Ling-2.6-1T-base

Home/Models/inclusionAI/Ling-2.6-1T-base

inclusionAI/Ling-2.6-1T-base

kind: fp8
quant: fp8 (8-bit)
family: misc
modality: text-generation
root model: inclusionAI/Ling-2.6-1T
provider: inclusionAI
license: mit
language: —
context: —
library: transformers
vRAM (GB): —
size on disk: —
downloads: 132
likes: 13
created: —
last modified: 2026-06-22T08:30:17+00:00 (2026)
huggingface: https://huggingface.co/inclusionAI/Ling-2.6-1T-base
tags: transformerssafetensorsbailing_hybridtext-generationconversationalcustom_codearxiv:2606.15079license:mitfp8region:us

benchmark	category	score	context	conf	evidence
GSM8K	math	89.31	GSM8K	medium	`\| GSM8K \| 89.31 \| 93.93 \|`
BBH	reasoning	86.88	BBH	medium	`\| BBH \| 86.88 \| 89.73 \|`
MMLU	knowledge	86.03	MMLU	medium	`\| MMLU \| 86.03 \| 86.82 \|`
HumanEval	coding	83.54	HumanEval-Plus	medium	`\| HumanEval-Plus \| 83.54 \| 85.98 \|`
MMLU-Pro	knowledge	67.91	MMLU-Pro	medium	`\| MMLU-Pro \| 67.91 \| 67.79 \|`
SimpleQA	knowledge	64.53	C-SimpleQA	medium	`\| C-SimpleQA \| 64.53 \| 76.83 \|`
GPQA	reasoning	41.92	GPQA	medium	`\| GPQA \| 41.92 \| 45.45 \|`
LiveCodeBench	coding	40.09	LiveCodeBench	medium	`\| LiveCodeBench \| 40.09 \| 44.27 \|`
OmniMath	math	33.6	OmniMath	medium	`\| OmniMath \| 33.60 \| 38.70 \|`
LongBench	long-context	30.02	LongBenchv2	medium	`\| LongBenchv2 \| 30.02 \| 43.54 \|`
SimpleQA	knowledge	20.87	SimpleQA	medium	`\| SimpleQA \| 20.87 \| 38.26 \|`

none scraped.