LongCat 2.0
- Input
- $0.75/M tok
- Output
- $2.95/M tok
- Blended
- $1.30/M tok · 3:1
- Speed
- 65tok/s
- Context
- 1Mtokens
- Cost per task
- ~$1.2/taskest.
Long-tail import from Artificial Analysis (2026-09-24); AA variant: LongCat 2.0. Price = AA median host price.
Rankings
Self-hostingEstimated
How we estimate →What it would cost to run these open weights yourself on rented GPUs, compared with the API price above.
- Hardware
- 24× H200 141GB
- FP8 weights
- Throughput
- ~30,088 tok/s
- many requests batched
- Price
- $0.39–3.19 /M tok
- busy → light use
- On your own machine
- Too large
- needs data-center GPUs
Assumptions (5)
- FP8 weights (1600B params, 48B active per token) + 40% KV-cache headroom ≈ 2240 GB
- 24× H200 141GB at $3.59–$7.91/GPU-hour on-demand (2026-09-24)
- ~30,088 output tok/s aggregate at batch 1273 (bandwidth-bound); MoE compute scales with active params
- Blended 3:1 input:output; prefill ~198,704 tok/s
- Low = 75% utilization at the low GPU price; high = 20% at the high price
Benchmark scores
~ italic, dashed = no published score yet, estimated from related benchmarks.
Coding
SWE-bench VerifiedEstimated
~#17 of 21 (estimated)~68.7%
- #1Claude Opus 596.0%
- #2Claude Sonnet 585.2%
- #16Nemotron 3 Ultra70.7%
- ~#17LongCat 2.0Estimated68.7%
- #17Intern-S2-Preview (35B-A3B)64.0%
No published score — estimated from related benchmarks
SWE-bench Pro (Public)Estimated
~#23 of 24 (estimated)~47.4%
- #1Claude Fable 5.293.0%
- #2Claude Opus 5.589.9%
- #22Muse Glimmer51.2%
- ~#23LongCat 2.0Estimated47.4%
- #23Nex-N2.5-Mini43.8%
No published score — estimated from related benchmarks
DeepSWE v1.1Estimated
~#41 of 46 (estimated)~41.4%
- #1Gemini 4 Argon78.8%
- #2DeepSeek V4.1 Flash 101777.0%
- #40Qwen3.8 27B42.2%
- ~#41LongCat 2.0Estimated41.4%
- #41Laguna S 2.140.4%
No published score — estimated from related benchmarks
Terminal-Bench 4.0Verified
#63 of 1010.0%
- #1Kimi K3.1 Pro67.2%
- #2Claude Sonnet 5.563.6%
- #63Llama 4 Scout0.0%
- #63LongCat 2.00.0%
- #63Mercury 2.50.0%
artificialanalysis.ai · 2026-09-24
LiveCodeBenchEstimated
~#17 of 28 (estimated)~58.6%
- #1Qwen3.8-Omni-Flash92.6%
- #2Qwen3.8 Flash-Next91.9%
- #16Claude Haiku 4.561.5%
- ~#17LongCat 2.0Estimated58.6%
- #17GLM-5.3 NVFP453.5%
No published score — estimated from related benchmarks
SciCodeVerified
#94 of 11836.3%
- #1Claude Fable 5.267.7%
- #2Claude Opus 5.566.9%
- #92Qwen3.6 35B A3B36.6%
- #94LongCat 2.036.3%
- #95Nemotron 3 Super 120B A12B36.2%
artificialanalysis.ai · 2026-09-24
AA Coding Agent IndexEstimated
~#25 of 26 (estimated)~28.7
- #1Claude Opus 5.561.7
- #2Claude Opus 559.7
- #24GPT-6 Luna31.1
- ~#25LongCat 2.0Estimated28.7
- #25Muse Spark Open26.3
No published score — estimated from related benchmarks
Hard reasoning
GPQA DiamondVerified
#84 of 19278.0%
- #1GPT-6 Astra96.1%
- #2Gemini 3.8 Flash95.3%
- #83gpt-oss-120b78.2%
- #84LongCat 2.078.0%
- #85Mistral Small 476.9%
artificialanalysis.ai · 2026-09-24
Humanity's Last ExamVerified
#49 of 19833.7%
- #1Claude Fable 5.274.3%
- #2Claude Opus 5.561.4%
- #48Qwen3.8 27B33.9%
- #49LongCat 2.033.7%
- #49Nex-N2-Pro33.7%
artificialanalysis.ai · 2026-09-24
AIME (latest)Estimated
~#21 of 34 (estimated)~83.2%
- #1GLM-5.3 NVFP499.5%
- #2Beam 1.0 501B A23B97.7%
- #20Claude Haiku 4.583.7%
- ~#21LongCat 2.0Estimated83.2%
- #21Magistral Small 1.280.3%
No published score — estimated from related benchmarks
Agents
τ²-bench (Telecom)Estimated
~#47 of 120 (estimated)~62.8%
- #1Step 3.7 Flash98.5%
- #2DeepSeek-V4-Pro-0813-nvfp4-DSpark98.3%
- #46HyperNova 60B 260563.2%
- ~#47LongCat 2.0Estimated62.8%
- #47gpt-oss-20b60.2%
No published score — estimated from related benchmarks
OSWorld-VerifiedEstimated
~#12 of 15 (estimated)~62.7%
- #1Kimi K384.8%
- #2Qwen3.8 27B84.3%
- #11Muse Glimmer65.9%
- ~#12LongCat 2.0Estimated62.7%
- #12Nemotron 3.5 Super VL NVFP452.3%
No published score — estimated from related benchmarks
OSWorld 2.0Estimated
~last of 5 (estimated)below measured range (<47.5%)
No published score — estimated from related benchmarks
BrowseCompEstimated
~#19 of 22 (estimated)~59.6%
- #1Atria Dawn Preview92.5%
- #2GPT-6 Astra91.5%
- #18Nemotron 3.5 Bolt 74B-A9B70.0%
- ~#19LongCat 2.0Estimated59.6%
- #19Mistral Medium 3.548.6%
No published score — estimated from related benchmarks
GDPval-AA (Elo)Verified
#49 of 91856 Elo
- #1Claude Opus 5.51866
- #2Muse Wonder Full1857
- #48K2 Horizon 3.7B865
- #49LongCat 2.0856
- #50Step 3.7 Flash845
artificialanalysis.ai · 2026-09-24
AutomationBench-AAVerified
#55 of 844.5%
- #1Claude Fable 5.276.4%
- #2Muse Wonder Full71.3%
- #54Gemma 4 31B4.9%
- #55LongCat 2.04.5%
- #56Nemotron 3 Super 120B A12B3.8%
artificialanalysis.ai · 2026-09-24