Kimi K2.7 Code
- Input
- $0.95/M tok
- Output
- $4.00/M tok
- Blended
- $1.712/M tok · 3:1
- Speed
- 90tok/s
- Context
- 256Ktokens
- Cost per task
- ~$1.7/taskest.
Long-tail import from Artificial Analysis (2026-09-24); AA variant: Kimi K2.7 Code. Price = AA median host price. Card: "adopts the same native int4 quantization method as Kimi-K2-Thinking".
Rankings
Coding
Verified#70 / 137rank by quality42.4±8.1quality / 1002/7 benchmarks measuredWriting & chat
Verified#65 / 162rank by quality54.1±9.5quality / 1001/5 benchmarks measuredHard reasoning
Verified#62 / 218rank by quality61.4±3.7quality / 1003/4 benchmarks measuredAgents
Verified#57 / 187rank by quality44.7±4.3quality / 1004/7 benchmarks measured
Self-hostingEstimated
How we estimate →What it would cost to run these open weights yourself on rented GPUs, compared with the API price above.
- Hardware
- 16× H200 141GB
- FP8 weights
- Throughput
- ~26,263 tok/s
- many requests batched
- Price
- $0.28–2.34 /M tok
- busy → light use
- On your own machine
- Too large
- needs data-center GPUs
Assumptions (5)
- FP8 weights (1000B params, 32B active per token) + 25% KV-cache headroom ≈ 1250 GB
- 16× H200 141GB at $3.59–$7.91/GPU-hour on-demand (2026-09-24)
- ~26,263 output tok/s aggregate at batch 1111 (bandwidth-bound); MoE compute scales with active params
- Blended 3:1 input:output; prefill ~198,704 tok/s
- Low = 75% utilization at the low GPU price; high = 20% at the high price
Benchmark scores
~ italic, dashed = no published score yet, estimated from related benchmarks.
Coding
SWE-bench VerifiedEstimated
~#11 of 21 (estimated)~75.6%
- #1Claude Opus 596.0%
- #2Claude Sonnet 585.2%
- #10Muse Glimmer76.0%
- ~#11Kimi K2.7 CodeEstimated75.6%
- #11Xing4.0-29B-A4B75.0%
No published score — estimated from related benchmarks
SWE-bench Pro (Public)Estimated
~#17 of 24 (estimated)~55.4%
- #1Claude Fable 5.293.0%
- #2Claude Opus 5.589.9%
- #16Hy357.9%
- ~#17Kimi K2.7 CodeEstimated55.4%
- #17Inkling54.3%
No published score — estimated from related benchmarks
DeepSWE v1.1Estimated
~#37 of 46 (estimated)~51.1%
- #1Gemini 4 Argon78.8%
- #2DeepSeek V4.1 Flash 101777.0%
- #36Nex-N2.5-Pro55.8%
- ~#37Kimi K2.7 CodeEstimated51.1%
- #37Qwen3.8 Max (0902)51.0%
No published score — estimated from related benchmarks
Terminal-Bench 4.0Verified
#46 of 1011.0%
- #1Kimi K3.1 Pro67.2%
- #2Claude Sonnet 5.563.6%
- #46K2 Horizon 7B1.0%
- #46Kimi K2.7 Code1.0%
- #46Quasar 438B1.0%
artificialanalysis.ai · 2026-09-24
LiveCodeBenchEstimated
~#15 of 28 (estimated)~71.1%
- #1Qwen3.8-Omni-Flash92.6%
- #2Qwen3.8 Flash-Next91.9%
- #14Maple-Preview75.1%
- ~#15Kimi K2.7 CodeEstimated71.1%
- #15Mistral Small 464.0%
No published score — estimated from related benchmarks
SciCodeVerified
#52 of 11847.8%
- #1Claude Fable 5.267.7%
- #2Claude Opus 5.566.9%
- #50Solar Pro 448.0%
- #52Kimi K2.7 Code47.8%
- #52Nemotron 3.5 Super VL47.8%
artificialanalysis.ai · 2026-09-24
AA Coding Agent IndexEstimated
~#23 of 26 (estimated)~33.6
- #1Claude Opus 5.561.7
- #2Claude Opus 559.7
- #22Claude Haiku 5.537.3
- ~#23Kimi K2.7 CodeEstimated33.6
- #23Gemini 3.8 Flash33.3
No published score — estimated from related benchmarks
Writing & chat
IFBenchVerified
#54 of 13963.1%
- #1MiniMax-M382.9%
- #2Qwen3.8 2.4T A95B82.8%
- #53Nemotron 3 Nano Omni 30B A3B Reasoning63.2%
- #54Kimi K2.7 Code63.1%
- #55K2 Think V262.8%
artificialanalysis.ai · 2026-09-24
LMArena Text, Non-English (Elo)Estimated
~#39 of 57 (estimated)~1403 Elo
- #1Gemini 4 ArgonFew votes1512
- #2Claude Opus 5.51497
- #38Nemotron 3 Ultra1405
- ~#39Kimi K2.7 CodeEstimated1403
- #39Mistral Large 31397
No published score — estimated from related benchmarks
LMArena Text (Elo)Estimated
~#39 of 57 (estimated)~1419 Elo
- #1Gemini 4 Argon1525
- #2Claude Opus 5.51507
- #38Muse GlimmerFew votes1424
- ~#39Kimi K2.7 CodeEstimated1419
- #39Qwen3.5 122B A10B1417
No published score — estimated from related benchmarks
EQ-Bench Creative Writing v3 (Elo)Estimated
~#15 of 26 (estimated)~1755 Elo
- #1GPT-6 Astra2173
- #2Claude Fable 5.12162
- #14Claude Sonnet 51794
- ~#15Kimi K2.7 CodeEstimated1755
- #15Gemini 3.8 Flash1748
No published score — estimated from related benchmarks
Hard reasoning
GPQA DiamondVerified
#34 of 19289.6%
- #1GPT-6 Astra96.1%
- #2Gemini 3.8 Flash95.3%
- #33Hy389.7%
- #34Kimi K2.7 Code89.6%
- #35Nemotron 3.5 Super VL89.5%
artificialanalysis.ai · 2026-09-24
Humanity's Last ExamVerified
#46 of 19835.0%
- #1Claude Fable 5.274.3%
- #2Claude Opus 5.561.4%
- #45Qwen3.8 Flash-Next NVFP435.4%
- #46Kimi K2.7 Code35.0%
- #47Apodex 1.134.1%
artificialanalysis.ai · 2026-09-24
AIME (latest)Estimated
~#7 of 34 (estimated)~94.6%
- #1GLM-5.3 NVFP499.5%
- #2Beam 1.0 501B A23B97.7%
- #6Muse Glimmer94.7%
- ~#7Kimi K2.7 CodeEstimated94.6%
- #7Nova 2.0 Lite94.3%
No published score — estimated from related benchmarks
Agents
τ²-bench (Telecom)Verified
#13 of 11990.1%
- #1Step 3.7 Flash98.5%
- #2DeepSeek-V4-Pro-0813-nvfp4-DSpark98.3%
- #12MiMo-V2.590.6%
- #13Kimi K2.7 Code90.1%
- #13Qwen3.8 Flash-Next NVFP490.1%
artificialanalysis.ai · 2026-09-24
OSWorld-VerifiedEstimated
~#11 of 15 (estimated)~68.9%
- #1Kimi K384.8%
- #2Qwen3.8 27B84.3%
- #10Nex-N2.5-Mini71.2%
- ~#11Kimi K2.7 CodeEstimated68.9%
- #11Muse Glimmer65.9%
No published score — estimated from related benchmarks
OSWorld 2.0Estimated
~last of 5 (estimated)below measured range (<47.5%)
No published score — estimated from related benchmarks
BrowseCompEstimated
~#19 of 22 (estimated)~69.4%
- #1Atria Dawn Preview92.5%
- #2GPT-6 Astra91.5%
- #18Nemotron 3.5 Bolt 74B-A9B70.0%
- ~#19Kimi K2.7 CodeEstimated69.4%
- #19Mistral Medium 3.548.6%
No published score — estimated from related benchmarks
AutomationBench-AAVerified
#37 of 8424.5%
- #1Claude Fable 5.276.4%
- #2Muse Wonder Full71.3%
- #36Gemini 3.5 Flash-Lite25.0%
- #37Kimi K2.7 Code24.5%
- #38Quasar 438B23.9%
artificialanalysis.ai · 2026-09-24