Kimi K3 again posts clear benchmark wins over Inkling across five tests
echen · x · 2026-07-24
A follow-up chart says Kimi K3 leads Inkling across every benchmark shown:
- Antidote: 1077 vs 985 Elo
- HANDBOOK.md: 11.9% vs 1.9%
- Chartography: 26.6% vs 3.4%
- Riemann-bench: 37.6% vs 15.2%
- ComplexConstraints: 37.9% vs 0.3%
The image is paired with the earlier caveat that the models are not directly comparable in size, and that Inkling is still an early release.
Related event: Kimi K3 Outperforms Inkling in Benchmarks Despite Size Disparity(2 posts)→
More from Models
- OpenAI Codex now supports one project across multiple folders — thesaraharminta · 2026-07-24
- Peter Diamandis says Kimi has dominated open-weights leaderboards for a year — PeterDiamandis · 2026-07-24
- Anthropic updates Claude Voice Mode with more capable models — RebeccaBellan · 2026-07-24
- Musk says Grok 4.5 is making progress as OpenRouter usage surges — elonmusk · 2026-07-24
- Bindu Reddy says Kimi K3 is cheap, strong on long tasks, but not frontier — bindureddy · 2026-07-24
- Artificial Analysis puts model intelligence and cost on San Francisco billboards — ArtificialAnlys · 2026-07-24