All models

TheoVexUnited States· released Jul 2026

TheoArca Magnus 5.1

Independent verification TBD. Internal evaluation pending.

TheoVex's deep-reasoning engine, served through Theo's governed gateway.

No scores yetNo scores yet
Theo

Available in Theo as Theo Arca Magnus

Theo orchestrates it for the steps it does best and always shows which engine answered.

Use it in Theo

Snapshot September 8, 2026

OpenCharts Index

No internal run recorded yet

Hard-set score

TBD

Counted from third-party scores only. Internal runs never feed it.

Internal · independent verification TBD

Independent verification: TBD

No third-party publisher has scored this engine yet. OpenCharts has not recorded an internal run for it yet, so every benchmark below reads TBD. Internal scores are marked on every surface, rank in the same table, and never lead a spotlight. Read the internal protocol.

Scores

Every test, every source

The best published run per benchmark, the raw value as the publisher reports it, who produced the number, how close it comes to the best published result on that test, and where the model sits among every model scored on it. Percent scores are read above chance, Arena ratings as a win rate against the board leader, open-ended values on a log scale. A test with too few models to compare against is shown but not counted.

GPQA DiamondReasoning

TBD

Internal run not recorded yet.

TBD

Internal run not recorded yet.

ARC-AGI-2Reasoning

TBD

Internal run not recorded yet.

ARC-AGI-1Reasoning

TBD

Internal run not recorded yet.

LiveBenchReasoning

TBD

Needs an agent harness; not internally runnable yet.

SimpleBenchReasoning

TBD

Needs an agent harness; not internally runnable yet.

CritPtReasoning

TBD

Needs an agent harness; not internally runnable yet.

TBD

Internal run not recorded yet.

TBD

Needs an agent harness; not internally runnable yet.

TBD

Needs an agent harness; not internally runnable yet.

SciCodeCoding

TBD

Needs an agent harness; not internally runnable yet.

WeirdMLCoding

TBD

Needs an agent harness; not internally runnable yet.

TBD

Needs an agent harness; not internally runnable yet.

TBD

Needs an agent harness; not internally runnable yet.

TBD

Needs an agent harness; not internally runnable yet.

TBD

Internal run not recorded yet.

TBD

Internal run not recorded yet.

TBD

Needs an agent harness; not internally runnable yet.

TBD

Needs an agent harness; not internally runnable yet.

TBD

Needs an agent harness; not internally runnable yet.

TBD

Needs an agent harness; not internally runnable yet.

GDPvalAgentic

TBD

Needs an agent harness; not internally runnable yet.

TBD

Needs an agent harness; not internally runnable yet.

TBD

Needs an agent harness; not internally runnable yet.

TBD

Needs an agent harness; not internally runnable yet.

TBD

Needs an agent harness; not internally runnable yet.

CybenchAgentic

TBD

Needs an agent harness; not internally runnable yet.

TBD

Needs an agent harness; not internally runnable yet.

Vision ArenaMultimodal

TBD

Needs an agent harness; not internally runnable yet.

Text ArenaHuman preference

TBD

Needs an agent harness; not internally runnable yet.

Fiction.LiveBenchLong context

TBD

Needs an agent harness; not internally runnable yet.

Top of the leaderboard

Compare with its neighbours.

Theo

The best models, ranked here, working inside Theo.

28 of the models on this page run inside Theo today. Theo picks the right one for each step and always shows which engine answered.