Skip to content
Model Pareto

Intern-S2-397B

Shanghai AI Lab (Intern)Open weightshuggingface.co ↗
Input
—
Output
—
Speed
~90tok/sest.
Context
262Ktokens

Scientific multimodal MoE (397B). No API price found (not on OpenRouter). Lab-reported scores from the HF model card results table (image).

Rankings

Self-hostingEstimated

How we estimate →

What it would cost to run these open weights yourself on rented GPUs. No API sells this model, so this is its price on the chart.

Hardware
4× B200 180GB
FP8 weights
Throughput
~12,969 tok/s
many requests batched
Price
$0.20–1.76 /M tok
busy → light use
On your own machine
Mac Studio M5 Ultra 512GB (int4, ~99 tok/s single-stream)
single consumer GPU or Mac
Assumptions (5)
  • FP8 weights (397B params, 17B active per token) + 25% KV-cache headroom ≈ 496 GB
  • 4× B200 180GB at $5.98–$14.24/GPU-hour on-demand (2026-09-24)
  • ~12,969 output tok/s aggregate at batch 371 (bandwidth-bound); MoE compute scales with active params
  • Blended 3:1 input:output; prefill ~250,147 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

~#4 of 21 (estimated)~81.6%
  1. #1Claude Opus 596.0%
  2. #2Claude Sonnet 585.2%
  3. #3Beam 1.0 501B A23B81.6%
  4. ~#4Intern-S2-397BEstimated81.6%
  5. #4Gemini 3.1 Pro80.6%
No published score — estimated from related benchmarks
DeepSWE v1.1Estimated
~#37 of 46 (estimated)~51.7%
  1. #1Gemini 4 Argon78.8%
  2. #2DeepSeek V4.1 Flash 101777.0%
  3. #36Nex-N2.5-Pro55.8%
  4. ~#37Intern-S2-397BEstimated51.7%
  5. #37Qwen3.8 Max (0902)51.0%
No published score — estimated from related benchmarks
~#31 of 102 (estimated)~19.9%
  1. #1Kimi K3.1 Pro67.2%
  2. #2Claude Sonnet 5.563.6%
  3. #30SWE-2 Flash20.0%
  4. ~#31Intern-S2-397BEstimated19.9%
  5. #31Gemini 3.8 Flash19.7%
No published score — estimated from related benchmarks
LiveCodeBenchEstimated
~#12 of 28 (estimated)~78.5%
  1. #1Qwen3.8-Omni-Flash92.6%
  2. #2Qwen3.8 Flash-Next91.9%
  3. #11Gemma 4 31B80.0%
  4. ~#12Intern-S2-397BEstimated78.5%
  5. #12gpt-oss-20b77.7%
No published score — estimated from related benchmarks
~#21 of 26 (estimated)~41.0
  1. #1Claude Opus 5.561.7
  2. #2Claude Opus 559.7
  3. #20Kimi K341.4
  4. ~#21Intern-S2-397BEstimated41.0
  5. #21Qwen3.8 Max (0902)39.2
No published score — estimated from related benchmarks

Vision

MMMUEstimated
~#2 of 3 (estimated)~71.3%
  1. #1Claude Haiku 4.573.2%
  2. ~#2Intern-S2-397BEstimated71.3%
  3. #2Llama 4 Maverick69.4%
No published score — estimated from related benchmarks
~#5 of 12 (estimated)~82.8%
  1. #1Gemini 3.8 Flash86.2%
  2. #2Kimi K384.8%
  3. #4Qwen3.8-Omni-Flash83.5%
  4. ~#5Intern-S2-397BEstimated82.8%
  5. #5MiniMax-M3.1-Flash82.5%
No published score — estimated from related benchmarks
~#4 of 8 (estimated)~88.4%
  1. #1MiniMax-M391.6%
  2. #2Kimi K391.1%
  3. #2Qwen3.8 27B91.1%
  4. ~#4Intern-S2-397BEstimated88.4%
  5. #4Gemini 3.1 Pro85.3%
No published score — estimated from related benchmarks
GDP.pdf (AA)Estimated
~#20 of 48 (estimated)~18.7%
  1. #1Muse Wonder Full32.6%
  2. #2GPT-6 Astra31.0%
  3. #19MiMo-V2.6-Pro19.2%
  4. ~#20Intern-S2-397BEstimated18.7%
  5. #20Gemini 3.1 Pro17.8%
No published score — estimated from related benchmarks
ChartographyEstimated
~#9 of 25 (estimated)~33.1%
  1. #1Claude Fable 5.273.4%
  2. #2GPT-6 Astra71.0%
  3. #8GPT-5.6 Terra34.0%
  4. ~#9Intern-S2-397BEstimated33.1%
  5. #9GPT-5.531.0%
No published score — estimated from related benchmarks