BenchLeader

LongCat 2.0

Not yet ranked: too few independent results so far. Released 29 Jun 2026.

Blended price
$1.30/M
$0.750 in · $2.95 out
Output speed
48 tok/s
First answer
46 s
first token 1.98 s
Context
1.0M
How it scores by categoryDashed line = average model (50). One step of 15 = one standard deviation.
  1. Knowledge53
  2. Long context59
  3. Composite54

Benchmark results

One column per reasoning effort. Rank is among every configuration of every model on that benchmark. Hover a score for the run it came from.

Reasoning

BenchmarkdefaultSource
GPQA Diamond (AA)not in index78.0%#209Artificial Analysis
Humanity's Last Exam (AA)not in index33.7%#87Artificial Analysis

Coding

BenchmarkdefaultSource
SciCode (AA)not in index36.3%#132Artificial Analysis

Knowledge

BenchmarkdefaultSource
AA-Omniscience-23.4#195Artificial Analysis

Long context

BenchmarkdefaultSource
AA-LCR65.0%#193Artificial Analysis

Composite

BenchmarkdefaultSource
AA Intelligence Index19.7#177Artificial Analysis

Where to run it

Every provider serving this model through OpenRouter, with throughput and first-token latency measured on live traffic over the last 30 minutes and each provider’s own price. Purple marks the best in each column.

ProviderSpeedFirst tokenInput $/MOutput $/MContextQuantisation
AtlasCloud34 tok/s1.98 s$0.300$1.201.0Mfp8

What a task costs

Estimates from list price, output speed and time to first answer for the best configuration. “With caching” assumes three-quarters of the input is served from the prompt cache. Reasoning tokens are not modelled.

WorkloadTokens in / outCostWith cachingTime
Chat reply400 / 300$0.001252.1 s
Summarise a 30-page report12,000 / 600$0.01158.3 s
Code edit6,000 / 1,500$0.00891.3 min
Agentic coding session60,000 / 4,000$0.0572.1 min
Structured extraction2,000 / 200$0.002150.1 s

See also

Data as of 9 Sept 2026. Compare with another model.