2. Linux.do
  3. Inkling-Small 276B-A12B 多模态模型开源 性能超越DeepSeek-V4-Flash 比肩GPT 5.6 Luna

Inkling-Small 276B-A12B 多模态模型开源 性能超越DeepSeek-V4-Flash 比肩GPT 5.6 Luna

fengchris 2026-07-31 07:09 1

官方博客：Introducing Inkling-Small - Thinking Machines Lab


评分指标:




































































































































































































































































































































































































































































































































































































Open weights Closed weights
Inkling-Small Qwen3.5397B-A17B MiMo V2.5 Minimax M2.7 DeepSeek V4Flash Nemotron 3Ultra Inkling Claude 4.5Haiku Gemini 3.5Flash-Lite GPT 5.6Luna
Model Info
AA Indexv4.1 40.0% 34.0% 37.0% 38.0% 40.0% 38.0% 41.0% 30.0% 36.0% 49.0%
Params (B)activated / total 12 / 276 17 / 397 15 / 310 10 / 230 13 / 284 55 / 550 41 / 975 – – –
Agentic (coding)
SWEBench Verified* 80.2% 76.4% 71.0% 79.9% 79.0% 70.7% 77.6% 73.3% 75.0% 93.0%
SWEBench Propublic 55.9% 50.9% 56.1% 56.2% 52.6% 46.4% 54.3% 39.5% 54.2% 62.7%
Terminal Bench 2.1*best harness 64.7% 51.3% 63.7% 55.4% 61.8% 56.4% 63.8% 44.2% 54.0% 82.5%
SciCode 48.7% 42.0% 43.1% 47.0% 44.9% 39.9% 46.1% 43.3% 40.9% 50.0%
Agentic (general)
GDPval-AA v2 1269 962 1145 1159 1189 1164 1238 911 1139 1530
MCP Atlaspublic / all 79.6/79.2% 74.2%/– – 49.4%/– 69.0%/– 47.4/44.7% 78.8/76.0% 41.2/40.2% 79.8/76.8% 77.0/75.0%
Tau 3 Banking 15.5% 13.4% 6.6% 8.9% 22.9% 13.8% 23.7% 9.1% 16.5% 24.3%
BrowseCompwith context management 77.4% 78.6% – 76.3% 73.2% 63.0% 77.1% – – 84.0%
Toolathlon Verified 54.4% 40.7% 49.1% 47.5% 50.9% 34.3% 45.5% 26.9% 57.1% 67.9%
AA-Briefcase 917 – – – 833 870 839 612 – –
Reasoning (general)
GPQA Diamond 89.5% 89.3% 84.9% 87.4% 89.4% 86.7% 87.2% 67.2% 83.8% 89.5%
HLEtext only 31.6% 27.3% 25.2% 28.1% 32.1% 26.6% 29.7% 9.7% 17.5% 35.6%
HLE†with tools 47.8% 48.3% 40.0% 40.3% 45.1% 37.4% 46.0% 17.8% 42.5% 48.9%
AIME 2026 95.5% 93.3% 93.6% 87.7% 95.8% 94.2% 97.1% 85.1% 82.2% 97.6%
HMMT Feb 2026 90.2% 87.9% 82.6% 71.2% 93.9% 78.8% 86.3% 66.7% 63.6% 98.5%
CritPt 8.3% 1.7% 3.7% 0.6% 7.1% 3.1% 5.4% 0.0% 0.0% 20.6%
Reasoning (abstract)
ARC-AGI-1 84.0% – – – – – 79.5% 47.7% – 87.7%
ARC-AGI-2 40.1% – – – – – 36.5% 4.0% – 47.6%
Factuality
SimpleQA Verified 20.6% 26.0% 16.1% 13.5% 34.1% 32.4% 43.9% 5.9% 44.1% 41.7%
AA Omniscienceindex -9.0 -29.8 -9.3 0.7 -22.9 -1.0 2.1 -4.2 6.9 -11.6
Chat
IFBench 82.2% 78.8% 67.1% 75.7% 79.2% 81.4% 79.8% 54.3% 78.6% 67.3%
Global-MMLU-Lite 86.7% 90.0% 83.5% 83.9% 88.4% 85.6% 88.7% 83.4% 89.4% 88.7%
Safety
StrongREJECT 98.4% 99.4% 99.3% 99.4% 97.4% 98.7% 98.6% 98.6% 97.6% 98.7%
FORTRESSadversarial 71.6% 77.3% 64.8% 86.3% 32.0% 77.6% 78.0% 91.3% 70.7% 83.8%
FORTRESSbenign 96.9% 95.4% 94.6% 90.1% 99.2% 90.6% 95.9% 94.1% 95.5% 97.8%
Vision
MMMU ProStandard 10 74.0% 77.3% 75.4% – – – 73.5% 58.6% 79.0% 78.6%
Charxiv RQoriginal / with python 77.4/81.3% 80.8%/– 81.0%/– – – – 78.1/82.0% 57.4%/– 70.0%/– 81.4%/–
Audio
Audio MC† 54.9% – 30.4% – – – 56.6% – 33.6% –
MMAU 77.0% – 73.6% – – – 77.2% – 75.2% –
VoiceBench† 90.1% – 86.4% – – – 91.4% – 85.9% –


个人碎碎念：



感觉国模的优势越来越小了

美国开源也在追赶，OAI还大降价，算力充沛的优势还是很明显的


最新回复 (3)
  • HenryHZY 07-31 07:55
    1楼

    看了看report是个接入了audio的多模态，感觉跟k3还有点差距

  • MineMine 07-31 07:59
    2楼


    一个小模型支持音频和图片输入难能可贵啊，这家公司我猜后续都是这个策略，可惜海外开源模型都好抠搜。



    o3 的图片裁剪，当初老惊艳了。


    国内的公司开源都会在 OpenRouter 或者 OpenCode 限免让大家体验下，海外的很少见提供免费的，最多给个对话框，体验不到啥东西。



    价格真一般

  • fengchris 楼主 07-31 08:05
    3楼

    你这个是自己部署的价格 下面有推理的价格 跟gpt-5.6-luna差不多

* 帖子来源Linux.do
附近帖子
返回
飞读
随机推荐