ResearchAI model intelligence hub

Research Hub

BenchGecko Research connects model rankings, benchmark evidence, API prices, compute constraints, and market attention in one readable view.

994 models267 providers128 benchmarks386 priced modelsUpdated May 6, 2026
Research signals

BenchGecko separates capability, price, infrastructure, and attention signals so readers can see which claims are benchmarked, sourced, and comparable.

Current leader
OpenAI · 3 benchmarks
Models with benchmark scores30%
Pricing coverage39%
Open model share70%
Benchmarks with source links98%
Compute index
61
high
Mindshare pulse
78
rising
Source links
126
benchmark records
Score coverage
30%
models benchmarked
Research paths
  • Model evaluation entry points
  • Benchmark and source discovery
  • Compute and market context

Papers · notes · methods · benchmark sources · datasets · API access

Research index
MethodologyLive method

How BenchGecko normalizes models, providers, benchmark scores, pricing fields, caveats, and comparison logic.

Updated May 6, 2026BenchGecko methods
MethodologyLive method

How chips, foundries, memory, systems, power, capex, and regional readiness are separated into compute signals.

Updated May 6, 2026Compute hub
MethodologyLive method

How BenchGecko tracks attention, source mix, sentiment, and weekly movement without mixing hype into capability scores.

Updated May 6, 2026Mindshare hub
Dataset386 priced models

Normalized model price records for input, output, cache, reasoning, and API access comparisons across providers.

Updated May 6, 2026Pricing index
API accessDeveloper path

Machine readable access paths for researchers and builders who want to use BenchGecko data in their own systems.

Updated May 6, 2026Developers
Research noteLive index

A current view of frontier and open model movement across normalized benchmark records and provider metadata.

Updated May 6, 2026Model rankings
Research noteLive dashboard

Current infrastructure pressure across chips, memory, systems, energy, capex, regions, and supply constraints.

Updated May 6, 2026Compute index
Paper trackStructure ready

Formal BenchGecko papers and downloadable research reports will live here once authored, reviewed, and versioned.

Formal papers pendingResearch hub
Research noteLive index

Tracks where public evaluations still separate frontier models and where scores are clustering too tightly to explain real deployment choices. 994 models · 128 tracked benchmarks.

Updated May 6, 2026Evaluation coverage
Research noteLive index

Watches provider pricing movement across input, output, cached, and access pricing so model quality can be read beside cost pressure. 267 providers · 386 priced models.

Updated May 6, 2026Pricing index
Research noteLive index

Explains how chips, memory, energy, regions, capex, and attention signals shape the market around model releases and inference capacity.

Updated May 6, 2026Compute hub
Benchmark sourcecoding

Code editing benchmark from the Aider project. Measures ability to apply targeted code changes while maintaining correctness and style.

Updated May 6, 2026aider
Showing 12 of 23. Search or filter to narrow the index.

Formal papers later · live methods and notes now

Reserved

Formal BenchGecko papers will need authorship, review, version dates, citation text, stable URLs, and downloadable files before publication.

Active

Research notes can track benchmark saturation, pricing compression, compute pressure, model movement, and mindshare shifts using live BenchGecko data.

Live

Public methodology, pricing, benchmark, compute, and API access pages are indexed in the searchable library above.

Models · Benchmarks · Pricing · Compute · Economy · Mindshare

994
Models tracked
267
Providers indexed
128
Benchmarks tracked
303
Scored models
386
Priced models
693
Open models
61
Compute index
78
Mindshare pulse
126
Source links
May 6, 2026
Dataset generated

Models · benchmarks · pricing · compute · economy · mindshare

Research map

Use this page as the front door for BenchGecko research. Start with a model, benchmark, price, compute signal, company, or mindshare trend, then jump to the page with the numbers behind it.

Research paths
6
main areas
benchmarks
126
with sources
Freshness
May 6, 2026
latest dataset

Jump from the research index into model, benchmark, provider, pricing, and methodology views.

Current BenchGecko rankings · top models by average benchmark score

Coverage readout
Models with benchmark scores30%
Models with price data39%
Open model share70%
Benchmarks with source links98%

This view explains what supports the public rankings: what is measured, what is priced, what has source context, and where the gaps remain.

Source URLs attached to benchmark records where available

AI compute demand index · regional readiness · capex context

Composite AICDI
61
high

Significant bottlenecks in AI compute supply chain

Open Compute Hub
Region #1
Readiness 68
Region #2
Readiness 62
Region #3
Readiness 57

Attention signals · source mix · model movement

Gecko Pulse
78
rising

BenchGecko tracks market attention separately from benchmark performance so hype, adoption, and capability can be compared instead of mixed together.

Open Mindshare
Models by attention
#1
GPT-5 Chat
openai
89
#2
Claude Mythos Preview
anthropic
92
#3
Gemini 3.1 Pro
google
85
#4
Claude Opus 4.6
anthropic
82
#5
DeepSeek V3.2 Speciale
deepseek
78

How the research hub connects back to source pages

01

Models, providers, benchmarks, prices, compute, and mindshare records.

02

Map records into comparable model, provider, benchmark, and topic layers.

03

Expose rankings, coverage, pressure, and attention as separate signals.

04

Link each claim to the specific BenchGecko page that supports it.

What does BenchGecko Research cover?

It covers model rankings, LLM benchmark evidence, API pricing, compute infrastructure, company data, and mindshare signals. Each section links to the relevant BenchGecko page for the details.

How fresh is the data?

The page uses the current BenchGecko dataset shown at the top of the page. Model, provider, benchmark, pricing, compute, and mindshare data are refreshed through the BenchGecko data pipeline.

Why does BenchGecko track benchmark sources?

Benchmark pages, papers, model releases, and open projects are the evidence behind capability claims. BenchGecko keeps that evidence close to the model, price, provider, and compute data it affects.

How should researchers cite BenchGecko?

Link to the specific model, benchmark, pricing, compute, or methodology page when possible. Use this page when citing the full research index rather than one record.