MDL
Kimi K2.6
Kimi
Verified against Artificial Analysis · Jul 13, 2026
Capability
95
percentile index
Price /M
$0.95 / $4
in / out
Context
262.1K
tokens
Avg score
66.6
7 benchmarks
AA Intelligence
44.2
index
Speed
43 tok/s
TTFT 1.2s
Released
Apr 20, 2026
About
Kimi K2.6 is a open-weights model in the Kimi family from Kimi. Benchmarked on 7 evals, averaging 66.6.
Benchmark scores · 7
avg 66.6 — higher is betterThe research behind this model
all papers mentioning it →Scaling the Horizon, Not the Parameters: Reaching Trillion-Parameter Performance with a 35B Agent▲ 98 on HF · Jun 29, 2026ComBench: A Benchmark for Rigorous Proof Reasoning and Constructive Realization in Olympiad-Level Combinatorics▲ 19 on HF · Jun 9, 2026Better Accuracies, Worse Reasoning: A Step-Level Audit of Medical Chain-of-Thought DistillationMay 27, 2026HTMLCure: Turning Browser Experience into State Guided Repair for Interactive HTMLMay 26, 2026SEC-bench Pro: Can Language Models Solve Long-Horizon Software Security Tasks?May 26, 2026
Mentions matched by name in title/abstract — from the arXiv + HF daily corpus.
Performance & price
Output speed43 tok/s
Latency (TTFT)1.2s
First answer1m 45s
Price in / out$0.95 / $4 per 1M
Blended price$1.71 / 1M
Coding index61.8
Median across API providers, via Artificial Analysis. Blended = 3:1 input:output. For reasoning models, latency includes thinking time. Methodology →
History
full ledger →Capability over time
Append-only ledger — every observed change to this model's numbers.
API providers
Artificial Analysis$4/M