Skip to main content
BenchLM

Scale Labs SciPredict (SciPredict)

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 SciPredict — September 29, 2026 snapshot

We mirror the published scale score view for SciPredict. gemini-3-pro-preview leads the public snapshot at 25.3%, followed by Claude Opus 4.5 (23.1%) and Claude Sonnet 4.5 (22.6%). We do not use these results to rank models overall.

15 modelsKnowledgeCurrentDisplay onlyUpdated September 29, 2026 snapshot

Scale score table (15 models)

Score
2
Claude Opus 4.5Anthropic · Closed
23.1%
3
Claude Sonnet 4.5Anthropic · Closed
22.6%
5
Gemini 3 FlashGoogle · Closed
22.2%
6
GPT-5.2OpenAI · Closed
20.6%
7
o3-miniOpenAI · Closed
19.8%
8
DeepSeek V3DeepSeek · Open weight
19.2%
9
18.2%
10
o3OpenAI · Closed
17.9%
11
Gemini 2.5 ProGoogle · Closed
17.0%
12
Qwen3-32BAlibaba
17.0%
13
Qwen3-235BAlibaba
16.6%
14
16.2%
15
14.7%

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: 15 sourced rows are currently displayable on this page; the leading published row is gemini-3-pro-preview at 25.3%.

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

How BenchLM shows SciPredict

BenchLM mirrors 15 published rows from Scale Labs’ public SciPredict 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

15 published rowsScale Labs sourceDisplay only

The published SciPredict snapshot places gemini-3-pro-preview first at 25.3%. The third row is 2.7 points behind. The broader top-10 range is 7.3 points, so many of the published results sit in a relatively narrow band.

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

About SciPredict

Year

2026

Tasks

15 published rows

Format

Published Scale leaderboard score

Difficulty

External agent and model evaluation

BenchLM mirrors 15 published rows from the SciPredict public table captured on September 29, 2026 snapshot.

Freshness and provenance

Version

SciPredict 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 SciPredict measure?

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

Which model leads the published SciPredict snapshot?

gemini-3-pro-preview currently leads the published SciPredict snapshot with 25.3% scale score. BenchLM shows this benchmark for display only and does not use it in overall rankings.

How many models are evaluated on SciPredict?

The September 29, 2026 snapshot snapshot contains 15 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.