HF Model & Benchmark Matrix

24,078 variants · 14,984 scores · 120 benchmarks

Home/Orgs/inclusionAI/inclusionAI/Ling-2.6-1T

inclusionAI/Ling-2.6-1T

family misc · 2 variants · unknown

provider: inclusionAI
released: —
huggingface: https://huggingface.co/inclusionAI/Ling-2.6-1T
best scores: MMLU: 86.03MMLU-Pro: 67.91GPQA: 41.92SimpleQA: 64.53GSM8K: 89.31OmniMath: 33.6HumanEval: 83.54LiveCodeBench: 40.09BBH: 86.88LongBench: 30.02

Best scores per benchmark

benchmark	category	best score
GSM8K	math	89.31
BBH	reasoning	86.88
MMLU	knowledge	86.03
HumanEval	coding	83.54
MMLU-Pro	knowledge	67.91
SimpleQA	knowledge	64.53
GPQA	reasoning	41.92
LiveCodeBench	coding	40.09
OmniMath	math	33.6
LongBench	long-context	30.02

Variants (2)

variant	kind	quant	bits	vRAM	dl	org	year
Ling-2.6-1T	original	bf16	16.0		1,356	inclusionAI	2026
Ling-2.6-1T-base	fp8	fp8	8.0		132	inclusionAI	2026

Hugging Face model & benchmark data scraped & matrix-ified. 24,078 variants · 14,984 scores · 120 benchmarks.