MDL
LongCat 2.0
LongCat
Verified against Artificial Analysis · Jul 27, 2026
Capability
78
percentile index
Price /M
$0 / $0
in / out
Context
1M
tokens
Avg score
50.9
4 benchmarks
AA Intelligence
33.5
index
Weights
Closed
Released
Jun 29, 2026
About
LongCat 2.0 is a proprietary model in the LongCat family from LongCat. Benchmarked on 4 evals, averaging 50.9.
Benchmark scores · 4
avg 50.9 — higher is betterPerformance & price
Price in / out$0 / $0 per 1M
Coding index45.3
Median across API providers, via Artificial Analysis. Blended = 3:1 input:output. For reasoning models, latency includes thinking time. Methodology →
History
full ledger →Capability over time
GPQA Diamondfirst seen at 78
8d ago
Humanity's Last Examfirst seen at 32.1
8d ago
SciCodefirst seen at 35.4
8d ago
AA Long-Context Reasoningfirst seen at 58
8d ago
Append-only ledger — every observed change to this model's numbers.
API providers
Artificial Analysis$0/M