Live Platform Data
Drux Activity
Real-world AI model performance from every query run on Drux. Speed, reliability, and consensus measured on actual user questions — not controlled benchmarks.
1,896 searches · 5,740 model calls · live
28.3Mtokens processed in the last 30 days
Platform Summary
563 Hub articles published, read 3044 times in total. 1896 total searches completed. 5740 individual model calls recorded. Average consensus score: 65%. Model completion rate: 76%.
Top Models by Speed
- inception/mercury-2: avg 5.8s, 97% reliability, 215 queries
- mistralai/mistral-small-2603: avg 8.4s, 83% reliability, 188 queries
- anthropic/claude-sonnet-4.6: avg 8.5s, 100% reliability, 3 queries
- microsoft/phi-4: avg 8.9s, 97% reliability, 200 queries
- openai/gpt-5.5: avg 10.0s, 100% reliability, 3 queries
Most Agreed Questions
- Is it true that cracking knuckles causes arthritis? — consensus score 100%
- Can water boil and freeze simultaneously? — consensus score 100%
- Does taking collagen improve skin and joint health? — consensus score 100%
- Do cold and flu tablets with oral phenylephrine effectively relieve congestion? — consensus score 90%
- Do lactase pills effectively help with lactose intolerance symptoms? — consensus score 90%
Platform Pulse
Total Searches
1,896
This Week
59
last 7 days
Today
4
Model Calls
5,740
across all searches
Avg Consensus Score
65%
across all completed searches
Model Completion Rate
76%
calls that returned successfully
Model Leaderboard — on Drux
Last 1,000 searches · click column to sort
| Model | Avg Speed▲ |
|---|---|
1Mercury 2FREE | 5.8s |
2Mistral Small 4FREE | 8.4s |
3Claude Sonnet 4.6PAID | 8.5s |
4Phi-4FREE | 8.9s |
5GPT-5.5PAID | 10.0s |
6Solar Pro 3FREE | 13.6s |
7Gemini 3.5 FlashPAID | 14.5s |
8Hermes 3 70BFREE | 14.7s |
9GLM 5.2FREE | 15.2s |
10Command RFREE | 16.1s |
11Llama 4 MaverickFREE | 17.7s |
12GPT OSS 120BFREE | 18.1s |
13Gemma 4 31BFREE | 19.0s |
14DeepSeek V3.2FREE | 21.3s |
15Seed 1.6FREE | 30.9s |
16Qwen3.5 397BPAID | 34.0s |
⚡ Fastest on Drux
Mercury 2
avg 5.8s · 97% reliable
✓ Most Reliable on Drux
Gemini 3.5 Flash
100% completion · 5 calls
Consensus Digest — Recent Public Searches
✓ Models Agreed
Is it true that cracking knuckles causes arthritis?
Can water boil and freeze simultaneously?
Does taking collagen improve skin and joint health?
Do cold and flu tablets with oral phenylephrine effectively relieve congestion?
Do lactase pills effectively help with lactose intolerance symptoms?
Updated every 5 min · Data from last 1,000 searches
About This Data
How is this different from other AI benchmarks?
Most AI benchmarks are run under controlled laboratory conditions on standardised test sets. Drux Activity measures performance on real user questions — diverse, unpredictable, and representative of actual use. Speed and reliability numbers here reflect what users actually experience.
What is a Consensus Win?
When multiple models answer the same question and their responses agree closely (consensus score ≥ 7/10), all models that responded are credited with a Consensus Win. A high Consensus Win rate means a model consistently lands on the same answer as its peers — a signal of reliability beyond just accuracy.
Why do free models have more queries?
Drux randomly selects models for each search. Free-tier models are included in more searches because they are available to all users. Paid models are selected when users opt into premium tiers. Query count reflects availability and tier distribution, not quality — sort by Speed or Reliability for a fairer comparison.
How often is this updated?
Every figure is computed live when the page loads. Search, model-call, consensus and completion totals cover every completed search; the per-model leaderboard uses the most recent 1,000 searches, so it reflects how models perform now rather than months ago.