Inkling 2 Small Model Card - Charxiv RQ - Original: 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. Original and Python-enabled variants remain separate.

Metric: Published score (%). Source: thinkingmachines.ai. Saturation forecast: Rough model projection: around 2026. 12 models tracked.

Top models

#ModelScoreOverall rank
1Gemini 3.8 Flash (Benchmark Sweep Run: source=Inkling2SmallCard; original; effort, temperature and snapshot unreported)86.2
2Inkling 2 Small (Benchmark Sweep Run: source=Inkling2SmallCard; original; effort=0.99 xhigh; temperature=1; trajectory=1M tokens)85.6
3Muse Spark Open (Benchmark Sweep Run: source=Inkling2SmallCard; original; effort, temperature and snapshot unreported)85.4
4Kimi K3 (Benchmark Sweep Run: source=Inkling2SmallCard; original; effort, temperature and snapshot unreported)84.8
5Claude Haiku 5.5 (Benchmark Sweep Run: source=Inkling2SmallCard; original; effort, temperature and snapshot unreported)84.4
6Mistral Large 4 (Benchmark Sweep Run: source=Inkling2SmallCard; original; effort, temperature and snapshot unreported)83.2
7MiniMax-M3.1-Flash (Benchmark Sweep Run: source=Inkling2SmallCard; original; effort, temperature and snapshot unreported)82.5
8GPT-6 Luna (Benchmark Sweep Run: source=Inkling2SmallCard; original; effort, temperature and snapshot unreported)81.8
9GLM-5.3-Flash (Benchmark Sweep Run: source=Inkling2SmallCard; original; effort, temperature and snapshot unreported)80.2
10DeepSeek-V4.1-Flash-1017 (Benchmark Sweep Run: source=Inkling2SmallCard; original; effort, temperature and snapshot unreported)77

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