Skip to content

d1-omni:600m

d1-omni · Liquid AI · 587M · ONNX Runtime · LFM Open License v1.0

Score
45.5
95 % interval 43.5–47.7
Rank
34
of 66 scored models
Public benchmark
63.9
macro accuracy, %
typed-decisions
57.5
accuracy, %

By task

Chance-corrected accuracy on each of the 14 tasks: 0 is guessing, 100 is every answer right.

Workflows
typed-decisions
37.7
Classification
MASSIVE en
82.8
MASSIVE de
70.0
Civil Comments
72.0
Aegis 2
28.0
Understanding
MultiNLI
69.9
VitaminC
48.9
PAWS
40.8
Knowledge
BoolQ
38.0
SQuAD 2
53.2
PubMedQA
46.6
Judging
HelpSteer 2
27.7
SummEval rel.
3.1
SummEval cons.
18.4

Accuracy and calibration

BenchmarkAccuracyChoiceNoulScoreECEBrierRejected
Public benchmark63.9(62.5–65.3)73.173.233.10.0750.4460 / 3,880
typed-decisions57.5(55.3–59.7)60.770.845.00.0660.5370 / 400 requests

Accuracy in %, with its 95 % bootstrap interval. A rejected request (the model can’t take the question, or the input is too long for it) counts as wrong.

Speed and memory

Devicep50p90LoadVRAMRAM peakPrecision
RTX 5090 CUDA16.6 ms17.4 ms7.90 s2.6 GB1.9 GBF32
Threadripper 3960X CPU960 ms992 ms5.80 s–1.8 GBF32

Five-question requests over HTTP, one at a time, each a different short message. VRAM: the rise of the GPU’s used memory while the model is loaded. RAM peak: the runner process’s peak resident memory.

Parity with the authors’ code

DeviceSame decisionMax logit diff.ResultRecord
RTX 4090 CPU456/4561.4e-4passresults/runs/2026-10-24-parity-rtx4090-cpu.json
RTX 4090 CUDA456/4568.6e-5passresults/runs/2026-10-24-parity-rtx4090-cuda.json

Reproduce

The tools are in convert/ollaya_convert and need only Python’s standard library. Run them against a local Ollaya 0.13.0 with the same model digest.

ollaya pull d1-omni:600m

# typed-decisions; export the test split once with
# uv run python -m ollaya_convert.bench_typed export --out typed.jsonl
python -m ollaya_convert.bench_typed run --model d1-omni:600m \
  --url http://127.0.0.1:11435 --data typed.jsonl --out typed/d1-omni-600m

# Bespoke Labs' public benchmark; build its 13 subsets first
NIMBLE_SRC=nimble python -m ollaya_convert.bench_public run --model d1-omni:600m \
  --url http://127.0.0.1:11435 --data public --out public/d1-omni-600m

# speed and memory
python -m ollaya_convert.bench_latency --models d1-omni:600m --memory \
  --machine my-machine --device cuda --out latency.json