Data edition: 2026-08 · 2026-08-30
Automated decision scope: 20 in automated verification / 79 catalog models
Current ranking snapshot: 2026-08-27 · 395 source records
Latest comparable change edition: 2026-07-21 → 2026-08-27
Lifecycle coverage: 36 lifecycle states documented / 79 · 20 in automation scope

OFFICIAL MODEL REFERENCE

AI model directory

Browse exact model IDs listed in provider documentation. Only versions reliably linked to comparable public data enter the rankings.

Model series: 13
Official versions: 79
Public ranking available: 0
Awaiting comparable data: 79

OFFICIAL MODEL REFERENCE

Official model IDs

Every tracked version remains visible. Ranked versions identify their data sources; other versions explain why no ranking is shown.

13 series · 79 versionsSubmit model

Showing 2 of 13 model series

01 · 7 versions

GPT

A broad proprietary model family with a mature API and tool ecosystem.

Everyday workSolve problems or codeUse current information or tools

Official source

Compare versions

3 of 7 versions shown · Reviewed Jul 2026

GPT · Compare versions
Select for comparison	Model / version	Best fit	Public ranking data	Official access
Select for comparison: gpt-5.6-sol	`gpt-5.6-sol`	Highest capability	Not yet rankedNo comparable public result is available for this exact version in the current edition.	Model detailsUnknown
Select for comparison: gpt-5.6-terra	`gpt-5.6-terra`	Quality and cost balance	Not yet rankedNo comparable public result is available for this exact version in the current edition.	Model detailsUnknown
Select for comparison: gpt-5.6-luna	`gpt-5.6-luna`	Speed and volume	Not yet rankedNo comparable public result is available for this exact version in the current edition.	Model detailsUnknown

Strengths

Covers general, coding, vision, and tool-based workflows.

Limitations

Closed weights and provider-controlled deployment.

02 · 6 versions

Claude

A proprietary family positioned for analysis, writing, coding, and long-context work.

Read, analyze, or writeRead long documentsSolve problems or code

Official source

Compare versions

3 of 6 versions shown · Reviewed Jul 2026

Claude · Compare versions
Select for comparison	Model / version	Best fit	Public ranking data	Official access
Select for comparison: claude-fable-5	`claude-fable-5`	Highest capability	Not yet rankedNo comparable public result is available for this exact version in the current edition.	Model detailsUnknown
Select for comparison: claude-sonnet-5	`claude-sonnet-5`	Quality and cost balance	Not yet rankedNo comparable public result is available for this exact version in the current edition.	Model detailsUnknown
Select for comparison: claude-opus-4-8	`claude-opus-4-8`	Coding and agents	Not yet rankedNo comparable public result is available for this exact version in the current edition.	Model detailsUnknown

Strengths

Well suited to document analysis and sustained written work.

Limitations

Closed weights and API-dependent access.

Showing 2 of 13 model series

PUBLIC SOURCE INDEX

Complete source-listed model index

All 425 published records from 2 public sources, grouped into 419 unique source labels. Inclusion is not a recommendation; identity mappings are shown separately.

425 / 419

Published records: 425
Unique source labels: 419
Mapped to official IDs: 0
Unresolved identities: 419

Showing 12 of 419 source labels

LiveBenchUnresolved identity

Source model ID

Qwen 3.8 Flash Next

Alibaba

Cost per successful task · #3 · $0.0423Open weights · #4 · 76.19

LiveBenchUnresolved identity

Source model ID

Qwen 3.8 Max

Alibaba

Objective tasks · #7 · 78.46Open weights · #2 · 78.46

LiveBenchUnresolved identity

Source model ID

Qwen3.8 27B

Alibaba

Open weights · #6 · 75.27

LiveBenchUnresolved identity

Source model ID

Claude 5 Opus Thinking Max Effort

Anthropic

Objective tasks · #4 · 80.08

LiveBenchUnresolved identity

Source model ID

Claude Fable 5 Max Effort

Anthropic

Objective tasks · #1 · 82.97

LiveBenchUnresolved identity

Source model ID

DeepSeek V4 Flash 0731

DeepSeek

Cost per successful task · #6 · $0.0596Open weights · #7 · 74.17

LiveBenchUnresolved identity

Source model ID

DeepSeek V4 Flash Vision Exp

DeepSeek

Cost per successful task · #5 · $0.0505

LiveBenchUnresolved identity

Source model ID

DeepSeek V4 Pro 0813

DeepSeek

Cost per successful task · #4 · $0.0442Open weights · #3 · 77.44

LiveBenchUnresolved identity

Source model ID

Gemini 3.5 Flash-Lite High

Google

Cost per successful task · #9 · $0.0686

LiveBenchUnresolved identity

Source model ID

Gemini 3.7 Flash High

Google

Objective tasks · #6 · 78.83

LiveBenchUnresolved identity

Source model ID

Muse Spark 1.2 xHigh Effort

Minimax M3

Minimax

Cost per successful task · #7 · $0.0597

Showing 12 of 419 source labels