OpenGPTLatest lifecycle reviewClaude Fable 5.1
claude-fable-5-1- Last verified
- Review due
- Official lifecycle source
- Open source
TRUST & DATA STATUS
What is checked, reviewed, and published
See the evidence status behind OpenGPT's model and Agent rankings, including source dates, latest checks, and publication controls.
Status policy updated
01
Official model lifecycle verification
Lifecycle labels are recorded only when an official provider source supports the exact model identity. A daily read-only check flags missing evidence and aging reviews.
Stale after more than 30 days91 exact model identities tracked91 lifecycle records are stale and must be rechecked against the official source.
91 lifecycle records are stale and must be rechecked against the official source.
gpt-6-astraOpen sourcegpt-5.5Open sourcegpt-5.6-solOpen sourcegpt-5.6-terraOpen sourcegpt-5.6-lunaOpen sourcegpt-5.4Open sourcegpt-5.4-proOpen sourcegpt-5.4-miniOpen sourcegpt-5.4-nanoOpen sourceclaude-fable-5-1Open sourceclaude-opus-5Open sourceclaude-fable-5Open sourceclaude-sonnet-5Open sourceclaude-opus-4-8Open sourceclaude-opus-4-7Open sourceclaude-opus-4-6Open sourceclaude-haiku-4-5-20251001Open sourcegemini-3.8-flashOpen sourcegemini-3.7-flashOpen sourcegemini-3.6-flashOpen sourcegemini-3.5-flashOpen sourcegemini-3.1-pro-previewOpen sourcegemini-3.1-flash-liteOpen sourcegemini-2.5-proOpen sourcegemini-2.5-flashOpen sourcegemini-2.5-flash-liteOpen sourcegoogle/gemma-4-E2B-itOpen sourcegoogle/gemma-4-E4B-itOpen sourcegoogle/gemma-4-12B-itOpen sourcegoogle/gemma-4-26B-A4B-itOpen sourcegoogle/gemma-4-31B-itOpen sourcemeta-llama/Llama-4-Maverick-17B-128E-InstructOpen sourcemeta-llama/Llama-4-Scout-17B-16E-InstructOpen sourcemeta-llama/Llama-3.3-70B-InstructOpen sourcemuse-spark-1.3Open sourcemuse-spark-1.1Open sourcemuse-sparkOpen sourcedeepseek-v4-flash-vision-expOpen sourcedeepseek-v4-proOpen sourcedeepseek-v4-flashOpen sourceqwen3.8-maxOpen sourceqwen3.8-flashOpen sourceqwen3.8-27bOpen sourceqwen3.7-max-2026-06-08Open sourceqwen3.7-plus-2026-05-26Open sourceqwen3.6-plus-2026-04-02Open sourceqwen3-coder-plus-2025-09-23Open sourceQwen/Qwen3-235B-A22BOpen sourceQwen/Qwen3-30B-A3BOpen sourceQwen/Qwen3-32BOpen sourceQwen/Qwen3-14BOpen sourceQwen/Qwen3-8BOpen sourceQwen/Qwen3-4BOpen sourceQwen/Qwen3-1.7BOpen sourceQwen/Qwen3-0.6BOpen sourcemistral-medium-3-5Open sourcemistral-small-2603Open sourcemistral-large-2512Open sourceministral-14b-2512Open sourceministral-8b-2512Open sourceministral-3b-2512Open sourcegrok-4.6Open sourcegrok-4.5Open sourcegrok-4.3Open sourcegrok-4.20-0309-reasoningOpen sourcegrok-4.20-0309-non-reasoningOpen sourcegrok-build-0.1Open sourcecommand-a-plus-05-2026Open sourcecommand-a-03-2025Open sourcecommand-a-reasoning-08-2025Open sourcecommand-a-vision-07-2025Open sourcecommand-a-translate-08-2025Open sourcecommand-r7b-12-2024Open sourcecommand-r-plus-08-2024Open sourcecommand-r-08-2024Open sourcemicrosoft/phi-4Open sourcemicrosoft/Phi-4-mini-instructOpen sourcemicrosoft/Phi-4-multimodal-instructOpen sourcemicrosoft/Phi-4-reasoningOpen sourcemicrosoft/Phi-4-mini-reasoningOpen sourcekimi-k3Open sourcekimi-k2.7-codeOpen sourcekimi-k2.7-code-highspeedOpen sourcekimi-k2.6Open sourcekimi-k2.5Open sourcemoonshot-v1-8kOpen sourcemoonshot-v1-32kOpen sourcemoonshot-v1-128kOpen sourcemoonshot-v1-8k-vision-previewOpen sourcemoonshot-v1-32k-vision-previewOpen sourcemoonshot-v1-128k-vision-previewOpen source
02
Model ranking sources
Live monitoring states come from the public status endpoint. Source dates remain separate from check times.
SourceEvidence stateSource data dateCheck activityPublication control
LMArenaOpen source
Reading live state
Latest attemptLast successfulNot published by source
Published through a reviewed release
LiveBenchOpen source
Reading live state
Latest attemptLast successfulNot published by source
Published through a reviewed release
03
Agent evaluation sources
Agent rows show the published evidence record and its latest recorded check. They do not claim source or product uptime.
SourceEvidence stateSource data dateCheck activityPublication control
SWE-bench VerifiedOpen source
Historical snapshot
Latest attemptLast successfulNot published by source
Excluded until adapter validation
Terminal-Bench 2.1Open source
Historical snapshot
Latest attemptLast successfulNot published by source
Excluded until adapter validation
AssistantBenchOpen source
Historical snapshot
Not published by source
Latest attemptLast successfulNot published by source
Excluded until adapter validation
WebArenaOpen source
Historical snapshot
Not published by source
Latest attemptLast successfulNot published by source
Excluded until adapter validation
OSWorld 2.0Open source
Historical snapshot
Latest attemptLast successfulNot published by source
Excluded until adapter validation
Berkeley Function-Calling LeaderboardOpen source
Historical snapshot
Latest attemptLast successfulNot published by source
Excluded until adapter validation
GAIAOpen source
Historical snapshot
Not published by source
Latest attemptLast successfulNot published by source
Excluded until adapter validation
τ²-bench CoreOpen source
Historical snapshot
Latest attemptLast successfulNot published by source
Excluded until adapter validation
τ³-Banking KnowledgeOpen source
Historical snapshot
Latest attemptLast successfulNot published by source
Excluded until adapter validation
04
Service boundaries
A status label only describes the specific workflow named here. It should not be read as a broader availability promise.
Public rankings
OpenGPT publishes source snapshots and catalog records. It does not continuously test provider APIs, model endpoints, prices, or regional access.
Source monitoring
Configured upstream artifacts are checked on their stated cadence. A successful check does not prove every source page, model, or API is available.
Local decision tools
Saved candidates, task inputs, and reports stay in this browser by default. This status page does not imply cloud sync or recovery.
Submissions and email
Submissions enter editorial review. Receipt and final-result emails use a queued transactional process; instant delivery or a response time is not promised.
05
How publication decisions work
Collection, review, catalog inclusion, comparability, and ranking remain separate decisions.
Published through a reviewed release
LMArena and LiveBench updates are collected and validated automatically as review candidates. Public rankings change only after the snapshot and its exact release have passed review.
Adapter coverage
Structured Agent sources publish only through validated adapters. Sources without a safe adapter remain paused or historical and are not used as current evidence.
User submissions
Approval can list a reviewed Agent product in the public directory. It does not set rank, comparability, evidence grade, or guarantee leaderboard inclusion.
06
Methods and corrections
Read the comparison rules or report an inaccurate date, mapping, link, or evidence label.