, Claude Opus 5 (max) 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?

Kimi K3 (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?

Agnes 2.5 Pro Beta 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 (max) 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 31 August 2026, the top-ranked AI model is Claude Opus 5 (max) by Anthropic. The strongest open-source model is Kimi K3 (max), and Agnes 2.5 Pro Beta offers the best price-to-performance. Rankings refresh every day at 04:00 Europe/Amsterdam.

Best closed model

Claude Opus 5 (max)

Anthropic

Intel: 63.1
Speed: 54t/s
Cost in/out: €4.29 / €21.47

State-of-the-art reasoning and complex coding tasks where intelligence is the only metric that matters

Best open model

Kimi K3 (max)

Kimi

Intel: 59.7
Speed: 36t/s
Cost in/out: Provider€2.58 / €12.88Sovereign~€132 / hr*

The leading open-source model for massive document analysis, boasting a million-token context window

Best value667.6

Agnes 2.5 Pro Beta

Sapiens AI

Intel: 49.1
Speed: 151t/s
Cost in/out: €0.09 / €0.26

Ultra-low-cost proprietary model with high speed and a million-token context window

Top 10, side by side

#↑	Model	Vendor	Intelligence	Speed (tok/s)	Cost (€/Mtok)	Context	Best for
1	Claude Opus 5 (max)	Anthropic	63.1	54	€4.29 / €21.47	1.0M	State-of-the-art reasoning and complex coding tasks where intelligence is the only metric that matters
2	Claude Opus 5 (Adaptive Reasoning, Xhigh Effort)	Anthropic	62.5	54	€4.29 / €21.47	—	Adaptive reasoning with maximum effort for highly complex logical problems, sacrificing context size
3	Claude Fable 5 (with fallback)	Anthropic	62.1	62	€8.59 / €42.94	1.0M	High-intelligence fallback model with a massive context window, though at a premium price point
4	Claude Opus 5 (Adaptive Reasoning, High Effort)	Anthropic	61.5	53	€4.29 / €21.47	—	High-effort adaptive reasoning for deep analytical tasks requiring maximum logical precision
5	GPT-5.6 Sol (max)	OpenAI	60.9	84	€3.44 / €17.18	1.0M	Blazing fast frontier intelligence with a massive context window for enterprise-grade workloads
6	Grok 4.6 (high)	SpaceXAI	60.9	58	€1.72 / €5.15	500K	Highly competitive proprietary intelligence with balanced speed and cost-effective pricing
7	KiKimi K3 (max)	Kimi	59.7	36	€2.58 / €12.88 ~€132 / hr*	1.0M	The leading open-source model for massive document analysis, boasting a million-token context window
8	ZGLM-5.3 (max)	Z AI	59.5	75	€1.2 / €3.78 ~€66 / hr*	1.0M	High-speed open-source intelligence with a large context window and highly competitive pricing
9	Claude Opus 5 (Adaptive Reasoning, Medium Effort)	Anthropic	58.6	51	€4.29 / €21.47	—	Balanced adaptive reasoning for complex tasks requiring a blend of speed and cognitive depth
10	Qwen3.8 Max	Alibaba	58.1	30	€1.72 / €5.15	1.0M	Top-tier multilingual performance and reasoning, ideal for global enterprise applications

Sovereign deploy cost is hourly (Scaleway dedicated GPU cluster, EU, all-in SevenLab pricing). Hover any estimate to see the exact GPU profile. Final price depends on throughput and infra choices.

#1 · proprietary

Claude Opus 5 (max)

Anthropic

Intel: 63.1
Speed: 54 t/s
Cost: €4.29 / €21.47
Ctx: 1.0M

State-of-the-art reasoning and complex coding tasks where intelligence is the only metric that matters

#2 · proprietary

Claude Opus 5 (Adaptive Reasoning, Xhigh Effort)

Anthropic

Intel: 62.5
Speed: 54 t/s
Cost: €4.29 / €21.47
Ctx: —

Adaptive reasoning with maximum effort for highly complex logical problems, sacrificing context size

#3 · proprietary

Claude Fable 5 (with fallback)

Anthropic

Intel: 62.1
Speed: 62 t/s
Cost: €8.59 / €42.94
Ctx: 1.0M

High-intelligence fallback model with a massive context window, though at a premium price point

#4 · proprietary

Claude Opus 5 (Adaptive Reasoning, High Effort)

Anthropic

Intel: 61.5
Speed: 53 t/s
Cost: €4.29 / €21.47
Ctx: —

High-effort adaptive reasoning for deep analytical tasks requiring maximum logical precision

#5 · proprietary

GPT-5.6 Sol (max)

OpenAI

Intel: 60.9
Speed: 84 t/s
Cost: €3.44 / €17.18
Ctx: 1.0M

Blazing fast frontier intelligence with a massive context window for enterprise-grade workloads

#6 · proprietary

Grok 4.6 (high)

SpaceXAI

Intel: 60.9
Speed: 58 t/s
Cost: €1.72 / €5.15
Ctx: 500K

Highly competitive proprietary intelligence with balanced speed and cost-effective pricing

#7 · open-source

Kimi K3 (max)

Kimi

Intel: 59.7
Speed: 36 t/s
Cost: €2.58 / €12.88
~€132 / hr*
Ctx: 1.0M

The leading open-source model for massive document analysis, boasting a million-token context window

#8 · open-source

GLM-5.3 (max)

Z AI

Intel: 59.5
Speed: 75 t/s
Cost: €1.2 / €3.78
~€66 / hr*
Ctx: 1.0M

High-speed open-source intelligence with a large context window and highly competitive pricing

#9 · proprietary

Claude Opus 5 (Adaptive Reasoning, Medium Effort)

Anthropic

Intel: 58.6
Speed: 51 t/s
Cost: €4.29 / €21.47
Ctx: —

Balanced adaptive reasoning for complex tasks requiring a blend of speed and cognitive depth

#10 · proprietary

Qwen3.8 Max

Alibaba

Intel: 58.1
Speed: 30 t/s
Cost: €1.72 / €5.15
Ctx: 1.0M

Top-tier multilingual performance and reasoning, ideal for global enterprise applications

Customer support
- Blazing speed of 345 tok/s minimises user waiting times
- Highly economical pricing at just €0.64 per million input tokens
- Generous 1,000,000 token context window handles long chat histories
Gemini 3.7 Flash (high)
Code generation
- Highest intelligence index of 63.1 ensures superior logic
- Massive 1,000,000 token context window easily ingests entire codebases
- Reliable proprietary architecture from Anthropic for enterprise use
Claude Opus 5 (max)
Document extraction
- Massive 1,048,576 token context window fits entire books
- Strong open-source intelligence index of 59.7 ensures accuracy
- Large 2800B parameter architecture handles complex layouts
Kimi K3 (max)
Long context analysis
- Industry-leading 1,048,576 token context window for deep analysis
- High proprietary intelligence index of 56.8 ensures deep insights
- Competitive pricing at €1.07 per million input tokens
Muse Spark 1.2 (xhigh)
On-prem sovereign
- Highest intelligence index of 59.7 among all open-source models
- Massive 1,048,576 token context window for local document processing
- Permissive Kimi K3 License allows for custom enterprise deployment
Kimi K3 (max)
Multimodal vision
- Top-tier intelligence index of 63.1 ensures precise visual reasoning
- Massive 1,000,000 token context window for multi-image analysis
- Anthropic proprietary architecture guarantees enterprise reliability
Claude Opus 5 (max)
Agentic automation
- Peak intelligence index of 63.1 guarantees robust decision making
- Massive 1,000,000 token context window retains long execution history
- Anthropic proprietary model offers industry-leading tool integration
Claude Opus 5 (max)
Multilingual translation
- High intelligence index of 58.1 ensures nuanced translations
- Alibaba proprietary model with proven non-English performance
- Cost-effective pricing at €1.72 per million input tokens
Qwen3.8 Max
Structured extraction
- Massive 1,048,576 token context window handles huge batch extractions
- High proprietary intelligence index of 56.8 ensures schema adherence
- Meta proprietary model offers reliable, structured outputs
Muse Spark 1.2 (xhigh)

How we rank

Snapshot taken 8/31/2026, 2:01:31 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 Opus 5 (max)

Kimi K3 (max)

Agnes 2.5 Pro Beta

Top 10, side by side

Claude Opus 5 (max)

Claude Opus 5 (Adaptive Reasoning, Xhigh Effort)

Claude Fable 5 (with fallback)

Claude Opus 5 (Adaptive Reasoning, High Effort)

GPT-5.6 Sol (max)

Grok 4.6 (high)

Kimi K3 (max)

GLM-5.3 (max)

Claude Opus 5 (Adaptive Reasoning, Medium Effort)

Qwen3.8 Max

Which model for which job

Customer support

Code generation

Document extraction

Long context analysis

On-prem sovereign

Multimodal vision

Agentic automation

Multilingual translation

Structured extraction

How we rank

AI leaderboard FAQ

We pick the model. Then we build the thing.

The AI Leaderboard

Claude Opus 5 (max)

Kimi K3 (max)

Agnes 2.5 Pro Beta

◈ Top 10, side by side

Customer support

Code generation

Document extraction

Long context analysis

On-prem sovereign

Multimodal vision

Agentic automation

Multilingual translation

Structured extraction

▣ How we rank

AI leaderboard FAQ

We pick the model. Then we build the thing.

Top 10, side by side

How we rank