Advertise here
#174

LongCat 2.0

Meituan Release: 2026-07-20 Tested on: 2026-10-01 03:48 meituan/longcat-2.0::medium
1.6T total (48B active)MoEOpen source
(high) (medium) (low) (none)

Summary

LongCat 2.0 scores 7.2 on AI BENCHY and ranks #174. It has 10.0 reliability, a 59.4% pass rate, $0.767 total cost, and 144.88s average response time.

What makes LongCat 2.0 unique: It stands out most in Coding, where it ranks #1, while Puzzle Solving is its weakest area at #17.

Identity note

Owl Alpha was the stealth version of LongCat 2.0.

Model facts

Researched on 2026-08-12

Reported
Parameters
1.6T total (48B active)
Architecture
MoE
Availability
Open source
License
MIT
Parameter source Availability source

Score

7.2

Consistency

9.0

Reliability

10.0

Total Cost (Current Price)

$0.767 ↑ +29.2%

Tested at: $0.593

Total Output Tokens

422,234

Total Input Tokens

287,669

Input Price

$0.300 / 1M

Output Price

$1.200 / 1M

Cache Read Price

$0.006 / 1M

Cache Write Price

N/A

Cache prices apply to input tokens. Reads reuse cached prompts; writes store them and can cost extra. Output tokens use the output price.

Tests Correct

Wrong Tests: 11

Attempt pass rate: 59.4%

Flaky tests

3

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

Response Time (avg)

144.88s

Response Time (max): 939.52s

Response Time (total): 3332.19s

Wrong answer: 8 API error: 1 No answer: 1 Timed out: 1

Hamster playing table tennis

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

#174 LongCat 2.0

medium
Cost
$0.016
Time
285.1s
Tokens
13,057 tok

Run history

Tested on Score Reliability Tests Correct Total Cost Compare
2026-10-01 03:48 Re-test 7.2 10.0 $0.767 ↑ Current run
2026-07-20 17:01 Initial run 7.4 9.8 $0.478 Compare

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

Run comparison

RunBenchmark coverageScoreConsistencyReliabilityTests CorrectFlaky testsTotal Output TokensTotal Input TokensTotal CostResponse Time (avg)
2026-10-01 03:48 · Current run69/69 attempts7.29.010.012/233422,234287,669$0.767144.88s
2026-07-20 17:01 · Initial run66/66 attempts7.48.99.812/223373,39697,315$0.478136.64s
Difference—-0.2+0.1+0.200+48838+190354+$0.289+8241ms

Benchmark coverage differs: 69/69 attempts (Target: 3 repeats per test) versus 66/66 attempts (Target: 3 repeats per test). Totals and repeat-sensitive metrics are not directly comparable.

These two runs used different benchmark suites, so the deltas reflect both model changes and suite changes.

Price History

Historical pricing data for this model from OpenRouter.

Date Input Price Output Price Cache Read Price Cache Write Price
2026-08-14 12:51 $0.300 / 1M $1.200 / 1M N/A N/A
2026-10-01 18:33 $0.300 / 1M $1.200 / 1M $0.006 / 1M N/A

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

LongCat 2.0mediumvsQwen3.7 FlashhighLongCat 2.0mediumvsGLM 5mediumLongCat 2.0mediumvsClaude Opus 4.8lowLongCat 2.0mediumvsStep 3.7 FlashlowLongCat 2.0mediumvsGemini 3.8 FlashlowLongCat 2.0mediumvsQwen3.6 27BmediumLongCat 2.0mediumvsQwen3.8 27BmediumFree AvailableLongCat 2.0mediumvsClaude Opus 5noneLongCat 2.0mediumvsQwen3.5 Plus 2026-02-15mediumLongCat 2.0mediumvsQwen3.8 Flash Nextxhigh

Category Breakdown

Category Score Consistency Tests Correct
Agentic 6.1 3.1
Anti-AI Tricks 10.0 10.0
Coding 10.0 10.0
Combined 7.3 5.8
Data parsing and extraction 6.3 10.0
Domain specific 3.0 10.0
General Intelligence 4.8 3.2
Instructions following 6.5 10.0
Puzzle Solving 5.4 10.0
Tool Calling 10.0 10.0
Trivia 3.0 10.0

Compared models