Skip to main content
BenchLM

Scale Labs PropensityBench (PropensityBench)

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 PropensityBench — September 29, 2026 snapshot

We mirror the published scale score view for PropensityBench. Gemini 2.5 Pro leads the public snapshot at 79%, followed by gemini-2.0-flash (77.8%) and Qwen3-8B (75.2%). We do not use these results to rank models overall.

14 modelsReasoningCurrentDisplay onlyUpdated September 29, 2026 snapshot

Scale score table (14 models)

Score
1
Gemini 2.5 ProGoogle · Closed
79%
2
77.8%
3
Qwen3-8BAlibaba
75.2%
5
66.5%
6
55.4%
8
GPT-4oOpenAI · Closed
46.1%
9
GPT-5.2OpenAI · Closed
34.4%
10
o3-miniOpenAI · Closed
33.2%
11
22.9%
12
15.8%
13
12.2%
14
o3OpenAI · Closed
10.5%

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: 14 sourced rows are currently displayable on this page; the leading published row is Gemini 2.5 Pro at 79%.

Honest limit: This Scale table is display-only context, not benchmark provenance or a weighted model-only comparison.

How BenchLM shows PropensityBench

BenchLM mirrors 14 published rows from Scale Labs’ public PropensityBench leaderboard, captured on September 29, 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

14 published rowsScale Labs sourceDisplay only

The published PropensityBench snapshot places Gemini 2.5 Pro first at 79%. The third row is 3.8 points behind. The broader top-10 range is 45.8 points, so the table still separates the published systems.

14 models have been evaluated on PropensityBench. The benchmark falls in the Reasoning category. We keep external benchmark mirrors separate from the weighted global scoring system, so these results remain source-specific evidence. PropensityBench is currently displayed for reference but excluded from the scoring formula, so it does not directly affect overall rankings.

About PropensityBench

Year

2026

Tasks

14 published rows

Format

Published Scale leaderboard score

Difficulty

External agent and model evaluation

BenchLM mirrors 14 published rows from the PropensityBench public table captured on September 29, 2026 snapshot.

Freshness and provenance

Version

PropensityBench 2026

Refresh cadence

Quarterly

Staleness state

Current

Question availability

Public benchmark set

CurrentDisplay only

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 PropensityBench measure?

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

Which model leads the published PropensityBench snapshot?

Gemini 2.5 Pro currently leads the published PropensityBench snapshot with 79% scale score. BenchLM shows this benchmark for display only and does not use it in overall rankings.

How many models are evaluated on PropensityBench?

The September 29, 2026 snapshot snapshot contains 14 AI models.

Last updated: September 29, 2026 snapshot · mirrored from the public benchmark leaderboard

Know when it’s worth switching models

The model to choose, the cheaper alternative, and the release we would wait on.

Read a sample issue

Join 2,000+ readers.

One email each week. Unsubscribe anytime.