Intern-S2-Preview-397B: benchmark scores, price and ranking
Intern-S2-Preview-397B from internlm ranks #79 of 827 LLMs on the LLMs Tiger aggregate benchmark score (52.4), based on 1 benchmark results captured up to 2026-11-18.
- Organisation
- internlm
- Type
- Open-weight / local model
- Open weights
- Yes
- Aggregate rank
- #79 of 827 (score 52.4)
Across the 1 benchmark where at least ten models are scored, Intern-S2-Preview-397B is in the top 10% on 1 and in the top half on 1.
Intern-S2-Preview-397B benchmark results
| Benchmark | Score | Rank | Source | Captured |
|---|---|---|---|---|
| MMLU-Pro | 89.8% | #1 of 158 | HuggingFace MMLU-Pro leaderboard | 2026-11-18 |
About Intern-S2-Preview-397B
Intern-S2-Preview-397B is an open-weight model that can run on your own hardware from internlm. No API price is listed for it yet. We hold 1 benchmark result for it across 1 area, and 1 is in the top tenth of its board.
Where Intern-S2-Preview-397B stands
On our aggregate score, Intern-S2-Preview-397B is #79 of 827 ranked models, in the top quarter. Its score is 52.4; the scale is centred on 50, so it sits 2.4 points above the typical model. That beats 90% of the ranked field. Among the 9 ranked internlm models it is #1. The next one down is Intern-S2-Preview at 52.2.
Intern-S2-Preview-397B, benchmark by benchmark
MMLU-Pro is where Intern-S2-Preview-397B does best: 89.8%, first of 158. The next result is Darwin-180B-RSI at 88.1%, 1.6 points behind. It covers 57-subject knowledge + reasoning. The board median is 58.1%, so Intern-S2-Preview-397B is 31.6 points above it. Source: HuggingFace MMLU-Pro leaderboard, captured 2026-11-18.
Reading these numbers
The 1 score on this page comes from 1 source: HuggingFace MMLU-Pro leaderboard (1). No official leaderboard supplied any of them, so treat them as third-party measurements. With 1 results the aggregate rank can move a lot when one new score arrives.
Models ranked nearby
- #76 Claude Code + Kimi K3.1 Pro (52.5)
- #77 DeepSeek-V3.2-Exp (high) (52.4)
- #78 Gemini 3 Deep Think (52.4)
- #80 Claude Fable 5.2 (with fallback, max) (52.4)
- #81 Step-3.5-Flash (52.3)
- #82 DeepSeek V4 Flash 0731 (max) (52.3)
More from internlm
- Intern-S2-Preview (#92, 52.2)
- Intern-S1-Pro (#106, 52.0)
- Intern-S1 (#141, 51.6)
- internlm2_5-7b-chat (#281, 49.7)
- internlm3-8b-instruct (#417, 48.3)
- internlm2-chat-20b (#432, 48.2)
Compare it on the live leaderboard → · How the aggregate score works