Skip to content
Model Pareto

Intern-S2-397B

Shanghai AI Lab (Intern)Open weightshuggingface.co ↗
Compare with nearest rivalsCompare with…
Input
—
Output
—
Speed
~92tok/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

SWE-bench VerifiedEstimated
~#3 of 14 (estimated)~82.3%
  1. #1Claude Opus 596.0%
  2. #2Claude Sonnet 585.2%
  3. ~#3Intern-S2-397BEstimated82.3%
  4. #3Gemini 3.1 Pro80.6%
No published score — estimated from related benchmarks
DeepSWE v1.1Estimated
~#27 of 31 (estimated)~54.8%
  1. #1DeepSeek V4.1 Flash74.2%
  2. #2Grok 4.772.6%
  3. #26Nex-N2.5-Pro55.8%
  4. ~#27Intern-S2-397BEstimated54.8%
  5. #27Qwen3.8 Max (0902)51.0%
No published score — estimated from related benchmarks
Terminal-Bench 4.0Estimated
~#19 of 84 (estimated)~18.2%
  1. #1Claude Sonnet 5.563.6%
  2. #2Claude Opus 5.559.6%
  3. #18Gemini 3.8 Flash19.7%
  4. ~#19Intern-S2-397BEstimated18.2%
  5. #19Grok 4.617.2%
No published score — estimated from related benchmarks
LiveCodeBenchEstimated
~#6 of 20 (estimated)~85.2%
  1. #1Qwen3.8-Omni-Flash92.6%
  2. #2Qwen3.8 Flash-Next91.9%
  3. #5gpt-oss-120b87.8%
  4. ~#6Intern-S2-397BEstimated85.2%
  5. #6Gemma 4 31B80.0%
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
CharXiv ReasoningEstimated
~#5 of 9 (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. #5Muse Glimmer78.8%
No published score — estimated from related benchmarks
OmniDocBench v1.5Estimated
~#4 of 8 (estimated)~88.5%
  1. #1MiniMax-M391.6%
  2. #2Kimi K391.1%
  3. #2Qwen3.8 27B91.1%
  4. ~#4Intern-S2-397BEstimated88.5%
  5. #4Gemini 3.1 Pro85.3%
No published score — estimated from related benchmarks
GDP.pdf (AA)Estimated
~#15 of 43 (estimated)~18.1%
  1. #1GPT-6 Astra31.0%
  2. #2Muse Spark 1.326.6%
  3. #14MiMo-V2.6-Pro19.2%
  4. ~#15Intern-S2-397BEstimated18.1%
  5. #15Gemini 3.1 Pro17.8%
No published score — estimated from related benchmarks
ChartographyEstimated
~#7 of 23 (estimated)~33.8%
  1. #1GPT-6 Astra71.0%
  2. #2Claude Opus 5.566.3%
  3. #6GPT-5.6 Terra34.0%
  4. ~#7Intern-S2-397BEstimated33.8%
  5. #7GPT-5.531.0%
No published score — estimated from related benchmarks