Scale Labs MultiChallenge (Small Language Models) (MultiChallenge (Small Language Models))
We show this table for reference; we do not rank on it.
A Scale Labs public leaderboard mirrored as display-only reference data. It does not affect BenchLM rankings.
Scale score on MultiChallenge (Small Language Models) — October 28, 2026 snapshot
We mirror the published scale score view for MultiChallenge (Small Language Models). Nemotron 3.5 Bolt E4B (Thinking) leads the public snapshot at 56.0%, followed by Gemma 4 E4B (Thinking) (43.2%) and Nemotron 3 Nano 4B (Thinking) (38.7%). We do not use these results to rank models overall.
Nemotron 3.5 Bolt E4B (Thinking)
Nvidia
MultiChallenge (Small Language Models)
Gemma 4 E4B (Thinking)
MultiChallenge (Small Language Models)
Nemotron 3 Nano 4B (Thinking)
Nvidia
MultiChallenge (Small Language Models)
9 modelsInstruction FollowingCurrentDisplay onlyUpdated October 28, 2026 snapshot
Scale score table (9 models)
| Rank | Model / configuration | Score | Parameters (B) | Open / closed |
|---|---|---|---|---|
| 1 | Nemotron 3.5 Bolt E4B (Thinking)NvidiaMultiChallenge (Small Language Models) | 56.0% | Not reported | Unknown |
| 2 | Gemma 4 E4B (Thinking)GoogleMultiChallenge (Small Language Models) | 43.2% | Not reported | Unknown |
| 3 | Nemotron 3 Nano 4B (Thinking)NvidiaMultiChallenge (Small Language Models) | 38.7% | Not reported | Unknown |
| 4 | Gemma 4 E2B (Thinking)GoogleMultiChallenge (Small Language Models) | 36.0% | Not reported | Unknown |
| 5 | Ministral 3 8B (Thinking)\nMistralMultiChallenge (Small Language Models) | 27.8% | Not reported | Unknown |
| 6 | Ministral 3 3B (Thinking)\nMistralMultiChallenge (Small Language Models) | 25.7% | Not reported | Unknown |
| 7 | Qwen3.5-4B (Thinking)AlibabaMultiChallenge (Small Language Models) | 25.1% | Not reported | Unknown |
| 8 | Llama 3.1 8B\nMetaMultiChallenge (Small Language Models) | 23.7% | Not reported | Unknown |
| 9 | Gemma 3 4BGoogleMultiChallenge (Small Language Models) | 22.8% | Not reported | Unknown |
How to read this leaderboard
Compare the published configurations as complete evaluation systems. The source can combine a base model, agent scaffold, tools, budget, and inference setting in each result.
Operator receipt: 9 sourced rows are currently displayable on this page; the leading published row is Nemotron 3.5 Bolt E4B (Thinking) at 56.0%.
Honest limit: This Scale table is display-only context, not benchmark provenance or a weighted model-only comparison.
How BenchLM shows MultiChallenge (Small Language Models)
BenchLM mirrors 9 published rows from Scale Labs’ public MultiChallenge (Small Language Models) leaderboard, captured on October 28, 2026 snapshot.
The table is display only. It is useful context for a published agent or model configuration, but it does not enter BenchLM’s overall or category rankings.
Snapshot
The published MultiChallenge (Small Language Models) snapshot places Nemotron 3.5 Bolt E4B (Thinking) first at 56.0%. The third row is 17.4 points behind. The broader top-10 range is 33.3 points, so the table still separates the published systems.
9 models have been evaluated on MultiChallenge (Small Language Models). The benchmark falls in the Instruction Following category. We keep external benchmark mirrors separate from the weighted global scoring system, so these results remain source-specific evidence. MultiChallenge (Small Language Models) is currently displayed for reference but excluded from the scoring formula, so it does not directly affect overall rankings.
About MultiChallenge (Small Language Models)
Year
2026
Tasks
9 published rows
Format
Published Scale leaderboard score
Difficulty
External agent and model evaluation
BenchLM mirrors 9 published rows from the MultiChallenge (Small Language Models) public table captured on October 28, 2026 snapshot.
Freshness and provenance
Version
MultiChallenge (Small Language Models) 2026
Refresh cadence
Quarterly
Staleness state
Current
Question availability
Public benchmark set
BenchLM uses freshness metadata to decide whether a benchmark should still be treated as a strong differentiator, a benchmark to watch, or a display-only reference. For the full scoring policy, see the BenchLM methodology page.
Questions
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 56.0% scale score. BenchLM shows this benchmark for display only and does not use it in overall rankings.
How many models are evaluated on MultiChallenge (Small Language Models)?
The October 28, 2026 snapshot snapshot contains 9 AI models.
Know when it’s worth switching models
The model to choose, the cheaper alternative, and the release we would wait on.
Read a sample issueJoin 6,100+ subscribers.
One email each week. Unsubscribe anytime.