← Back to explorer
KimiReleased 2026-05Open weights
Kimi K2.6
Moonshot's long-context specialist with competitive open-weight intelligence scores.
Context
2M
Speed
70 t/s
Price /M
$0.50 / $2
Access
open weights
When to use it
Huge document analysis and Chinese/English long-context apps.
Watch-outs
Frontier closed models still lead on hardest agent benches.
Long contextBest valueWriting
Benchmarks
Arena Elo—
Human preference ranking from blind pairwise chats. Higher is better; top frontier models cluster within ~50–80 Elo.
AA Intelligence Index43
Artificial Analysis composite across agents, coding, science, and general evaluations (v4.1 weighting).
SWE-bench Verified—
Percent of real GitHub issues resolved end-to-end. Strong signal for agentic coding usefulness.
GPQA Diamond—
PhD-level science questions. Separates frontier reasoning models better than saturated knowledge tests.
MMLU-Pro—
Harder multi-choice knowledge/reasoning suite than classic MMLU.
Humanity's Last Exam—
Frontier closed-ended academic difficulty across many domains.