MeituanLongCat 2.0
LongCat 2.0 is a Meituan open-weights reasoning model, released 29 Jun 2026. Its best configuration ranks #400 of 785 on the BenchLeader Index at 49.4 ±4.9, in the lower half. The ± is the point: 331 other configurations score within that range, so they and this one cannot be told apart on quality alone — price and speed are what separate them. It scores highest in long context (57) and lowest in agents & tools (41). At $1.30 per million tokens blended it is pricier than most ranked models. Output speed of 77 tokens per second puts it slower than most, with a first answer in 28.8 s. Last measured 29 Jun 2026.
- Blended price
- $1.30/M
- $0.750 in · $2.95 out
- Output speed
- 77 tok/s
- measured by Artificial Analysis
- First answer
- 29 s
- first token 1.51 s
- Context
- 1.0M
- Full answer
- 35 s
- median, reasoning included
- Cost per run
- $0.146
- one full Intelligence Index run
- Released
- 29 Jun 2026
- Overall index49
- Reasoning45
- Agents & tools41
- Knowledge51
- Long context57
- Composite51
How its index has moved
19 Sept 2026 to 18 Oct 2026The index is recomputed from scratch every day, so a line moves when a new benchmark result lands, when a publisher revises a score, or when the models it is normalised against change. Early movement usually means the score is still settling.
Benchmark results
See all LLM benchmarks. 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
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| GPQA Diamond (AA)not in index | 78.0%#214 | Artificial Analysis | |
| Humanity's Last Exam (AA)not in index | 33.7%#133 | Artificial Analysis | |
| CritPt | 2.6%#189 | Artificial Analysis |
Coding
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| SciCode (AA)not in index | 36.3%#195 | Artificial Analysis | |
| Terminal-Bench 4.0 (AA)not in index | 0.0%#152 | Artificial Analysis | |
| Terminal-Bench 2.1 (AA)not in index | 50.2%#120 | Artificial Analysis |
Agents & tools
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| GDPval-AA v2.1not in index | 18.5%#101 | Artificial Analysis | |
| τ³-Banking (AA) | 13.2%#129 | Artificial Analysis | |
| AutomationBenchnot in index | 4.5%#168 | Artificial Analysis | |
| GDP.pdf (AA)not in index | 6.4%#152 | Artificial Analysis |
Knowledge
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| AA-Omniscience | -23.4#257 | Artificial Analysis | |
| AA-Omniscience: accuracynot in index | 29.6%#186 | Artificial Analysis | |
| AA-Omniscience: non-hallucinationnot in index | 24.6%#246 | Artificial Analysis |
Long context
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| AA-LCR | 65.0%#252 | Artificial Analysis |
Composite
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| AA Intelligence Index v4.3.2 | 19.1#245 | Artificial 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.
| Provider | Speed | First token | Input $/M | Output $/M | Context | Quantisation |
|---|---|---|---|---|---|---|
| AtlasCloud | 45 tok/s | 1.51 s | $0.300 | $1.20 | 1.0M | fp8 |
Price history
The price above, per 1M tokens, every day it changed.
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 at $0.015 per 1M. Reasoning tokens are not modelled.
| Workload | Tokens in / out | Cost | With caching | Time |
|---|---|---|---|---|
| Chat reply | 400 / 300 | $0.0012 | $0.0010 | 32.7 s |
| Summarize a 30-page report | 12,000 / 600 | $0.011 | $0.0042 | 36.6 s |
| Code edit | 6,000 / 1,500 | $0.0089 | $0.0056 | 48.3 s |
| Agentic coding session | 60,000 / 4,000 | $0.057 | $0.024 | 1.3 min |
| Structured extraction | 2,000 / 200 | $0.0021 | $0.0010 | 31.4 s |
More from Meituan
See also
Questions people ask
- What are LongCat 2.0's benchmark scores?
- As of 25 Oct 2026, LongCat 2.0 scores 49.4 ±4.9 on the BenchLeader Index, strongest in long context (57) and weakest in agents & tools (41). That rests on 5 independent benchmark results, and every score on this page links to its publisher.
- How does LongCat 2.0 rank?
- LongCat 2.0 is #400 of 785 ranked configurations on 25 Oct 2026. 331 other configurations score within its margin, so the exact position matters less than the band. The leader is Claude Opus 5.5 (max effort) at 72.6.
- How much does LongCat 2.0 cost per 1M tokens?
- As of 25 Oct 2026, LongCat 2.0 costs $0.750 per 1M input tokens and $2.95 per 1M output tokens, $1.30 blended (three input tokens per output token). The list price last changed on 10 Oct 2026.
- When was LongCat 2.0 released?
- Meituan released LongCat 2.0 on 29 Jun 2026.
Data as of 25 Oct 2026. Compare with another model.
Cite as: BenchLeader, “LongCat 2.0: benchmarks, pricing, speed and rank”, data as of 25 Oct 2026, https://www.benchleader.com/models/longcat-2-0.