An agentic spatial reasoning benchmark reported as a normalized score.
BenchLM mirrors the published score view for Blueprint-Bench 2. Claude Mythos 5 leads the public snapshot at 38.6% , followed by Claude Fable 5 (38.6%) and Gemini 3.5 Flash (33.6%). BenchLM does not use these results to rank models overall.
Claude Mythos 5
Anthropic
Claude Fable 5
Anthropic
Gemini 3.5 Flash
The published Blueprint-Bench 2 snapshot is tightly clustered at the top: Claude Mythos 5 sits at 38.6%, while the third row is only 5.0 points behind. The broader top-10 spread is 5.0 points, so many of the published scores sit in a relatively narrow band.
3 models have been evaluated on Blueprint-Bench 2. The benchmark falls in the Multimodal & Grounded category. This category carries a 12% weight in BenchLM.ai's overall scoring system. Blueprint-Bench 2 is currently displayed for reference but excluded from the scoring formula, so it does not directly affect overall rankings.
Year
2026
Tasks
Spatial reasoning from blueprints
Format
Normalized score
Difficulty
Agentic spatial reasoning
Google reported Blueprint-Bench 2 in the Gemini 3.5 Flash launch comparison table. BenchLM stores it as a display-only multimodal and spatial-reasoning benchmark until Google publishes the full methodology page.
Version
Blueprint-Bench 2 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.
An agentic spatial reasoning benchmark reported as a normalized score.
Claude Mythos 5 by Anthropic currently leads with a score of 38.6% on Blueprint-Bench 2.
3 AI models have been evaluated on Blueprint-Bench 2 on BenchLM.
For engineers, researchers, and the plain curious — a weekly brief on new models, ranking shifts, and pricing changes.
Free. No spam. Unsubscribe anytime.