Inkling 2 Small Model Card - LongBench v2: leaderboard

November 5 publisher model-card comparison. Inkling 2 Small is reported at effort 0.99 (xhigh), temperature 1.0 and a 1M-token maximum trajectory. Comparator effort, generation settings and dated snapshots are not specified. No rc17 or Vals identity is inferred.

Metric: Published score (%). Source: thinkingmachines.ai. Saturation forecast: Rough model projection: around 2026. 13 models tracked.

Top models

#ModelScoreOverall rank
1Gemini 3.8 Flash (Benchmark Sweep Run: source=Inkling2SmallCard; as published; effort, temperature and snapshot unreported)73.7
2Inkling 2 Small (Benchmark Sweep Run: source=Inkling2SmallCard; as published; effort=0.99 xhigh; temperature=1; trajectory=1M tokens)70.6
3DeepSeek-V4.1-Flash-1017 (Benchmark Sweep Run: source=Inkling2SmallCard; as published; effort, temperature and snapshot unreported)69
4Kimi K3 (Benchmark Sweep Run: source=Inkling2SmallCard; as published; effort, temperature and snapshot unreported)69
5Muse Spark Open (Benchmark Sweep Run: source=Inkling2SmallCard; as published; effort, temperature and snapshot unreported)68.7
6GLM 5.3 (Benchmark Sweep Run: source=Inkling2SmallCard; as published; effort, temperature and snapshot unreported)68.4
7GLM-5.3-Flash (Benchmark Sweep Run: source=Inkling2SmallCard; as published; effort, temperature and snapshot unreported)68.2
8MiMo V2.6 Pro (Benchmark Sweep Run: source=Inkling2SmallCard; as published; effort, temperature and snapshot unreported)68
9Mistral Large 4 (Benchmark Sweep Run: source=Inkling2SmallCard; as published; effort, temperature and snapshot unreported)65.7
10Claude Haiku 5.5 (Benchmark Sweep Run: source=Inkling2SmallCard; as published; effort, temperature and snapshot unreported)65.3

Interactive version: theaggregate.ai/benchmark?slug=inkling-2-small-model-card-longbench-v2 · How It Works · Data refreshed daily, snapshot 2026-11-06.