Kimi K3 Flash Benchmarks, Pricing & Rankings
Moonshot AI · 2026-08-02 · Open · Current
Snapshot 2026-10-14 · updated weekly
Kimi K3 Flash ranks #33 of 42 on the AMR leaderboard.
Kimi K3 Flash benchmark scores
| GPQA Diamond | 70.2% | |
| MMLU-Pro | 68.9% | |
| SWE-Bench Verified | 42.6% | |
| AIME 2025 | 67.8% | |
| LiveCodeBench v6 | 58.4% | |
| Arena Elo | 1325 |
Kimi K3 Flash price, speed & context
Input price
$0.14
per 1M tokens
Output price
$0.55
per 1M tokens
Speed
296
tok/s
Context
256K
tokens
About Kimi K3 Flash
Kimi K3 Flash carries the Kimi long-context DNA at flash pricing and is a strong open alternative to Gemini 3.8 Flash.
Models around Kimi K3 Flash in the rankings
More Moonshot AI models
Kimi K3 Flash FAQ
Where does Kimi K3 Flash rank?
Kimi K3 Flash ranks #33 of 42 tracked AI models on the AMR aggregate as of October 2026, with an aggregate score of 76.0. Its strongest dimension is GPQA Diamond at 70.2%.
How much does Kimi K3 Flash cost?
Kimi K3 Flash costs $0.14 per million input tokens and $0.55 per million output tokens on the standard API. At a typical 1:3 input/output agent workload, that blends to roughly $0.45 per million tokens.
What is the Kimi K3 Flash context window?
Kimi K3 Flash supports a 256K token context window and generates at a median 296 output tokens per second. That context fits roughly 171 standard documents in a single prompt.
Is Kimi K3 Flash open source?
Yes — Kimi K3 Flash ships open weights that you can download and self-host or serve through any compatible inference provider.
What is better than Kimi K3 Flash?
MiMo-V2.6-Pro ranks one place higher at #32 with an AMR score of 78.0. Kimi K3 Flash still wins 0 of the tracked dimensions head-to-head — check the comparison table to see exactly which.