# Scale Labs MultiChallenge (Small Language Models) (MultiChallenge (Small Language Models))

> A Scale Labs public leaderboard mirrored as display-only reference data. It does not affect BenchLM rankings.

Canonical page: https://benchlm.ai/benchmarks/scale-multichallenge-small

- Category: [Instruction Following](/instruction-following)
- Last updated: October 28, 2026 snapshot

## About MultiChallenge (Small Language Models)

- Year: 2026
- Tasks: 9 published rows
- Format: Published Scale leaderboard score
- Difficulty: External agent and model evaluation
- Paper: [Scale Labs leaderboard](https://labs.scale.com/leaderboard/multichallenge)

BenchLM mirrors 9 published rows from the MultiChallenge (Small Language Models) public table captured on October 28, 2026 snapshot.

MultiChallenge (Small Language Models) is currently displayed on BenchLM for reference, but it is excluded from the weighted scoring formula.

## Leaderboard (9 models)

| Rank | Model | Configuration | Creator | Score |
|------|-------|---------------|---------|-------|
| 1 | [Nemotron 3.5 Bolt E4B (Thinking)](https://labs.scale.com/leaderboard/multichallenge) | MultiChallenge (Small Language Models) | Nvidia | 56.03% |
| 2 | [Gemma 4 E4B (Thinking)](https://labs.scale.com/leaderboard/multichallenge) | MultiChallenge (Small Language Models) | Google | 43.23% |
| 3 | [Nemotron 3 Nano 4B (Thinking)](https://labs.scale.com/leaderboard/multichallenge) | MultiChallenge (Small Language Models) | Nvidia | 38.67% |
| 4 | [Gemma 4 E2B (Thinking)](https://labs.scale.com/leaderboard/multichallenge) | MultiChallenge (Small Language Models) | Google | 35.98% |
| 5 | [Ministral 3 8B (Thinking)\n](https://labs.scale.com/leaderboard/multichallenge) | MultiChallenge (Small Language Models) | Mistral | 27.78% |
| 6 | [Ministral 3 3B (Thinking)\n](https://labs.scale.com/leaderboard/multichallenge) | MultiChallenge (Small Language Models) | Mistral | 25.68% |
| 7 | [Qwen3.5-4B (Thinking)](https://labs.scale.com/leaderboard/multichallenge) | MultiChallenge (Small Language Models) | Alibaba | 25.13% |
| 8 | [Llama 3.1 8B\n](https://labs.scale.com/leaderboard/multichallenge) | MultiChallenge (Small Language Models) | Meta | 23.71% |
| 9 | [Gemma 3 4B](https://labs.scale.com/leaderboard/multichallenge) | MultiChallenge (Small Language Models) | Google | 22.75% |

## FAQ

### What does MultiChallenge (Small Language Models) measure?

A Scale Labs public leaderboard mirrored as display-only reference data. It does not affect BenchLM rankings.

### Which model leads the published MultiChallenge (Small Language Models) snapshot?

Nemotron 3.5 Bolt E4B (Thinking) currently leads the published MultiChallenge (Small Language Models) snapshot with a score of 56.03%.

### How many models are evaluated on MultiChallenge (Small Language Models)?

The October 28, 2026 snapshot contains 9 AI models.

### Does MultiChallenge (Small Language Models) affect BenchLM's overall score?

Not directly. MultiChallenge (Small Language Models) is still displayed on BenchLM for reference, but it is excluded from the weighted scoring formula.