tuieval 0.2.0.dev8__py3-none-any.whl → 0.2.0.dev9__py3-none-any.whl

tuieval/_version.py

@@ -18,7 +18,7 @@ version_tuple: tuple[int | str, ...]
 commit_id: str | None
 __commit_id__: str | None
 
-__version__ = version = '0.2.0.dev8'
-__version_tuple__ = version_tuple = (0, 2, 0, 'dev8')
+__version__ = version = '0.2.0.dev9'
+__version_tuple__ = version_tuple = (0, 2, 0, 'dev9')
 
 __commit_id__ = commit_id = None

{tuieval-0.2.0.dev8.dist-info → tuieval-0.2.0.dev9.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.5
 Name: tuieval
-Version: 0.2.0.dev8
+Version: 0.2.0.dev9
 Summary: Evaluate local and frontier LLMs on your own questions: accuracy, speed, tokens and PASS/FAIL verdicts, in the terminal.
 Project-URL: Homepage, https://github.com/ashe-wb/tuieval
 Project-URL: Issues, https://github.com/ashe-wb/tuieval/issues
@@ -26,7 +26,9 @@ Description-Content-Type: text/markdown
 
 <p align="center"><img src="https://raw.githubusercontent.com/ashe-wb/tuieval/main/docs/images/brand/readme-header.png" alt="tuieval" width="100%"></p>
 
-**Find out which model you can trust with your work, on your own questions, in the terminal.** Run the same eval packs against local models (llama.cpp GGUFs, LM Studio, Ollama, vLLM; tiny, dense or MoE) and against any frontier model on OpenRouter, side by side. tuieval measures **accuracy, speed and token use** together, and gives a **PASS / FAIL / INCONCLUSIVE** verdict per use case. Grading is automatic; there's no LLM judge.
+**Find out which model you can trust with your work, on your own questions, in the terminal.**
+
+Run the same eval packs against local models (llama.cpp GGUFs, LM Studio, Ollama, vLLM; tiny, dense or MoE) and against any frontier model on OpenRouter, side by side. tuieval measures **accuracy, speed and token use** together, and gives a **PASS / FAIL / INCONCLUSIVE** verdict per use case. Grading is automatic; there's no LLM judge.
 
 Public benchmarks leak into training data and rarely look like your work, so tuieval ships with **no built-in benchmark**. Instead you build *eval packs* from what you actually do: questions with checkable answers, in your domain, with your rules. Then you get an answer to the questions that matter:
 

{tuieval-0.2.0.dev8.dist-info → tuieval-0.2.0.dev9.dist-info}/RECORD

@@ -1,6 +1,6 @@
 tuieval/__init__.py,sha256=myVXVX7htbwezW6k3x_FuKgn1RSZ2WcTaDEMByGn6Wg,312
 tuieval/__main__.py,sha256=E6Gls0DNz8GQK2K-kOUIx8cYhgANW_CH54VKrfCfs14,52
-tuieval/_version.py,sha256=ZFKaQJwtFTREyItfS0YpGkf0higmKXlOBPZqpRTwzWQ,533
+tuieval/_version.py,sha256=IHVwmalkoW20mASroKhIhmhNf5irHisjdIrjTxJWRpc,533
 tuieval/cli.py,sha256=ZaLoWrxyCABu4SJzx5U2gVUUmwcwRgpZVqdqnxyFMOk,4167
 tuieval/client.py,sha256=Vui7ucVv_GiKObGoVS_EWSZFUKPou9PWmutqMTrahXk,9313
 tuieval/compare.py,sha256=b-rVcMwq0Tos3oNKcpUP1HXULKhAQNAS4rlXYSY7t6k,25460
@@ -42,8 +42,8 @@ tuieval/templates/packs/tool_call/pack.toml,sha256=n4bx0lGJHSmW41uVqhfIXJ2BWZpmT
 tuieval/templates/packs/tool_call/system.txt,sha256=mKxu-lB-0YjLHXdgeFJa8x2C180OvcNz5cHv2N5Bg3U,254
 tuieval/templates/packs/tool_call/tests.yaml,sha256=Nv7c4syrzJ9cU8EBKSK_1ZSFx9V02aCjW4-2TBCPT7s,1859
 tuieval/templates/packs/tool_call/tools.yaml,sha256=HgxCkh0On2VwbHSsjAGM8tNCK7ZtKLGrs7lMCn3Fprs,1048
-tuieval-0.2.0.dev8.dist-info/METADATA,sha256=Nox6CCCb4EVEYI8dBI9uKQ_z9yQswBPt6Jva4vqq7ls,12079
-tuieval-0.2.0.dev8.dist-info/WHEEL,sha256=W3fkpkm7-wf9vBI5Z-7s0eWkeM-spu78I8Neb98DeEg,87
-tuieval-0.2.0.dev8.dist-info/entry_points.txt,sha256=7eIhi1GpFxBP2OLJV02Nn8LwsNuO512eKOGt1IBbj04,45
-tuieval-0.2.0.dev8.dist-info/licenses/LICENSE,sha256=7wfRgGtBGH1aXhZkIn47oUznqKC18kEPMvUVgol7Ffc,1077
-tuieval-0.2.0.dev8.dist-info/RECORD,,
+tuieval-0.2.0.dev9.dist-info/METADATA,sha256=BuLF9eKFTrAyKzsz2etiwhH3qBrr1Gv_Czy0VGrHx5A,12080
+tuieval-0.2.0.dev9.dist-info/WHEEL,sha256=W3fkpkm7-wf9vBI5Z-7s0eWkeM-spu78I8Neb98DeEg,87
+tuieval-0.2.0.dev9.dist-info/entry_points.txt,sha256=7eIhi1GpFxBP2OLJV02Nn8LwsNuO512eKOGt1IBbj04,45
+tuieval-0.2.0.dev9.dist-info/licenses/LICENSE,sha256=7wfRgGtBGH1aXhZkIn47oUznqKC18kEPMvUVgol7Ffc,1077
+tuieval-0.2.0.dev9.dist-info/RECORD,,