Endeavor 1.0 Benchmarks, Specifications & Availability

Endeavor 1.0

Explore Endeavor 1.0 from Flower Labs: published specifications, source-linked vendor benchmarks, independent evaluator coverage and recorded pricing when available.

Older versionReplaced by Endeavor 1.1Release source ↗

Published specifications

Provider: Flower Labs
Access: Proprietary
License: Proprietary
Context window: 1M
Total parameters: Not published
Active parameters: Not published
Released: 2026-09-01
Modalities: text
Family: Endeavor

Announcement · Website

Model notes

Flower Labs frontier generalist for reasoning, coding and agent work, text only. Access by request through the Flower-managed API or private deployment; model artifacts are distributed privately, and Hugging Face has no official Endeavor weights (flwrlabs lists only Lizzy-7B, checked 3 November 2026). Built on unnamed open-weight models with continual pre-training and post-training by Flower. Maximum context 1M tokens per the Flower 1.38.0 release notes (22 September 2026); the supplied Codex configuration uses 128K with compaction at 96K. Parameters, API model ID and pricing are unpublished; no OpenRouter route. Flower says its scores come from an internal evaluation of the launch configuration available on 31 August 2026.

Compare Endeavor 1.0 with other models →Compare subscription plans Explore data coverage

Pricing · OpenRouter

No OpenRouter pricing is recorded for this model. Missing rates are not free.

Official / vendor benchmarks

Default headline records. Own-vendor, peer-vendor and third-party provenance remain visible in evidence; configurations may differ.

Official / vendor headline scores; expand evidence for every record
Benchmark / evaluator	Headline score	Evidence
GPQA (Flower; subset unstated)	92%unknown effort	The recorded result & source 92% · raw 92 % Headline · unknown effort · Own vendor Source/record date: 2026-09-01 Harness: Flower Labs internal evaluation of the launch configuration available on 31 August 2026, per the documentation; settings and effort unpublished. Same value in the 1 September launch post and the August datasheet. Label “GPQA”; subset unstated. https://flower.ai/docs/model/endeavor.html
HumanEval (Flower; protocol unstated)	98.2%unknown effort	The recorded result & source 98.2% · raw 98.2 % Headline · unknown effort · Own vendor Source/record date: 2026-09-01 Harness: Flower Labs internal evaluation of the launch configuration available on 31 August 2026, per the documentation; settings and effort unpublished. Same value in the 1 September launch post and the August datasheet. Label “HumanEval”; protocol unstated. https://flower.ai/docs/model/endeavor.html
IFEval	94.1%unknown effort	The recorded result & source 94.1% · raw 94.1 % Headline · unknown effort · Own vendor Source/record date: 2026-09-01 Harness: Flower Labs internal evaluation of the launch configuration available on 31 August 2026, per the documentation; settings and effort unpublished. Same value in the 1 September launch post and the August datasheet. Label “IFEval”; scoring variant unstated. https://flower.ai/docs/model/endeavor.html
AIME 2026	99.9%unknown effort	The recorded result & source 99.9% · raw 99.9 % Headline · unknown effort · Own vendor Source/record date: 2026-09-01 Harness: Flower Labs internal evaluation of the launch configuration available on 31 August 2026, per the documentation; settings and effort unpublished. Same value in the 1 September launch post and the August datasheet. Label “AIME 2026”; sampling, aggregation and tools unstated. https://flower.ai/docs/model/endeavor.html

Independent evaluators

Evaluator harnesses are distinct from vendor measurements. Missing coverage is not a failed test.

No independent evaluator results are recorded for this model.

Read how we select and source scores or the comparison guide.