Open SLM Leaderboard: leaderboard
The Open SLM Leaderboard (Axiomic Labs, Hugging Face Space) ranks open-weight language models under 400M parameters that their submitters pretrained from scratch, with zero-shot scores from LM-eval harness and Axiomic Labs' ArithMark-3 script that the leaderboard team checks before merging. Unlike the Hugging Face Open LLM Leaderboard, which evaluated every submitted model on its own cluster, it lists zero-shot results the submitters ran and admits only small from-scratch checkpoints (no merges). The page does not state the harness version, the accuracy variant (acc or acc_norm) or the evaluated splits. Rows are bound to their Hugging Face model card; a row without one (Mystery-5M-Preview) is withheld, and a row missing a score is absent from that board only. Intelligence Index, the page's headline: each score is rescaled so chance is 0 and perfect is 100 (HellaSwag, ARC and ArithMark-3 chance 25, PIQA chance 50), then Index = (HellaSwag + mean of ARC-Easy and ARC-Challenge + PIQA + 0.65 x ArithMark-3) / 3.65; models below chance score below zero (floor -51.6). Admitted only for rows with all five inputs; ArithMark-2, the superseded arithmetic set kept in the expanded columns, is not part of the Index and is not admitted.
Metric: Intelligence Index: chance-normalized HellaSwag, combined ARC, PIQA and 0.65 x ArithMark-3, divided by 3.65 (0 = chance, 100 = perfect; below chance is negative). Source: huggingface.co. Saturation forecast: Rough model projection: around 2026. 255 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | SmolLM2-360M (Benchmark Sweep Run: source=Open SLM Leaderboard; zero-shot; card=HuggingFaceTB/SmolLM2-360M) | 41.86 | |
| 2 | MobileLLM-R1-360M-base (Benchmark Sweep Run: source=Open SLM Leaderboard; zero-shot; card=facebook/MobileLLM-R1-360M-base) | 38.65 | |
| 3 | KLM-1.6 (Benchmark Sweep Run: source=Open SLM Leaderboard; zero-shot; card=MinimaLabs/KLM-1.6) | 33.95 | |
| 4 | GPT-X3-150M (Benchmark Sweep Run: source=Open SLM Leaderboard; zero-shot; card=AxiomicLabs/GPT-X3-150M) | 33.05 | |
| 5 | Inferno-Exp-1.7 (Benchmark Sweep Run: source=Open SLM Leaderboard; zero-shot; card=AlgoDriveAI/Inferno-Exp-1.7) | 32.02 | |
| 6 | LFM-2.5-350M-Base (Benchmark Sweep Run: source=Open SLM Leaderboard; zero-shot; card=LiquidAI/LFM2.5-350M-Base) | 30.62 | |
| 7 | Boris-2-Preview-2 (Benchmark Sweep Run: source=Open SLM Leaderboard; zero-shot; card=opencerebral/Boris-2-Preview-2) | 30.58 | |
| 8 | KLM-1.5 (Benchmark Sweep Run: source=Open SLM Leaderboard; zero-shot; card=MinimaLabs/KLM-1.5) | 30.26 | |
| 9 | BananaMind-2.5-Pro (Benchmark Sweep Run: source=Open SLM Leaderboard; zero-shot; card=BananaMind/BananaMind-2.5-Pro) | 28.98 | |
| 10 | Rose-1.5-Pro (Benchmark Sweep Run: source=Open SLM Leaderboard; zero-shot; card=GODELEV/Rose-1.5-Pro) | 28.27 |
Interactive version: theaggregate.ai/benchmark?slug=open-slm-leaderboard · How It Works · Data refreshed daily, snapshot 2026-11-12.