RotomArenaAI gaming benchmark • 2 benchmarks

Language model

Hy4 Preview

Released

tencent/hy4-preview via openrouterprovisional

Rating (95% CI)
—
Rank
—
Record
0–0
Win rate
0%
Turns played
27
Switch rate
27%
Median Mega Evolution turn
never
Autopilot rate
57.7%
Hallucinated moves
3.7%
Tokens per turn
13,154
Cost per game
$0.460

Style

Signature move
Crunch
Most time on the field
Rotomwash

In its own words

...
Shortest explanation on record.
Plan: Excadrill switched in to counter Clefable; next turn Iron Head (Steel, 2x) should KO. Keep Tyranitar for Dragapult (Crunch super effective). Rotom-Wash handles Garchomp with Hydro Pump. Sandstorm 7 turns left; Excadrill fast in sand. Opponent's third mon unknown (Garchomp/Gengar/Rotom/Tyranitar). Clefable may use Moonblast/status; Excadrill resists Fairy.
Longest explanation on record.

Its own teams

Built by the model itself from the rules of each format. How teams are built.

draft 1 of 3six picked on attempt 1sets legal on attempt 4

"Incineroar provides Intimidate and Fake Out support with Parting Shot to pivot, while Rotom-Wash and Primarina offer special offense and utility through Will-O-Wisp, pivoting, and coverage. Garchomp and Kingambit act as powerful physical sweepers, with Kingambit using Sucker Punch priority and Garchomp boosting with Swords Dance, and Mimikyu uses Disguise to safely set up Swords Dance and sweep with priority Shadow Sneak. The items and EV spreads maximize each role within the limits, including Garchomp holding Garchompite to Mega Evolve."

Full sets
Incineroar @ Sitrus Berry
Intimidate · Adamant · 32 HP / 32 Atk / 2 Def
  • Fake Out
  • Parting Shot
  • Will-O-Wisp
  • Flare Blitz
Rotom-Wash @ Leftovers
Levitate · Timid · 2 HP / 32 SpA / 32 Spe
  • Hydro Pump
  • Volt Switch
  • Will-O-Wisp
  • Nasty Plot
Garchomp @ Garchompite
Rough Skin · Jolly · 2 HP / 32 Atk / 32 Spe
  • Swords Dance
  • Earthquake
  • Dragon Claw
  • Fire Fang
Mimikyu @ Life Orb
Disguise · Jolly · 2 HP / 32 Atk / 32 Spe
  • Swords Dance
  • Play Rough
  • Shadow Sneak
  • Drain Punch
Kingambit @ Lum Berry
Supreme Overlord · Adamant · 32 HP / 32 Atk / 2 Def
  • Swords Dance
  • Sucker Punch
  • Kowtow Cleave
  • Iron Head
Primarina @ Mystic Water
Liquid Voice · Modest · 32 HP / 32 SpA / 2 Spe
  • Hyper Voice
  • Moonblast
  • Ice Beam
  • Flip Turn
Rejected sets (3)

Attempt 1

  • No <team>...</team> block found (the answer was cut off at the token budget).

Attempt 2

  • No <team>...</team> block found (the answer was cut off at the token budget).

Attempt 3

  • ... is not among the six Pokémon you picked (Incineroar, Rotom-Wash, Garchomp, Mimikyu, Kingambit, Primarina).
  • Your <team> block has 1 Pokémon; it needs all six you picked, inside one <team>...</team> block. Missing: Incineroar, Rotom-Wash, Garchomp, Mimikyu, Kingambit, Primarina.
  • You must bring at least 6 Pokémon (your team has 1).
  • The Pokemon "" does not exist.
draft 2 of 3six picked on attempt 1sets legal on attempt 2

"The team still centers on Tyranitar's Sand Stream plus Smooth Rock to keep sand up for Excadrill's Sand Rush sweep, with Rotom-Wash and Incineroar providing pivoting, Intimidate, and status to bring sweepers in safely. Dragonite and Mimikyu use Multiscale and Disguise to set up and clean, while Incineroar now runs Taunt over the illegal Knock Off to shut down opposing setup and support Pokémon."

Full sets
Tyranitar @ Smooth Rock
Sand Stream · Adamant · 32 HP / 32 Atk / 2 SpD
  • Rock Slide
  • Crunch
  • Earthquake
  • Stealth Rock
Excadrill @ Life Orb
Sand Rush · Jolly · 2 HP / 32 Atk / 32 Spe
  • Earthquake
  • Iron Head
  • Rock Slide
  • Swords Dance
Rotom-Wash @ Sitrus Berry
Levitate · Bold · 32 HP / 32 Def / 2 SpD
  • Volt Switch
  • Hydro Pump
  • Will-O-Wisp
  • Thunder Wave
Dragonite @ Lum Berry
Multiscale · Jolly · 2 HP / 32 Atk / 32 Spe
  • Dragon Dance
  • Extreme Speed
  • Earthquake
  • Roost
Mimikyu @ Focus Sash
Disguise · Jolly · 2 HP / 32 Atk / 32 Spe
  • Swords Dance
  • Play Rough
  • Shadow Sneak
  • Drain Punch
Incineroar @ Leftovers
Intimidate · Careful · 32 HP / 32 Atk / 2 SpD
  • Parting Shot
  • Flare Blitz
  • Fake Out
  • Taunt
Rejected sets (1)

Attempt 1

  • Incineroar can't learn Knock Off.
draft 3 of 3six picked on attempt 1sets legal on attempt 3

"Incineroar leads with Intimidate and Fake Out before pivoting with Parting Shot, while Garchomp and Mimikyu use Swords Dance to become dangerous setup sweepers. Rotom-Wash acts as a bulky Volt Switch pivot that spreads burns with Will-O-Wisp, and Primarina and Hydreigon provide powerful special attacking pressure, with Hydreigon using a Choice Scarf to outspeed and revenge kill with its wide coverage."

Full sets
Incineroar @ Sitrus Berry
Intimidate · Adamant · 32 HP / 32 Atk / 2 SpD
  • Fake Out
  • Flare Blitz
  • Darkest Lariat
  • Parting Shot
Garchomp @ Life Orb
Rough Skin · Jolly · 2 HP / 32 Atk / 32 Spe
  • Swords Dance
  • Earthquake
  • Dragon Claw
  • Fire Fang
Rotom-Wash @ Leftovers
Levitate · Bold · 32 HP / 32 Def / 2 SpD
  • Volt Switch
  • Hydro Pump
  • Will-O-Wisp
  • Protect
Mimikyu @ Lum Berry
Disguise · Jolly · 2 HP / 32 Atk / 32 Spe
  • Swords Dance
  • Play Rough
  • Shadow Claw
  • Shadow Sneak
Primarina @ Mystic Water
Liquid Voice · Modest · 2 HP / 32 SpA / 32 Spe
  • Hydro Pump
  • Moonblast
  • Hyper Voice
  • Ice Beam
Hydreigon @ Choice Scarf
Levitate · Timid · 2 HP / 32 SpA / 32 Spe
  • Draco Meteor
  • Dark Pulse
  • Fire Blast
  • Earth Power
Rejected sets (2)

Attempt 1

  • No <team>...</team> block found (the answer was cut off at the token budget).

Attempt 2

  • No <team>...</team> block found (the answer was cut off at the token budget).

Matches

No rated matches yet.