INTELLECT-1

7 benchmarks · 7 observations · 2 sources · released 2024-11-29

Scores at a glance

7 benchmarks · large dot: INTELLECT-1; small dots: closest models where reported

ARC AI2 ↗54.52%

INTELLECT-1 · ARC AI2 · Challenge score · % ↗

BIG-Bench Hard ↗34.85%

INTELLECT-1 · BBH · Average · % ↗

GSM8K ↗38.58%

INTELLECT-1 · GSM8K · EM · % ↗

HellaSwag ↗71.42%

INTELLECT-1 · HellaSwag · Overall accuracy · % ↗

MMLU ↗49.89%

INTELLECT-1 · MMLU · EM · % ↗

WinoGrande ↗65.82%

INTELLECT-1 · Winogrande · Accuracy · % ↗

Epoch Capabilities Index (ECI) ↗100.54 ECI

INTELLECT-1 · General ECI · 26 October 2026 fit ↗

Closest models by score

Similar positions on shared benchmark leaderboards. Smaller gaps are closer.

There are not enough shared scored settings to identify close comparisons reliably.

Filter comparisons to this model →

Sources

Every plotted observation links to its evaluation. Reported configurations, benchmark versions and task subsets can differ; similarity describes shared scores, not training lift.

INTELLECT-1 Technical Report ↗
Jaghouar, Sami, Ong, Jack Min, Basra, Manveer, Obeid, Fares, Straube, Jannik, Keiblinger, Michael et al. · 2024
All 12 authors
Jaghouar, Sami, Ong, Jack Min, Basra, Manveer, Obeid, Fares, Straube, Jannik, Keiblinger, Michael, Bakouch, Elie, Atkins, Lucas, Panahi, Maziyar, Goddard, Charles, Ryabinin, Max, Hagemann, Johannes
AI benchmarks & capabilities ↗
Epoch AI

Names used in source tables

INTELLECT-1