AI BENCHY
Advertise here
#135

Kimi K2.5

Moonshot AI Release: 2026-01-27 Tested on: 2026-06-04 13:32 moonshotai/kimi-k2.5::none
(medium) (none)

Summary

Kimi K2.5 scores 5.5 on AI BENCHY and ranks #135. It has 10.0 reliability, a 34.9% pass rate, $0.027 total cost, and 13.18s average response time.

What makes Kimi K2.5 unique: It stands out most in General Intelligence, where it ranks #1, while Data parsing and extraction is its weakest area at #12.

Score

5.5

Consistency

8.9

Reliability

10.0

Total Cost (Current Price)

$0.027 ↑ +1.8%

Tested at: $0.027

Total Output Tokens

6,657

Total Input Tokens

36,034

Input Price

$0.375 / 1M

Output Price

$2.025 / 1M

Tests Correct

Wrong Tests: 15

Attempt pass rate: 34.9%

Flaky tests

3

Flaky tests had mixed outcomes across runs (at least one pass and one fail).

Response Time (avg)

13.18s

Response Time (max): 42.13s

Response Time (total): 184.47s

Wrong answer: 15

Generation showcase

Hamster playing table tennis

Prompt: Create a detailed SVG illustration of a hamster playing table tennis.

#135 MoonshotAI: Kimi K2.5

none
Cost
$0.015
Time
89.1s
Tokens
5,421 tok

Run history

Tested on Score Reliability Tests Correct Total Cost Compare
2026-06-04 13:32 New test added 5.2 10.0 $0.028 ↑ Current run
2026-05-22 00:03 Suite changed 5.3 10.0 $0.026 Compare
2026-04-20 17:48 First recorded run 5.5 N/A $0.017 Compare

This run used a different benchmark suite. Keep suite changes in mind when reading historical movement.

Price History

Historical pricing data for this model from OpenRouter.

Date Input Price Output Price
2026-06-04 15:40 $0.400 / 1M $1.900 / 1M
2026-06-17 10:07 $0.375 / 1M $2.025 / 1M

Charts

Choose the first model, then click a second model to open a side-by-side page.

Total Output Tokens

Score vs Total Output Tokens

Quick Compare

Kimi K2.5nonevsNemotron 3 Ultra 550b A55bnoneFree AvailableKimi K2.5nonevsGPT-5.6 TerranoneKimi K2.5nonevsGemma 4 31BnoneFree AvailableKimi K2.5nonevsGLM 5noneKimi K2.5nonevsQwen3.5-FlashnoneKimi K2.5nonevsQwen3.6 FlashnoneKimi K2.5nonevsGemini 3.5 FlashhighKimi K2.5nonevsGemini 3 Flash PreviewmediumKimi K2.5nonevsNemotron 3 Ultra 550b A55bmediumFree AvailableKimi K2.5nonevsGPT-5.5low

Category Breakdown

Category Score Consistency Tests Correct
Anti-AI Tricks 3.6 8.4
Coding 5.5 10.0
Combined 2.8 2.1
Data parsing and extraction 7.3 5.8
Domain specific 5.3 10.0
General Intelligence 10.0 10.0
Instructions following 6.5 10.0
Puzzle Solving 3.0 10.0
Tool Calling 10.0 10.0
Trivia 3.0 10.0

Compared models