GoTry AI

Kimi K2.6

Language Moonshot AI Available Released Apr 21, 2026 Partly verified
Model ID
Context
262.14K
262K max output
Input price
$0.95
per 1M tokens · Moonshot AI Platform
Output price
$4.00
per 1M tokens
Epoch Capabilities Index
151
#38 of 71 listed
LMArena Text
1,461
#33 of 79 listed

Where to run it

3 offerings · prices as listed
MeterTierPrice
Moonshot AI Platform (opens in a new tab) Official Global · USD kimi-k2.6
InputStandard $0.95 / 1M tokens
OutputStandard $4.00 / 1M tokens
Cache readStandard $0.16 / 1M tokens
Moonshot AI Platform (opens in a new tab) Official China · CNY kimi-k2.6
InputStandard ¥6.50 / 1M tokens
OutputStandard ¥27.00 / 1M tokens
Cache readStandard ¥1.10 / 1M tokens
SiliconFlow (opens in a new tab) China · CNY Pro/moonshotai/Kimi-K2.6
InputStandard ¥6.50 / 1M tokens
OutputStandard ¥27.00 / 1M tokens
Cache readStandard ¥1.10 / 1M tokens

Vendor-reported scores

Published by Moonshot AI, under the conditions it states
BenchmarkSettingScore
Humanity's Last Examfull set, no tools, thinking34.7%
full set, with search/code/browsing tools, thinking54%
BrowseCompthinking, with tools, discard-all context management83.2%
Agent Swarm mode86.3%
OSWorld-Verifiedthinking73.1%
Terminal-Bench 2.0Terminus-2 harness, preserve thinking66.7%
SWE-bench Proin-house SWE-agent-based harness, avg of 10 runs58.6%
SWE-bench Verifiedin-house SWE-agent-based harness, avg of 10 runs80.2%
LiveCodeBenchv6, thinking89.6%
AIME 2026thinking96.4%
GPQA Diamondthinking90.5%
MMMU-Prono tools, thinking, avg@379.4%
with Python tool, thinking, avg@380.1%

Cited scores

From third-party leaderboards, not measured by us
  • Epoch Capabilities Index 151

    #38 of 71 listed models · CI 149.2–152.8

    Epoch AI, 'Capabilities & benchmarking'. Published online at epoch.ai. Retrieved from 'https://epoch.ai/benchmarks'. Licensed CC BY 4.0. · License · as of Sep 26, 2026 · changes we made

  • LMArena Text 1,461

    #33 of 79 listed models · CI 1,457–1,465 · 39,971 votes

    LMArena (Arena), leaderboard-dataset on Hugging Face, licensed CC BY 4.0 · License · as of Sep 25, 2026 · changes we made

  • Epoch AI · FrontierMath Tiers 1–3 57.2%

    #32 of 56 listed models · ±2.94

    Epoch AI, 'Capabilities & benchmarking'. Published online at epoch.ai. Retrieved from 'https://epoch.ai/benchmarks'. Licensed CC BY 4.0. · License · as of Sep 26, 2026 · changes we made

  • Epoch AI · GPQA Diamond 90.8%

    #24 of 64 listed models · ±1.72

    Epoch AI, 'Capabilities & benchmarking'. Published online at epoch.ai. Retrieved from 'https://epoch.ai/benchmarks'. Licensed CC BY 4.0. · License · as of Sep 26, 2026 · changes we made

  • Epoch AI · SWE-bench Verified 76.7%

    #9 of 23 listed models · ±1.92

    Epoch AI, 'Capabilities & benchmarking'. Published online at epoch.ai. Retrieved from 'https://epoch.ai/benchmarks'. Licensed CC BY 4.0. · License · as of Sep 26, 2026 · changes we made

  • LMArena Text · Chinese 1,517

    #24 of 79 listed models · CI 1,504–1,530 · 2,343 votes

    LMArena (Arena), leaderboard-dataset on Hugging Face, licensed CC BY 4.0 · License · as of Sep 25, 2026 · changes we made

  • LMArena Text · Coding 1,516

    #30 of 79 listed models · CI 1,509–1,523 · 11,092 votes

    LMArena (Arena), leaderboard-dataset on Hugging Face, licensed CC BY 4.0 · License · as of Sep 25, 2026 · changes we made

  • LMArena Vision 1,280

    #19 of 49 listed models · CI 1,273–1,287 · 15,347 votes

    LMArena (Arena), leaderboard-dataset on Hugging Face, licensed CC BY 4.0 · License · as of Sep 13, 2026 · changes we made