Kimi K3 Jumps to 3rd on VoxelBench
scaling01 · x · 2026-07-18
A VoxelBench screenshot shows Kimi K3 ranking 3rd on the text leaderboard with a score of 2099. Although it still trails behind GPT-5.6 Sol (1st) and Claude Fable 5 (2nd), it marks a significant improvement from K2.6's 28th place.
The core takeaway is Kimi K3's substantial progress on this benchmark, with the screenshot detailing its score, confidence interval, number of votes, and win rate.
Related event: Kimi K3 vs Qwen 3.8 Max: Fierce Competition in Chinese LLMs(4 posts)→
More from Models
- Kimi K2.8 Preview rolls out: near-K3 coding performance, 1M context for all tiers — teortaxesTex · 2026-09-11
- Looking for a classifier of software engineering task shapes to pick models per task — StewartalsopIII · 2026-09-11
- DeepSeek V4 Pro API to continue after Sept 2026, billing unchanged — teortaxesTex · 2026-09-11
- DeepSeek V4.1 Flash Hits 98% of GPT-6 Astra's Score at 1.4% of the Cost in Third-Party Benchmark — ayushtweetshere · 2026-09-11
- TheZvi Polls: Has Your Coding Model Choice Changed Since Fable 5.1 and Astra? — TheZvi · 2026-09-11
- antirez Weighs In on Anthropic Banning Minors From Using Claude — antirez · 2026-09-11