Kimi K2.7 Code

Kimi’s most capable coding model yet

Open Source

Artificial Intelligence

Development

Visit WebsiteSee on Product HuntHugging Face ⧉Twitter ⧉

The open-weights + 256K context combination is what I'd test first, especially on a repo task where the model has to keep tool outputs, diffs, and failed test logs straight. Lower reasoning-token usage is useful, but the tradeoff I wonder about is recovery after the agent makes a bad edit. Do you have evals that measure whether K2.7 can backtrack from a failed test run without losing the original instruction?

Interesting launch. For coding-focused models, the thing I’d want to test is not just generation quality, but how well it handles long-running repo work: keeping context clean, explaining risky changes, and recovering after failed tests.

The 30% drop in reasoning tokens alongside better multi-step task success is the interesting signal here. It suggests you're pruning unproductive reasoning chains rather than just thinking less. We've seen agent costs spiral on complex multi-turn tasks because of runaway chain-of-thought. How did you train the model to distinguish productive reasoning steps from redundant ones?

Interesting model. The 30% lower reasoning-token count is notable. Does that also reduce latency proportionally for typical multi-step tasks?

To be honest, I really like Kimi, but this time the benchmarks are a bit below my expectations; they only seem to be slightly better than 2.6. But I really appreciate the fact that you’re open-source and constantly striving to improve. Thanks, team.

Love seeing the focus shift from benchmark chasing to real-world coding workflows. Long-context instruction following is where a lot of models still struggle, so it's great to see improvements there. Excited to test this on an actual project.