GPQA DiamondVerified
78%
GPQA Diamond (AA run)
Models / Meituan
LongCat-2.0
LongCat · Released 2026-06-29
Meituan's June 2026 agentic-coding model: a 1.6T-parameter MoE with roughly 48B active parameters per token, 1M-context training, MIT licensing, and a public reveal as the model behind OpenRouter's Owl Alpha stealth route.
Track as a near-frontier open-weights coding contender, but wait for weights and independent reruns before treating the OpenRouter/Owl Alpha adoption story as durable evidence.
Composite56
Context1M
Input / 1M$0.75
Output / 1M$3.0
Knowledge cutoffopen
Output speed65 t/s
Statussolid
Family profile
Best published score in each covered benchmark family.
63/100 avg
- Reasoning
- 78
- Coding
- 36
- Agentic
- 71
- Long context
- 65
4 tested benchmark families
Editor's note
LongCat-2.0 is important because the adoption happened before the brand reveal: Owl Alpha had already become a high-volume OpenRouter coding route. Keep the tool sober: Meituan's 1.6T / 48B-active / 1M-context claims are official, but the weights are still 'coming soon' and benchmark claims remain vendor-reported.Benchmark placements
Per-benchmark positions
Where LongCat-2.0 places on each public benchmark source that publishes a row. Rank counts every model with a latest row in the same test — not a universal quality score.
| Benchmark | Family | Rank | Score | Source | Date |
|---|---|---|---|---|---|
| Terminal-Bench | Agentic | #40/ 167 | 71 | Meituan LongCat-2.0 release materials | 2026-06-29 |
| Humanity's Last Exam | Reasoning | #67/ 186 | 34 | Artificial Analysis | 2026-09-28 |
| SciCode | Coding | #90/ 97 | 36 | Artificial Analysis | 2026-09-28 |
| AA output speed | Performance | #95/ 195 | Artificial Analysis | 2026-10-12 | |
| AA-LCR | Long context | #142/ 184 | 65 | Artificial Analysis | 2026-09-28 |
| GPQA Diamond | Reasoning | #146/ 184 | 78 | Artificial Analysis | 2026-09-28 |
Family context
Strongest rows in each family
The three highest-scoring models with pages in each capability family. Where LongCat-2.0 shows up, it's highlighted.
ReasoningLongCat-2.0 · 78
- 196
- 295
- 395
Math
- 152
- 252
- 350
CodingLongCat-2.0 · 36
- 174
- 273
- 370
AgenticLongCat-2.0 · 71
- 191
- 289
- 389
Long contextLongCat-2.0 · 65
- 189
- 286
- 385
Newest receipts
6 recentLast 120 days
Benchmark rows added to the public ledger for LongCat-2.0 in the last 120 days. Older rows live in the full table below.
| Benchmark | Family | Score | Source | Days ago |
|---|---|---|---|---|
| AA output speed | Performance | 65 t/s | Artificial Analysis | 10 |
| AA-LCR | Long context | 65% | Artificial Analysis | 24 |
| GPQA Diamond | Reasoning | 78% | Artificial Analysis | 24 |
| Humanity's Last Exam | Reasoning | 33.7% | Artificial Analysis | 24 |
| SciCode | Coding | 36.3% | Artificial Analysis | 24 |
| Terminal-Bench | Agentic | 70.8% | Meituan LongCat-2.0 release materials | 115 |
Family coverage
Best score per family
A high composite that hides a weak family is a trap. These bars surface the families where this model hasn't been publicly tested, and where it leads.
Price vs. performance
Where LongCat-2.0 sits on the scatter
Hover any dot for name, score, and input price. Keyboard: tab through the top twelve, or use the ranking below.
AnthropicOpenAIGoogleAlibabaMetaZhipuxAIDeepSeekMiniMaxXiaomiMoonshotOtherMeituanMistralNVIDIACohere
Full benchmark ledger
Every catalog benchmark for LongCat-2.0. Scores link to the original source; gaps mean no public row exists yet.
6 of 13 catalog benchmarks have a sourced row for LongCat-2.0.
Reasoning
Humanity's Last ExamVerified
33.7%
HLE (AA run)
Coding
SciCodeVerified
36.3%
SciCode (AA run)
Agentic
70.8%
Terminal-Bench 2.1 vendor-reported
Long context
AA-LCRVerified
65%
AA-LCR (AA run)
Performance
AA output speedVerified
65 t/s
Median output tokens/s (1k prompt, default provider)
Changelog
Version history
- Meituan revealed LongCat-2.0 and identified OpenRouter's Owl Alpha stealth route as LongCat-backed; GitHub/Hugging Face pages say model weights are coming soon.
Sources
Where the numbers come from
- LongCat-2.0 GitHub· checked 2026-07-01
- LongCat-2.0 Hugging Face· checked 2026-07-01
- Official LongCat-2.0 technical blog· checked 2026-07-01
- Reuters — Meituan LongCat release· checked 2026-07-01
- OpenRouter Owl Alpha model page· checked 2026-07-01
Questions this model page answers
Every answer below is assembled from the dated fields on this page. Nothing is written separately for search.
What is LongCat-2.0?
LongCat-2.0 is a Meituan model: Meituan's June 2026 agentic-coding model: a 1.6T-parameter MoE with roughly 48B active parameters per token, 1M-context training, MIT licensing, and a public reveal as the model behind OpenRouter's Owl Alpha stealth route.
What is LongCat-2.0 for?
Track as a near-frontier open-weights coding contender, but wait for weights and independent reruns before treating the OpenRouter/Owl Alpha adoption story as durable evidence.
What does LongCat-2.0 cost?
LongCat-2.0 lists $0.75 input and $3.0 output per 1M tokens. Pricing last checked 2026-07-01.
How large is the LongCat-2.0 context window?
LongCat-2.0 publishes a 1M token context window.
What is the VerdictPal status of LongCat-2.0?
LongCat-2.0 carries Solid status on the model atlas.
The Pack · Editorial newsletter
Know when the rules move.
One short email when a university changes its AI rule for theses, or a research tool changes its pricing or privacy terms. No tracking, no third-party analytics. Unsubscribe in one click.