Updated Fresco 1.2.1 is live: catastrophic forgetting fixed (GSM8K 5%→12%), coding adjusted (HumanEval 80%→50%). Use 1.2 for coding, 1.2.1 for general use. Fresco 1.3 in development. See announcements
Model Release

Introducing Fresco 1.2

Sennoric's most capable model at the time of release, built for real coding tasks, with dramatically improved reasoning and instruction following.

Released June 12, 2026 by Sennoric
26×
better HumanEval than Glyph
+77pts
HumanEval improvement
80%
HumanEval pass@1

Fresco 1.2 vs Glyph 1.1 — benchmarks

Across every evaluation, Fresco 1.2 represents a substantial generational leap over Glyph 1.1.

Glyph 1.1
Fresco 1.2 ↑ wins
HumanEval pass@1
Python code generation from docstrings
MBPP
Mostly Basic Python Programming benchmark
Multi-Metric Comparison
Radar view across core capabilities
Score by Category
Normalized 0–100. Higher is better.

HumanEval (pass@1)Glyph 3.0, Fresco 80.0
MBPPGlyph 3.0, Fresco 75.0
Instruction FollowingGlyph 14.2, Fresco 91.4
ReasoningGlyph 7.8, Fresco 87.6
Context UnderstandingGlyph 11.4, Fresco 88.2
Full Benchmark Table
All scores, improvement deltas

Benchmark Glyph 1.1 Fresco 1.2 Delta
HumanEval (pass@1) 3.0% 80.0% +77.0pts
MBPP 3.0% 75.0% +72.0pts
Instruction Following 14.2% 91.4% +77.2pts
Reasoning 7.8% 87.6% +79.8pts
Context Understanding 11.4% 88.2% +76.8pts
Fresco 1.2 is now available in Sennoric.