Best overall
Closed model
Anthropic
- Intelligence
- 60.7
- Speed
- 61tok/s
- Input / output
- $5 / $25
- Context
- 1M
Best fit
State-of-the-art reasoning and complex agentic workflows
AI · LEADERBOARD
Escolha o modelo certo para o trabalho.
Uma comparação prática dos modelos de IA que equipes podem implantar agora.
Snapshot: 5 Aug 2026 · 13:01 TST12 models compared
Independent editorial snapshot · not live platform telemetry
The short answer
Three leaders, three different decisions.
Best open model
Open weights
Kimi
- Intelligence
- 57.1
- Speed
- 36tok/s
- Input / output
- $3 / $15
- Context
- 1.05M
Best fit
Sovereign, open-weight deployments needing maximum intelligence
Best value
Open weights
Xiaomi
- Intelligence
- 37.2
- Speed
- 82tok/s
- Input / output
- $0.14 / $0.28
- Context
- 1.05M
Best fit
Cost-sensitive extraction and high-volume structured work
OpenRouter usage
OpenRouter LLM usage ranking
Top models by prompt, completion, and reasoning tokens processed on OpenRouter. Showing the first 20 only.
Top 20OpenRouter data · cached hourlyUpstream · Aug 6, 2026
- 1.DeepSeek V4 Flash 0423by DeepSeek6.31T tokens17%
- 2.DeepSeek V4 Flash 0731by DeepSeek6.15T tokensnew
- 3.Hy3by Tencent5.69T tokens19%
- 4.MiMo-V2.5by Xiaomi5.3T tokens40%
- 5.GPT-5.6 Luna (batch)by OpenAI4.15T tokens900%
- 6.GLM 5.2 (batch)by Z.ai2.99T tokens8%
- 7.DeepSeek V4 Proby DeepSeek2.64T tokens27%
- 8.Nemotron 3 Ultra (free)by Nvidia2.33T tokens13%
- 9.Gemini 3.6 Flash (batch)by Google2T tokens466%
- 10.Laguna S 2.1 (free)by Poolside1.82T tokens466%
- 11.MiniMax M3 (batch)by MiniMax1.76T tokens13%
- 12.Kimi K3by Moonshot AI1.39T tokens3%
- 13.Step 3.7 Flashby StepFun1.32T tokens24%
- 14.Ling-3.0-flash (free)by Inclusion AI1.14T tokens12%
- 15.Claude Opus 5 (batch)by Anthropic1.13T tokens44%
- 16.Claude Sonnet 5 (batch)by Anthropic1.04T tokens2%
- 17.Gemini 3 Flash Preview (batch)by Google929B tokens5%
- 18.Claude Sonnet 4.6 (batch)by Anthropic866B tokens7%
- 19.GPT-5.6 Terra (batch)by OpenAI758B tokens145%
- 20.Gemini 2.5 Flash Lite (batch)by Google612B tokens13%
From benchmark to decision
Which model for which job?
Nine recurring production scenarios, with the trade-offs that matter before a team commits to a model.
Selected use case
01 / 09
Decision view
Customer support
Why it fits
- 01288 tok/s keeps wait time low
- 02Multilingual intake
- 03Strong multimodal routing
How the ranking works
Transparent enough to disagree with.
The ranking combines public benchmark signals with price, measured throughput, context and deployment constraints. It is a decision aid—not a universal definition of model quality.
- Dataset snapshot
- 5 Aug 2026 · 13:01 TST
- Review cadence
- Revalidated when major model data changes
Value score
(intelligence − 25)² × min(1, speed ÷ 30) ÷ (input cost + output cost × 3)
Output is weighted ×3 to reflect output-heavy production use; intelligence is squared so cheap but weak models do not dominate.
- Intelligence
- Public benchmark and reasoning signals form the default order.
- Speed
- Output tokens per second; provider and region still affect real latency.
- Cost
- Public input and output price per million tokens, before enterprise discounts.
- Deployment
- Context, weight access and hosting constraints determine production fit.
Public references
Prices and performance can change without notice. Validate the finalists against your own prompts, infrastructure and risk requirements before procurement.
FAQ
Questions worth asking before the benchmark wins the argument.
Claude Opus 5 leads the intelligence-first ranking in this captured dataset. The best choice can change once price, latency, hosting and task-specific evaluation enter the decision.
Kimi K3 is the leading open-weight option in this snapshot, combining the strongest open-model intelligence signal with a 1M-token context window and sovereign deployment flexibility.
MiMo-V2.5 leads the value formula because its low token price and large context offset a lower raw intelligence score. It is particularly compelling for structured, high-volume work.
No. Context capacity only describes how much can be submitted. Retrieval design, instruction quality, attention behaviour and evaluation still determine whether that context produces a useful answer.
This page is an editorial snapshot, not live platform telemetry. We revalidate the dataset when major model releases or material pricing and performance changes occur.
The default order uses the public intelligence signal. Speed, price, context, openness and a separate value formula remain visible so teams can challenge the default order.
Tenten does not sell model tokens through this page. Public sources are linked, assumptions are shown, and we recommend a task-specific evaluation before any production decision.
TENTEN AI · MODEL EVALUATION
The leaderboard is the start
Bring the workflow. We’ll test the shortlist.
A model only becomes a good decision after it survives your documents, permissions, latency budget and failure cases.