AI BENCHY
Advertise here
#141

KAT-Coder-Pro V2.5

Kwaipilot Release: 2026-07-14 Tested on: 2026-08-14 03:23 kwaipilot/kat-coder-pro-v2.5::none
~700B total (~72B active)MoEClosedEstimated
(high) (medium) (low) (none)

Summary

KAT-Coder-Pro V2.5 scores 6.7 on AI BENCHY and ranks #141. It has 10.0 reliability, a 71.2% pass rate, $0.487 total cost, and 26.01s average response time.

Model facts

Researched on 2026-08-12

Estimated
Parameters
~700B total (~72B active)
Architecture
MoE
Availability
Closed
License
-

Best estimate from public evidence; the vendor did not disclose every value. The active count has stronger secondary evidence than the inferred total.

Parameter source Availability source

Score

6.7

Consistency

7.0

Reliability

10.0

Total Cost (Current Price)

$0.487

Total Output Tokens

139,572

Total Input Tokens

98,508

Input Price

$0.740 / 1M

Output Price

$2.960 / 1M

Tests Correct

Wrong Tests: 11

Attempt pass rate: 71.2%

Flaky tests

8

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

Response Time (avg)

26.01s

Response Time (max): 335.41s

Response Time (total): 572.22s

Wrong answer: 10 Invalid tool call: 1

Hamster playing table tennis

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

#141 KAT-Coder-Pro V2.5

none
Cost
$0.010
Time
29.0s
Tokens
3,439 tok

Run history

Tested on Score Reliability Tests Correct Total Cost Compare
2026-08-14 03:23 Re-test 6.7 10.0 $0.487 Current run
2026-07-16 23:43 New test added 6.7 10.0 $0.476 Compare
2026-07-14 11:05 Initial run 6.8 10.0 $0.220 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
2026-08-14 12:51 $0.740 / 1M $2.960 / 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

KAT-Coder-Pro V2.5nonevsGLM 5.2noneKAT-Coder-Pro V2.5nonevsLongCat 2.0lowKAT-Coder-Pro V2.5nonevsGemma 4 26B A4BmediumFree AvailableKAT-Coder-Pro V2.5nonevsGemini 3.5 FlashminimalKAT-Coder-Pro V2.5nonevsGemini 3 Flash PreviewnoneKAT-Coder-Pro V2.5nonevsLongCat 2.0highKAT-Coder-Pro V2.5nonevsMiMo-V2.5-PromediumKAT-Coder-Pro V2.5nonevsGemini 3.5 Flash LitelowKAT-Coder-Pro V2.5nonevsGLM 5.3lowKAT-Coder-Pro V2.5nonevsQwen3.5-27Bnone

Category Breakdown

Category Score Consistency Tests Correct
Anti-AI Tricks 8.7 7.9
Coding 6.1 4.7
Combined 4.1 5.0
Data parsing and extraction 10.0 10.0
Domain specific 4.1 4.4
General Intelligence 4.8 3.2
Instructions following 9.8 10.0
Puzzle Solving 8.2 7.2
Tool Calling 10.0 10.0
Trivia 3.0 10.0

Compared models