← Leaderboard

GPT-OSS Safeguard 20B MLX

Retired Rank #32 of 33 · 2/8 GAUNTLET progress
Generalist — 50.9 / 100 G Agentic — pending A Understanding — pending U Needle — pending N Thinking — pending T Live — pending L Engineering — pending E Throughput — 35.5 / 100 T

Hollow markers & dashed spokes: axis not yet scored

G
50.9
A
U
N
T
n/d
L
E
T
35.5

Specification

Parameters
20B
Architecture
gpt_oss
Size on disk
11.15 GB
Quantization
Format
MLX
Reasoning (CoT)
Yes — emits reasoning tokens
Internal ID
G3
Mean speed
58 tok/s across suites
Stall census
0 stalls in 9 observed tests (0.0%)
Model card
huggingface.co

Suite results

Suite Score Avg / 20 Tests tok/s
General capability (13-task real-workload suite) 1a 132.3 / 260 14.7 9/13 58

Each test is LLM-judged 0–20 against a fixed rubric; suite max = tests × 20. Where fewer tests ran than the suite total, unrun tests count as zero toward the axis score. See methodology.