Skip to content

Kimi K2.7 Code

Moonshot AIOpen weightsReasoningVerifiedReleased Jun 12, 2026Input: text, image
Compare with Nemotron 3.5 Super VL 120B A12BSource scores ↗OpenRouter ↗
Overall score
49.4
Rank 103 of 222 · 42.2–56.5
Context window
256K
256,000 tokens
Price per 1M tokens
$0.95 in · $4.00 out
Source: BenchLM
Blended price
$1.71
3:1 input:output tokens
Output speed
—
Not measured yet

Category scores

Scores per capability area with the model's rank among ranked models in that category.

  1. 1Reasoning79.5
  2. 2Instruction following#6376.6
  3. 3Agentic & tool use#7268.8
  4. 4Knowledge63.7
  5. 5Math58.3
  6. 6Coding#6347.7
Higher is better. #N is the model's rank in that category, where it is eligible to be ranked.

Benchmark results (11)

As reported in system cards, papers and public evaluations. Position compares this model with every other model reporting the same benchmark.

Coding

ProgramBench53.6#9 of 15
OpenHarmony Bench52.1#11 of 12
MLS-Bench Lite35.1#4 of 4
Kimi Code Bench v262.0#2 of 2

Agentic & tool use

MCP Atlas76.0#16 of 42
Kimi Claw 24/746.9#1 of 1
MCP Mark Verified81.1#1 of 1

Math

FrontierMath v2 (Tiers 1-3)54.035#39 of 64
FrontierMath v2 (Tier 4)12.195#43 of 51

Multimodal

Design Arena Website1265#33 of 91

Pricing by source

USD per 1M tokens.

SourceInputOutputCached in
List price (BenchLM)$0.95$4.00$0.19
OpenRouter moonshotai/kimi-k2.7-code$0.67$3.35$0.18

Moonshot's Kimi API platform lists kimi-k2.7-code at $0.95 cache-miss input / $4.00 output per million tokens, with cache-hit input priced at $0.19 per million tokens (chat pricing page, read September 25, 2026).

Arena ratings

Human-preference ratings from LMArena. Best-rated variant shown.

WebDev (coding)1474#69 · 5K votes

Open weights

From the Hugging Face repository.

Parameters
1.03T
Licence
other
Downloads (30 days)
107.8K

Speed

Measured by us through OpenRouter (median of trials).

Not measured yet.

Related models

Same family

Similar score