Inkling Breaks into Top 10 Open-Source Models on Arena
mervenoyann · x · 2026-07-17
Arena has updated the scores for Inkling across two leaderboards.
Key Results
- In the Text Arena, Inkling ranks 10th among open-source models and 58th overall.
- It also stands as the second strongest open-source model in the US, trailing only GoogleDeepMind's Gemma-4-31B.
Category Breakdown
- Hard prompts: #10
- Longer Query: #12
- Coding: #14
- Instruction Following: #15
- It also ranks in the top 15 for professional topics, covering categories like Writing, Literature & Language, Entertainment/Media, and Software.
Related event: Open-Source Model Inkling Enters Top 10 Across Multiple Arena Leaderboards(4 posts)→
More from Models
- Nanbeige4.3-33B benchmarked: 59 tok/s single stream, ~1,060 tok/s across 64 concurrent runs — MaziyarPanahi · 2026-10-26
- Only 2 of 25 full ChatGPT rewrites flagged 100% AI by detectors — paulnovosad · 2026-10-26
- Qwen 4 Reportedly Spotted in the Arena, Hints at Alibaba's Next-Gen Model Testing — AIFlow_ML · 2026-10-26
- Nathan Lambert's first open models lecture: distillation, risks and the ecosystem explained — natolambert · 2026-10-26
- Nanbeige 4.3-33B flops real-world test: zero compilable output vs Qwen — julianharris · 2026-10-26
- Claude's safety classifier blocks SS7 defense research, pushing a security dev to an abliterated GLM — l4rz · 2026-10-26