← Akhilesh's Notepad

01 / MacPaw - Eney

Eney

Notes on the Eney harness and local evaluation of LFM tool-use models.

Benchmark Versions

This page contains results from multiple, non-equivalent benchmark releases. Only scores in the same row and version are comparable.

VersionWhat it isSizeStatus
Legacy Export v0Original MacPaw split: general desktop tasks plus MCP tasks.84Archived exploratory suite
Liquid Memory Extension v1General-user memory tasks authored by Liquid to cover writing, maintenance, retrieval, restraint, conflict, expiry, forgetting, and long context.32Liquid augmentation
Liquid Draft v1MacPaw's Aug 10 draft plus Liquid's 32 memory tasks. This was a working union, not a canonical MacPaw release.222
190 + 32
Superseded
Eney Refined v2MacPaw's reviewed, refined benchmark incorporating the selected Liquid memory set.204
172 + 32
Current

Current Readout: Eney Refined v2

Current benchmark: 172 reviewed base samples + 32 Liquid memory samples = 204 (Aug 14). MacPaw reports Claude Sonnet at 80% and Gemma 4 E4B at 39%. LFM 2.5 2.6B Q4_K_M is running locally; its final score will be added here once all 204 cases have graded. Do not compare this table with the archived suites below.

Liquid Memory Extension v1

The Aug 10 extension adds 32 general-user Mac memory cases: durable writes and updates, restraint, retrieval, multi-note synthesis, fresh-session persistence, conflict/recency, expiry, forgetting, conditional memory, conversation/tool-result recall, and longer context. The 28 cases that do not depend on host-home filesystem paths have clean, comparable local runs for both models.

Aug 10 memory sliceCasesLFM 2.5 2.6B Tool
Q4_K_M
Claude Sonnet 4.6Interpretation
Core memory calibration163/1613/16Memory-only local cases.
Coverage extension103/109/10Conflict, expiry, forgetting, conditional, and tool-result context.
Fresh-session lifecycle pairs20/22/2Write in one session; retrieve from memory in a new session.
Comparable local total2821.4% (6/28)85.7% (24/28)Draft-v1 memory benchmark readout.
VM-bound filesystem actions4ExcludedExcludedNeed MacPaw's VM path semantics for a valid score.

What changed from Legacy Export v0: memory is evaluated as an explicit agent capability, including writes, maintenance, retrieval, restraint, and fresh-session use. The now-superseded 190-case MacPaw draft plus this 32-case extension formed the 222-task Liquid Draft v1 combined dataset.

Aug 10 / EvalMemory-extension method, run coverage, and combined 222-task plan
Archived local tool-use runs: Legacy Export v0

These earlier 34/50-task results use Liquid's local-host fallback rather than MacPaw's private Tart VM environment. Docker/tool isolation differs modestly, but this is not considered a material blocker for early directional comparison.

Legacy Export v0 / llama.cpp

Suite2.6B Tool
Q8_0
2.6B Tool
Q4_K_M
2.6B RC1
Q8_0
2.6B RC1
Q4_K_M
8B A1B
Q8_0
8B A1B
Q4_K_M
Hermes 3 8B
Q4_K_M
Claude
Sonnet 4.6
Inference serverllama.cppllama.cppllama.cppllama.cppllama.cppllama.cppllama.cppHosted
34 tasks / non-MCP29% (10/34)24% (8/34)41.2% (14/34)35.3% (12/34)29.4% (10/34)29.4% (10/34)11.8% (4/34)82.4%
50 tasks / MCP32% (16/50)28% (14/50)56.0% (28/50)46.0% (23/50)42.0% (21/50)40.0% (20/50)24.0% (12/50)80.0%

Legacy Export v0 is the original 34-task general + 50-task MCP split, not the current refined benchmark. Q8_0 and Q4_K_M use the June 2.6B Tool GGUF checkpoint. RC1 uses the same engine through Q8_0 and Q4_K_M GGUFs. Hermes 3 uses its owner-specified ChatML and XML function-calling protocol, translated only at Eney's OpenAI boundary.

Diagnostic / non-comparable runs

Suite2.6B RC1
BF16
8B A1B
8-bit
Qwen 3.5 9B
Q4_K_M
Qwen 3.5 9B
Q8_0
Inference serverMLXMLXllama.cppllama.cpp
34 tasks / non-MCP29.4% (10/34)26.5% (9/34)17.6% (6/34)Stopped early
50 tasks / MCP22.0% (11/50)Invalid run32.0% (16/50)Not run

MLX results are retained for investigation but should not be compared directly: the 8B run hit the coordinator's 120-second no-harness-event watchdog before grading. Qwen is also retained as a diagnostic only: its low score and early Q8 behavior suggest a likely prompt/parser mismatch with Eney's generic tool surface.

Research noteHow Eney handles memoryResearch noteEney benchmark quality assessment