Skip to content
Model Pareto

Intern-S2-Preview (35B-A3B)

Shanghai AI Lab (Intern)Open weightshuggingface.co ↗
Compare with nearest rivalsCompare with…
Input
—
Output
—
Speed
~120tok/sest.
Context
262Ktokens

35B-A3B scientific multimodal model continued-pretrained from Qwen3.5. No API price found. Lab-reported scores from the HF model card results table (image; OpenCompass / VLMEvalKit, thinking mode).

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
1× H200 141GB
FP8 weights
Throughput
~8,390 tok/s
many requests batched
Price
$0.046–0.38 /M tok
busy → light use
On your own machine
RTX 5090 32GB (int4, 300+ tok/s single-stream)
single consumer GPU or Mac
Assumptions (5)
  • FP8 weights (35B params, 3B active per token) + 25% KV-cache headroom ≈ 44 GB
  • 1× H200 141GB at $3.59–$7.91/GPU-hour on-demand (2026-09-24)
  • ~8,390 output tok/s aggregate at batch 256 (bandwidth-bound); MoE compute scales with active params
  • Blended 3:1 input:output; prefill ~155,846 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

DeepSWE v1.1Estimated
~#28 of 31 (estimated)~44.1%
  1. #1DeepSeek V4.1 Flash74.2%
  2. #2Grok 4.772.6%
  3. #27Qwen3.8 Max (0902)51.0%
  4. ~#28Intern-S2-Preview (35B-A3B)Estimated44.1%
  5. #28Qwen3.8 27B42.2%
No published score — estimated from related benchmarks
AA Coding Agent IndexEstimated
~last of 15 (estimated)below measured range (<41.1)
  1. #1Claude Opus 5.566.0
  2. #2Claude Fable 5.162.2
  3. #14GPT-6 Luna41.1
  4. ~#15Intern-S2-Preview (35B-A3B)Estimated<41.1
No published score — estimated from related benchmarks

Writing & chat

MMMLUEstimated
~#2 of 5 (estimated)~89.1%
  1. #1Gemini 3.1 Pro92.6%
  2. ~#2Intern-S2-Preview (35B-A3B)Estimated89.1%
  3. #2Gemma 4 31B88.4%
No published score — estimated from related benchmarks
LMArena Text, Non-English (Elo)Estimated
~#32 of 54 (estimated)~1420 Elo
  1. #1Claude Opus 5.51501
  2. #2Claude Fable 5.1Few votes1496
  3. #31Gemma 4 26B A4BFew votes1423
  4. ~#32Intern-S2-Preview (35B-A3B)Estimated1420
  5. #32Muse GlimmerFew votes1418
No published score — estimated from related benchmarks
LMArena Text (Elo)Estimated
~#33 of 54 (estimated)~1434 Elo
  1. #1Claude Opus 5.51509
  2. #2Claude Fable 5.11501
  3. #32MiMo-V2.51434
  4. ~#33Intern-S2-Preview (35B-A3B)Estimated1434
  5. #33Mistral Medium 3.51426
No published score — estimated from related benchmarks

Vision

MMMUEstimated
~#2 of 3 (estimated)~71.3%
  1. #1Claude Haiku 4.573.2%
  2. ~#2Intern-S2-Preview (35B-A3B)Estimated71.3%
  3. #2Llama 4 Maverick69.4%
No published score — estimated from related benchmarks
OmniDocBench v1.5Estimated
~#4 of 8 (estimated)~85.8%
  1. #1MiniMax-M391.6%
  2. #2Kimi K391.1%
  3. #2Qwen3.8 27B91.1%
  4. ~#4Intern-S2-Preview (35B-A3B)Estimated85.8%
  5. #4Gemini 3.1 Pro85.3%
No published score — estimated from related benchmarks
ChartographyEstimated
~#14 of 23 (estimated)~24.4%
  1. #1GPT-6 Astra71.0%
  2. #2Claude Opus 5.566.3%
  3. #13Gemini 3.1 Pro26.1%
  4. ~#14Intern-S2-Preview (35B-A3B)Estimated24.4%
  5. #14Grok 4.620.5%
No published score — estimated from related benchmarks

Hard reasoning

AIME (latest)Estimated
~#2 of 25 (estimated)~94.8%
  1. #1Inkling97.1%
  2. ~#2Intern-S2-Preview (35B-A3B)Estimated94.8%
  3. #2Muse Glimmer94.7%
No published score — estimated from related benchmarks