Language modelActive

Kimi K2.7 Code

Moonshot AI

Released: June 2026
Data date: September 8, 2026

Speed: 63.1 tokens/s
Output throughput
Price: $0.95 · $4
Input · Output / 1M tokens
Input: Text, Image, Video
Output: Text

What is distinctive about Kimi K2.7 Code is its explicit focus on long software projects. Moonshot combines 1 trillion total parameters and 32 billion active parameters with a 256,000-token context window, tool calls, and multimodal input for text, images, and experimental video.

Reasoning is always enabled, and preserve_thinking is part of the intended usage mode. The resulting output is correspondingly more verbose.

Specifications and access

Specification	Value and source
Weights	Open weightsSource
Access	API, LocalSource
Parameters	1TSource
Active parameters	32BSource
Context window	262,144 tokensSource
Notes	1T total, 32B active, 256K context, thinking always enabledSource
License	modified MITSource
Parameters	1,000 BSource
Active parameters	32 BSource
Architecture	MoE with MLA and MoonViTSource
Output	TextSource
Tool calling	YesSource
Input	Text, Image, Video (Video is experimental and supported by the official API.)Source
Reasoning mode	Thinking mode; preserve_thinking is mandatory.Source

Published benchmarks

Coding

Code Migration

Overall

1.Claude Sonnet 5.569.83%

2.GPT-6 Astra67.74%

3.Claude Opus 5.566.65%

4.Claude Opus 557.47%

5.GPT-6 Sol57.2%

6.Claude Fable 555.07%

7.Claude Fable 5.154.61%

8.GPT-5.6 Sol52.92%

9.GPT-5.6 Terra47.8%

10.Claude Opus 4.847.25%

11.DeepSeek-V4.1-Flash45.62%

12.GPT-5.545.16%

13.Grok 4.744.82%

14.Grok 4.644.57%

15.GPT-5.6 Luna44.55%

16.Claude Sonnet 544.39%

17.GLM-5.344.22%

18.Claude Opus 4.743.88%

19.GPT-6 Luna42.55%

20.Claude Sonnet 4.639.89%

21.GLM-5.237.87%

22.Grok 4.536.6%

23.Gemini 3.8 Flash36.55%

24.GPT-5.434.98%

25.Gemini 3.7 Flash34.8%

26.Gemini 3.6 Flash30.93%

27.Kimi K2.627.77%

28.Gemini 3.5 Flash26.75%

29.DeepSeek-V4-Pro26.2%

30.GLM-5.125.77%

31.Kimi K2.7 Code25.39%

32.Qwen 3.8 Max 090223.96%

33.MiMo-V2.5-Pro21.56%

34.GLM-5.3-Flash20.52%

35.MiniMax M319.93%

36.Gemini 3.1 Pro Preview17.31%

37.Kimi K316.1%

38.GPT-5.4 nano14.47%

39.MiMo-V2.514.23%

40.Qwen 3.8 27B14.16%

41.Inkling Small13.68%

42.Qwen 3.7 Max13.07%

43.GPT-5.4 mini12.94%

44.Qwen 3.7 Plus12.86%

45.Inkling11.79%

46.MiniMax M2.78.69%

47.Kimi K2.56.96%

48.Grok 4.36.8%

49.Gemini 3 Flash Preview6.39%

50.Gemini 3.5 Flash-Lite6.15%

51.Mistral Medium 3.55.13%

52.Nemotron 3 Ultra4.91%

53.Gemini 3.1 Flash-Lite4.61%

54.Mercury 2.54.49%

55.Nemotron 3.5 Lightning2.95%

56.Grok 4.20 Reasoning0.31%

57.Ling 3.0 Flash0%

higher is betterAs of September 29, 2026Scale: 0% - 100%

Source: Vals AI

CC BY 4.0

gradually.ai

Methodology and context

Comparison cohort: vals-code-migration:1:overall
Metric: accuracy
Scale: 0-100
Participants: 57
Methodology and context: Source model ID: kimi/kimi-k2.7-code. Source model name: Kimi K2.7 Code. Evaluator: Vals AI. Dataset type: private. Leaderboard date: 2026-09-27. Latency in seconds: 5945.669. Cost per task in USD: 5.040913. Source ID: vals-ai. Evidence capture ID: vals-code-migration-2026-09-29-f0b317d5bed3. Source payload hash: f0b317d5bed3a2654a9ea39762d5e57f4649306adce3e6103e845ee1b9b94add. Parser version: vals-astro-v2. Imported at: 2026-09-29

Source: Vals AI

LiveCodeBench v6

Sub-task	Kimi K2.7 Code (This model)	Claude Opus 5	GLM-5.1	GLM-5.2
Easy	97.83%	99.07% (best value in this row)	98.75%	97.21%
Hard	60.86%	77.43% (best value in this row)	57.43%	37.14%
Medium	87.47%	90.6% (best value in this row)	87.96%	74.15%

higher is betterAs of August 11, 2026Source: Vals AIbars scaled within each row, not across rows

Methodology and context

Metric: accuracy

LiveCodeBench v6

Overall

1.Claude Fable 5.190.52%

2.Claude Fable 589.78%

3.Gemini 3.8 Flash89.48%

4.Claude Opus 589.03%

5.Gemini 3.7 Flash88.65%

6.Gemini 3.1 Pro Preview88.49%

7.Grok 4.688.22%

8.Gemini 3.6 Flash88.08%

9.Qwen 3.8 Max 090287.85%

10.Claude Opus 4.887.82%

11.Gemini 3.5 Flash87.6%

12.DeepSeek-V4-Pro87.48%

13.Grok 4.587.35%

14.GPT-5.3-Codex87.31%

15.Kimi K387.19%

16.Qwen 3.7 Max87.06%

17.Kimi K2.686.77%

18.GPT-5 mini86.61%

19.Nemotron 3 Ultra85.98%

20.Inkling Small85.93%

21.GPT-5.6 Terra85.93%

22.GPT-585.91%

23.Gemini 3 Flash Preview85.59%

24.Inkling85.52%

25.GPT-5.585.3%

26.Claude Opus 4.785.07%

27.Grok 4.384.49%

28.Grok 4.20 Reasoning84.27%

29.GPT-5.484.14%

30.GPT-5.4 nano84.01%

31.Qwen 3.8 27B84%

32.Ling 3.0 Flash83.99%

33.o383.91%

34.Kimi K2.583.87%

35.GPT OSS 120B83.23%

36.GPT-5.6 Sol82.6%

37.Claude Sonnet 582.43%

38.GLM-4.782.23%

39.o4-mini82.21%

40.MiniMax M382.15%

41.Claude Sonnet 4.682.09%

42.Kimi K2.7 Code82.05%

43.GLM-581.87%

44.MiniMax M2.181.76%

45.MiMo-V2.581.51%

46.GPT-5.4 mini81.47%

47.GLM-5.181.38%

48.MiMo-V2.5-Pro81.35%

49.GLM-4.681.04%

50.GLM-5.380.54%

51.GLM-5.3-Flash80.51%

52.GPT OSS 20B80.39%

53.Gemini 3.1 Flash-Lite80.12%

54.MiniMax M2.779.93%

55.MiniMax M2.579.21%

56.Gemini 3.5 Flash-Lite79.01%

57.Claude Opus 4.575.03%

58.o3-mini71.48%

59.Kimi K2 071170.45%

60.DeepSeek-R170.22%

61.GPT-5 nano70.22%

62.DeepSeek-V3.269.86%

63.GLM-5.269.5%

64.GLM-4.567.45%

65.DeepSeek-V3 032465.48%

66.Kimi K2 Thinking63.15%

67.GPT-4.1 mini58.16%

68.Mistral Large 355.34%

69.GPT-4.154.67%

70.o150.26%

71.GPT-4o43.44%

72.GPT-4.1 nano42.72%

73.Llama 4 Scout38.54%

74.Command A35.07%

75.Mistral Small 3.131.82%

76.GPT-4o mini26.42%

77.Command R+18.24%

higher is betterAs of September 29, 2026Scale: 0% - 100%

Source: Vals AI

CC BY 4.0

gradually.ai

Methodology and context

Comparison cohort: vals-lcb:1:overall
Metric: accuracy
Scale: 0-100
Participants: 77
Methodology and context: Source model ID: kimi/kimi-k2.7-code. Source model name: Kimi K2.7 Code. Evaluator: Vals AI. Dataset type: public. Leaderboard date: 2026-09-01. Latency in seconds: 214.178. Cost per task in USD: 0.027349. Source ID: vals-ai. Evidence capture ID: vals-lcb-2026-09-29-b6ee1006a41a. Source payload hash: b6ee1006a41aab0c68eef9d3e42a2151634fffaaeb6bdc2230a6d02994198a59. Parser version: vals-astro-v2. Imported at: 2026-09-29

Source: Vals AI

ProgramBench

Overall

1.Claude Opus 5.518.5%

2.Claude Fable 5.17%

3.GPT-6 Astra5.5%

4.Claude Opus 53%

5.Claude Fable 52%

5.GPT-6 Sol2%

5.Kimi K32%

8.GLM-5.31.5%

8.GPT-5.6 Sol1.5%

10.Claude Opus 4.81%

10.Gemini 3.8 Flash1%

12.Claude Sonnet 4.60.5%

12.GLM-5.20.5%

12.GPT-5.50.5%

12.GPT-5.6 Terra0.5%

12.GPT-6 Luna0.5%

12.Grok 4.70.5%

12.Inkling Small0.5%

19.Claude Opus 4.70%

19.Claude Sonnet 50%

19.DeepSeek-V4-Pro0%

19.Gemini 3 Flash Preview0%

19.Gemini 3.1 Flash-Lite0%

19.Gemini 3.1 Pro Preview0%

19.Gemini 3.5 Flash0%

19.Gemini 3.5 Flash-Lite0%

19.Gemini 3.6 Flash0%

19.Gemini 3.7 Flash0%

19.GLM-5.10%

19.GLM-5.3-Flash0%

19.GPT-5.40%

19.GPT-5.4 mini0%

19.GPT-5.6 Luna0%

19.Grok 4.30%

19.Grok 4.50%

19.Inkling0%

19.Kimi K2.60%

19.Kimi K2.7 Code0%

19.MiniMax M2.70%

19.Nemotron 3 Ultra0%

19.Qwen 3.8 27B0%

19.Qwen 3.8 Max 09020%

higher is betterAs of September 29, 2026Scale: 0% - 100%

Source: Vals AI

CC BY 4.0

gradually.ai

Methodology and context

Comparison cohort: vals-programbench:1:overall
Metric: accuracy
Scale: 0-100
Participants: 42
Methodology and context: Source model ID: kimi/kimi-k2.7-code. Source model name: Kimi K2.7 Code. Evaluator: Vals AI. Dataset type: public. Leaderboard date: 2026-09-27. Latency in seconds: 3860.332. Cost per task in USD: 3.185154. Source ID: vals-ai. Evidence capture ID: vals-programbench-2026-09-29-bff20a0d17ec. Source payload hash: bff20a0d17ec279ecc2de4a40b1e08d0eb38e155e58aaf585a09af58807a4e0d. Parser version: vals-astro-v2. Imported at: 2026-09-29

Source: Vals AI

SWE-bench Verified

Sub-task	Kimi K2.7 Code (This model)	Claude Opus 5
<15 min fix	88.66%	98.45% (best value in this row)
>4 hours	33.33%	100% (best value in this row)
1-4 hours	50%	90.48% (best value in this row)
15 min - 1 hour	75.48%	96.94% (best value in this row)

higher is betterAs of August 11, 2026Source: Vals AIbars scaled within each row, not across rows

Methodology and context

Metric: accuracy

SWE-bench Verified

Overall

1.Claude Opus 597%

2.GPT-5.6 Sol96.2%

3.Grok 4.695.6%

4.GLM-5.395.4%

4.GPT-5.6 Terra95.4%

6.Claude Fable 595%

7.Kimi K393.4%

8.GPT-5.6 Luna93%

9.GLM-5.3-Flash92%

10.Claude Opus 4.888.6%

11.Grok 4.586.6%

12.Qwen 3.8 27B86%

13.Qwen 3.8 Max 090285.6%

14.GLM-5.282.8%

15.GPT-5.582.6%

16.Inkling Small82.2%

17.Claude Opus 4.782%

18.Gemini 3.7 Flash80.8%

19.Gemini 3.8 Flash80%

20.Claude Sonnet 579.6%

20.Gemini 3.6 Flash79.6%

22.Gemini 3.1 Pro Preview78.8%

22.Gemini 3.5 Flash78.8%

24.GPT-5.478.2%

24.Kimi K2.7 Code78.2%

26.GPT-5.3-Codex78%

27.Inkling77.6%

28.Claude Sonnet 4.677.4%

28.DeepSeek-V4-Pro77.4%

30.GLM-5.176.4%

31.Kimi K2.676.2%

32.Gemini 3 Flash Preview75%

32.Gemini 3.5 Flash-Lite75%

32.MiniMax M375%

35.MiniMax M2.174.8%

36.MiniMax M2.574.2%

37.MiMo-V2.5-Pro74%

38.MiniMax M2.773.8%

39.GPT-5.4 mini73%

40.Grok 4.20 Reasoning72.2%

41.GLM-571.4%

41.Grok 4.371.4%

43.MiMo-V2.571%

44.Kimi K2.570%

44.Qwen 3.6 27B70%

46.GPT-5.4 nano69.8%

47.GLM-4.769.4%

48.GPT-569%

48.Nemotron 3 Ultra69%

50.Qwen 3.7 Max68.8%

51.Mistral Medium 3.566.4%

52.Ling 3.0 Flash65.2%

53.Gemini 3.1 Flash-Lite62.8%

54.GPT-5 mini60.8%

55.Kimi K2 Thinking60.2%

56.Gemini 2.5 Pro54.4%

57.Nemotron 3.5 Lightning52.8%

58.Mistral Large 341.4%

59.GPT OSS 120B33.6%

60.Command A7.8%

higher is betterAs of September 29, 2026Scale: 0% - 100%

Source: Vals AI

CC BY 4.0

gradually.ai

Methodology and context

Comparison cohort: vals-swebench:1:overall
Metric: accuracy
Scale: 0-100
Participants: 60
Methodology and context: Source model ID: kimi/kimi-k2.7-code. Source model name: Kimi K2.7 Code. Evaluator: Vals AI. Dataset type: public. Leaderboard date: 2026-09-01. Latency in seconds: 896.71. Cost per task in USD: 0.265276. Source ID: vals-ai. Evidence capture ID: vals-swebench-2026-09-29-20166fd31f31. Source payload hash: 20166fd31f31a0b278e6471c59ece1600abba838f3db178873d3a1c762a6f44f. Parser version: vals-astro-v2. Imported at: 2026-09-29

Source: Vals AI

SkillsBench

Overall

1.DeepSeek-V4.1-Flash69.8%

2.Grok 4.566.03%

3.Gemini 3.7 Flash65.89%

4.GPT-5.562.21%

5.Claude Fable 5.161.55%

6.GPT-5.6 Luna60.45%

7.Claude Opus 560.44%

8.Claude Opus 4.859.23%

9.GPT-5.6 Terra58.9%

10.Gemini 3.8 Flash57.99%

11.Grok 4.655.77%

12.Qwen 3.7 Plus54.3%

13.GPT-5.6 Sol54.1%

14.Gemini 3.5 Flash52.74%

15.GPT-5.451.71%

16.MiniMax M351.5%

17.DeepSeek-V4-Pro51.27%

18.Kimi K2.7 Code50.04%

19.Claude Sonnet 4.649.05%

20.GLM-5.347.51%

21.Claude Sonnet 546.48%

22.GLM-5.245.08%

23.Qwen 3.8 Max 090242.01%

24.Grok 4.340.64%

25.GLM-5.3-Flash40.16%

26.Qwen 3.8 27B38.11%

27.Inkling Small33.58%

28.Ling 3.0 Flash27.95%

29.Inkling26.09%

30.Mercury 2.518.06%

higher is betterAs of September 29, 2026Scale: 0% - 100%

Source: Vals AI

CC BY 4.0

gradually.ai

Methodology and context

Comparison cohort: vals-skillsbench:1:overall
Metric: accuracy
Scale: 0-100
Participants: 30
Methodology and context: Source model ID: kimi/kimi-k2.7-code. Source model name: Kimi K2.7 Code. Evaluator: Vals AI. Dataset type: public. Leaderboard date: 2026-09-27. Harness: OpenHands. Latency in seconds: 803.827. Cost per task in USD: 0.443192. Source ID: vals-ai. Evidence capture ID: vals-skillsbench-2026-09-29-38ec42553ceb. Source payload hash: 38ec42553ceb08e4efe7336723e87e67325977245b113ef7b86401dc72b0481a. Parser version: vals-astro-v2. Imported at: 2026-09-29

Source: Vals AI

Recorded measurement details

Code Migration: Overall (Show measurement, test conditions, and source)

Source value: 25.392
Score: 25.392
Metric: accuracy
Unit: %
Benchmark version: 1
Category: coding
Task: overall
Task label: Overall
Direction: Higher is better
Comparison cohort: vals-code-migration:1:overall
Source type: independent-evaluator
Evaluator: Vals AI
Status: active
Retrieved at: 2026-09-29
Methodology: Source model ID: kimi/kimi-k2.7-code. Source model name: Kimi K2.7 Code. Evaluator: Vals AI. Dataset type: private. Leaderboard date: 2026-09-27. Latency in seconds: 5945.669. Cost per task in USD: 5.040913. Source ID: vals-ai. Evidence capture ID: vals-code-migration-2026-09-29-f0b317d5bed3. Source payload hash: f0b317d5bed3a2654a9ea39762d5e57f4649306adce3e6103e845ee1b9b94add. Parser version: vals-astro-v2. Imported at: 2026-09-29

Source Vals AI

LiveCodeBench v6: Easy (Show measurement, test conditions, and source)

Source value: 97.826
Score: 97.826
Metric: accuracy
Unit: %
Benchmark version: 1
Category: coding
Task: easy
Task label: Easy
Direction: Higher is better
Comparison cohort: vals-lcb:1:easy
Source type: independent-evaluator
Evaluator: Vals AI
Status: active
Retrieved at: 2026-08-11
Methodology: Source model ID: kimi/kimi-k2.7-code. Source model name: Kimi K2.7 Code. Provider reported by source: Moonshot AI. Evaluator: Vals AI. Dataset type: public. Leaderboard date: 2026-08-09. Latency in seconds: 70.383. Standard error: 0.813. Cost per task in USD: 0.002724. Source ID: vals-ai. Evidence capture ID: vals-lcb-2026-08-11-0342bcc364e4. Source payload hash: 0342bcc364e4426ffb24589c2752c9225be61fbd26db8deba5bdab9775ce5a75. Parser version: vals-astro-v2. Imported at: 2026-08-11

Source Vals AI

LiveCodeBench v6: Hard (Show measurement, test conditions, and source)

Source value: 60.857
Score: 60.857
Metric: accuracy
Unit: %
Benchmark version: 1
Category: coding
Task: hard
Task label: Hard
Direction: Higher is better
Comparison cohort: vals-lcb:1:hard
Source type: independent-evaluator
Evaluator: Vals AI
Status: active
Retrieved at: 2026-08-11
Methodology: Source model ID: kimi/kimi-k2.7-code. Source model name: Kimi K2.7 Code. Provider reported by source: Moonshot AI. Evaluator: Vals AI. Dataset type: public. Leaderboard date: 2026-08-09. Latency in seconds: 388.241. Standard error: 2.609. Cost per task in USD: 0.060639. Source ID: vals-ai. Evidence capture ID: vals-lcb-2026-08-11-0342bcc364e4. Source payload hash: 0342bcc364e4426ffb24589c2752c9225be61fbd26db8deba5bdab9775ce5a75. Parser version: vals-astro-v2. Imported at: 2026-08-11

Source Vals AI

LiveCodeBench v6: Medium (Show measurement, test conditions, and source)

Source value: 87.467
Score: 87.467
Metric: accuracy
Unit: %
Benchmark version: 1
Category: coding
Task: medium
Task label: Medium
Direction: Higher is better
Comparison cohort: vals-lcb:1:medium
Source type: independent-evaluator
Evaluator: Vals AI
Status: active
Retrieved at: 2026-08-11
Methodology: Source model ID: kimi/kimi-k2.7-code. Source model name: Kimi K2.7 Code. Provider reported by source: Moonshot AI. Evaluator: Vals AI. Dataset type: public. Leaderboard date: 2026-08-09. Latency in seconds: 183.911. Standard error: 1.692. Cost per task in USD: 0.018683. Source ID: vals-ai. Evidence capture ID: vals-lcb-2026-08-11-0342bcc364e4. Source payload hash: 0342bcc364e4426ffb24589c2752c9225be61fbd26db8deba5bdab9775ce5a75. Parser version: vals-astro-v2. Imported at: 2026-08-11

Source Vals AI

LiveCodeBench v6: Overall (Show measurement, test conditions, and source)

Source value: 82.05
Score: 82.05
Metric: accuracy
Unit: %
Benchmark version: 1
Category: coding
Task: overall
Task label: Overall
Direction: Higher is better
Comparison cohort: vals-lcb:1:overall
Source type: independent-evaluator
Evaluator: Vals AI
Status: active
Retrieved at: 2026-09-29
Methodology: Source model ID: kimi/kimi-k2.7-code. Source model name: Kimi K2.7 Code. Evaluator: Vals AI. Dataset type: public. Leaderboard date: 2026-09-01. Latency in seconds: 214.178. Cost per task in USD: 0.027349. Source ID: vals-ai. Evidence capture ID: vals-lcb-2026-09-29-b6ee1006a41a. Source payload hash: b6ee1006a41aab0c68eef9d3e42a2151634fffaaeb6bdc2230a6d02994198a59. Parser version: vals-astro-v2. Imported at: 2026-09-29

Source Vals AI

ProgramBench: Overall (Show measurement, test conditions, and source)

Source value: 0
Score: 0
Metric: accuracy
Unit: %
Benchmark version: 1
Category: coding
Task: overall
Task label: Overall
Direction: Higher is better
Comparison cohort: vals-programbench:1:overall
Source type: independent-evaluator
Evaluator: Vals AI
Status: active
Retrieved at: 2026-09-29
Methodology: Source model ID: kimi/kimi-k2.7-code. Source model name: Kimi K2.7 Code. Evaluator: Vals AI. Dataset type: public. Leaderboard date: 2026-09-27. Latency in seconds: 3860.332. Cost per task in USD: 3.185154. Source ID: vals-ai. Evidence capture ID: vals-programbench-2026-09-29-bff20a0d17ec. Source payload hash: bff20a0d17ec279ecc2de4a40b1e08d0eb38e155e58aaf585a09af58807a4e0d. Parser version: vals-astro-v2. Imported at: 2026-09-29

Source Vals AI

SkillsBench: Overall (Show measurement, test conditions, and source)

Source value: 50.036
Score: 50.036
Metric: accuracy
Unit: %
Benchmark version: 1
Category: agentic
Task: overall
Task label: Overall
Direction: Higher is better
Comparison cohort: vals-skillsbench:1:overall
Source type: independent-evaluator
Evaluator: Vals AI
Status: active
Retrieved at: 2026-09-29
Methodology: Source model ID: kimi/kimi-k2.7-code. Source model name: Kimi K2.7 Code. Evaluator: Vals AI. Dataset type: public. Leaderboard date: 2026-09-27. Harness: OpenHands. Latency in seconds: 803.827. Cost per task in USD: 0.443192. Source ID: vals-ai. Evidence capture ID: vals-skillsbench-2026-09-29-38ec42553ceb. Source payload hash: 38ec42553ceb08e4efe7336723e87e67325977245b113ef7b86401dc72b0481a. Parser version: vals-astro-v2. Imported at: 2026-09-29
Comparison methodology: Harness: OpenHands

Source Vals AI

SWE-bench Verified: <15 min fix (Show measurement, test conditions, and source)

Source value: 88.66
Score: 88.66
Metric: accuracy
Unit: %
Benchmark version: 1
Category: coding
Task: <15 min fix
Task label: <15 min fix
Direction: Higher is better
Comparison cohort: vals-swebench:1:<15 min fix
Source type: independent-evaluator
Evaluator: Vals AI
Status: active
Retrieved at: 2026-08-11
Methodology: Source model ID: kimi/kimi-k2.7-code. Source model name: Kimi K2.7 Code. Provider reported by source: Moonshot AI. Evaluator: Vals AI. Dataset type: public. Leaderboard date: 2026-08-08. Latency in seconds: 561.729. Standard error: 2.282. Cost per task in USD: 0.154689. Source ID: vals-ai. Evidence capture ID: vals-swebench-2026-08-11-a6212cd857d8. Source payload hash: a6212cd857d8406828224bea2aee5b657d927338e035f1ff603eea74c9bc8a7b. Parser version: vals-astro-v2. Imported at: 2026-08-11

Source Vals AI

SWE-bench Verified: >4 hours (Show measurement, test conditions, and source)

Source value: 33.333
Score: 33.333
Metric: accuracy
Unit: %
Benchmark version: 1
Category: coding
Task: >4 hours
Task label: >4 hours
Direction: Higher is better
Comparison cohort: vals-swebench:1:>4 hours
Source type: independent-evaluator
Evaluator: Vals AI
Status: active
Retrieved at: 2026-08-11
Methodology: Source model ID: kimi/kimi-k2.7-code. Source model name: Kimi K2.7 Code. Provider reported by source: Moonshot AI. Evaluator: Vals AI. Dataset type: public. Leaderboard date: 2026-08-08. Latency in seconds: 1862.15. Standard error: 33.333. Cost per task in USD: 0.561509. Source ID: vals-ai. Evidence capture ID: vals-swebench-2026-08-11-a6212cd857d8. Source payload hash: a6212cd857d8406828224bea2aee5b657d927338e035f1ff603eea74c9bc8a7b. Parser version: vals-astro-v2. Imported at: 2026-08-11

Source Vals AI

SWE-bench Verified: 1-4 hours (Show measurement, test conditions, and source)

Source value: 50
Score: 50
Metric: accuracy
Unit: %
Benchmark version: 1
Category: coding
Task: 1-4 hours
Task label: 1-4 hours
Direction: Higher is better
Comparison cohort: vals-swebench:1:1-4 hours
Source type: independent-evaluator
Evaluator: Vals AI
Status: active
Retrieved at: 2026-08-11
Methodology: Source model ID: kimi/kimi-k2.7-code. Source model name: Kimi K2.7 Code. Provider reported by source: Moonshot AI. Evaluator: Vals AI. Dataset type: public. Leaderboard date: 2026-08-08. Latency in seconds: 1477.273. Standard error: 7.809. Cost per task in USD: 0.464016. Source ID: vals-ai. Evidence capture ID: vals-swebench-2026-08-11-a6212cd857d8. Source payload hash: a6212cd857d8406828224bea2aee5b657d927338e035f1ff603eea74c9bc8a7b. Parser version: vals-astro-v2. Imported at: 2026-08-11

Source Vals AI

SWE-bench Verified: 15 min - 1 hour (Show measurement, test conditions, and source)

Source value: 75.479
Score: 75.479
Metric: accuracy
Unit: %
Benchmark version: 1
Category: coding
Task: 15 min - 1 hour
Task label: 15 min - 1 hour
Direction: Higher is better
Comparison cohort: vals-swebench:1:15 min - 1 hour
Source type: independent-evaluator
Evaluator: Vals AI
Status: active
Retrieved at: 2026-08-11
Methodology: Source model ID: kimi/kimi-k2.7-code. Source model name: Kimi K2.7 Code. Provider reported by source: Moonshot AI. Evaluator: Vals AI. Dataset type: public. Leaderboard date: 2026-08-08. Latency in seconds: 1041.18. Standard error: 2.668. Cost per task in USD: 0.312089. Source ID: vals-ai. Evidence capture ID: vals-swebench-2026-08-11-a6212cd857d8. Source payload hash: a6212cd857d8406828224bea2aee5b657d927338e035f1ff603eea74c9bc8a7b. Parser version: vals-astro-v2. Imported at: 2026-08-11

Source Vals AI

SWE-bench Verified: Overall (Show measurement, test conditions, and source)

Source value: 78.2
Score: 78.2
Metric: accuracy
Unit: %
Benchmark version: 1
Category: coding
Task: overall
Task label: Overall
Direction: Higher is better
Comparison cohort: vals-swebench:1:overall
Source type: independent-evaluator
Evaluator: Vals AI
Status: active
Retrieved at: 2026-09-29
Methodology: Source model ID: kimi/kimi-k2.7-code. Source model name: Kimi K2.7 Code. Evaluator: Vals AI. Dataset type: public. Leaderboard date: 2026-09-01. Latency in seconds: 896.71. Cost per task in USD: 0.265276. Source ID: vals-ai. Evidence capture ID: vals-swebench-2026-09-29-20166fd31f31. Source payload hash: 20166fd31f31a0b278e6471c59ece1600abba838f3db178873d3a1c762a6f44f. Parser version: vals-astro-v2. Imported at: 2026-09-29

Source Vals AI

Page 1 of 4

Sources and data date

Type	Evidence and data date
Speed	Kimi. Output speed after the first streaming chunk, not total response time. Retrieved September 8, 2026. Source: Artificial Analysis · Artificial Analysis (retrieved September 8, 2026)Speed measurement methodology
Price	Base API prices without caching or batch discounts. Higher context tiers and other rates are listed under Costs. Source: Pricing · API pricing
Input	Documented modalities. Retrieved September 8, 2026. Source: Model documentation · Kimi K2.7 Code model card (retrieved September 8, 2026) · Kimi K2.7 Code model card · Editorial description reviewed October 2, 2026
Output	Documented modalities. Retrieved September 8, 2026. Source: Model documentation · Kimi K2.7 Code model card (retrieved September 8, 2026) · Kimi K2.7 Code model card · Editorial description reviewed October 2, 2026
Research status	Research date September 8, 2026. 2 source URLs checked. This documents the inspected sources, not an exhaustive inventory of every publication.
Unresolved	release-date Original wording No normalized release-date field in card.
Additional source	Model metadata · Kimi K2.7 Code resource · Editorial description reviewed October 2, 2026
Additional source	Vals AI (retrieved August 11, 2026; September 29, 2026)
Additional source	Vals AI (retrieved August 11, 2026; September 29, 2026)
Additional source	Vals AI (retrieved August 11, 2026; September 29, 2026)
Additional source	Vals AI (retrieved August 11, 2026; September 29, 2026)
Additional source	Vals AI (retrieved August 11, 2026; September 29, 2026)
Additional source	Vals AI (retrieved August 11, 2026; September 29, 2026)
Additional source	Vals AI (retrieved September 29, 2026)
Additional source	Kimi API model list · Editorial description reviewed October 2, 2026
Additional source	OpenRouter: Popularity index (derived), CC BY 4.0
Additional source	Vercel AI Gateway: Popularity index (derived), CC BY 4.0
Additional source	Creative Commons Attribution 4.0

Kimi K2.7 Code

Specifications and access

Published benchmarks

Coding

Code Migration

LiveCodeBench v6

LiveCodeBench v6

ProgramBench

SWE-bench Verified

SWE-bench Verified

SkillsBench

Recorded measurement details

Our tests

Pelican on a bicycle

Popularity

Published prices

Sources and data date