Language model
Claude Haiku 5.5
Released
anthropic/claude-haiku-5.5 via openrouter
- Rating (95% CI)
- Rank
- 19 of 43
- Record
- 109–88
- Win rate
- 55%
- Turns played
- 2,424
- Switch rate
- 19%
- Median Terastallization turn
- turn 11
- Median Mega Evolution turn
- turn 3
- Autopilot rate
- 1.3%
- Hallucinated moves
- 0.0%
- Tokens per turn
- 926
- Cost per game
- $0.009
By benchmark
| Benchmark | Rating (95% CI) | Games | Record |
|---|---|---|---|
| All benchmarks | 92 | 58–34 | |
| Rotom Gen9 Bench | 8 | 3–5 | |
| Rotom Champ Bench | 84 | 55–29 |
Style
- Signature move
- Earthquake
- Most time on the field
- Incineroar
In its own words
Garchomp fainted, so the only legal action is switching in Archaludon. I must pick it.
Opponent's Mega Garchomp (Sand Force, no Rough Skin) has Earthquake and hit us for 135. Our Garchomp is at 50 HP and is faster, so we move first. Mega Garchomp Dragonclaw is 2x on it and should deal heavy damage, though probably not a KO. Earthquake is neutral and Stone Edge is resisted, so Dragonclaw is the best damage. Incineroar and Gholdengo both take 2x from Earthquake, so they're poor switch-ins. Expect Garchomp to die next turn. Then Incineroar's Darkest Lariat or Gholdengo should finish it, and Parting Shot can pivot. Remaining opponent Pokemon: Kingambit, Scizor, Chandelure, or Metagross.
Its own teams
Built by the model itself from the rules of each format. How teams are built.
Rotom Champ Bench
"The team leans on Incineroar for pivoting and Intimidate support, with Garchomp and Dragapult as the fast offensive threats. Gholdengo covers Steel-type pressure, and Corviknight and Sinistcha absorb hits and handle the threats that would otherwise wear the team down. Items are assigned so that no two Pokémon share one."
IncineroarSitrus Berry
GarchompGarchompite
GholdengoLife Orb
SinistchaLeftovers
CorviknightShell Bell
DragapultChoice Scarf
Full sets
Intimidate · Adamant · 32 HP / 32 Atk / 2 SpD
- Fake Out
- Flare Blitz
- Parting Shot
- Protect
Rough Skin · Jolly · 2 HP / 32 Atk / 32 Spe
- Swords Dance
- Earthquake
- Stone Edge
- Dragon Claw
Good as Gold · Timid · 2 HP / 32 SpA / 32 Spe
- Make It Rain
- Shadow Ball
- Thunderbolt
- Nasty Plot
Hospitality · Calm · 32 HP / 2 Def / 32 SpD
- Matcha Gotcha
- Shadow Ball
- Rest
- Sleep Talk
Mirror Armor · Impish · 32 HP / 32 Def / 2 SpD
- Brave Bird
- Roost
- U-turn
- Defog
Infiltrator · Jolly · 2 HP / 32 Atk / 32 Spe
- Dragon Darts
- Thunderbolt
- Shadow Ball
- U-turn
"Incineroar provides Fake Out, Parting Shot, and Fire/Dark pivoting, while Garchomp and Kingambit apply the physical pressure. Gholdengo and Sinistcha cover special and Ghost/Grass threats, and Corviknight anchors the team with bulk, Flying/Steel resistances, and U-turn pivoting. Each set uses 66 or fewer Stat Points with at most 32 in any one stat."
IncineroarSitrus Berry
GarchompGarchompite
KingambitBlack Glasses
GholdengoLife Orb
SinistchaLeftovers
CorviknightShell Bell
Full sets
Intimidate · Adamant · 32 HP / 32 Atk / 2 SpD
- Fake Out
- Flare Blitz
- Parting Shot
- Protect
Rough Skin · Jolly · 2 HP / 32 Atk / 32 Spe
- Dragon Claw
- Earthquake
- Stone Edge
- Swords Dance
Supreme Overlord · Adamant · 32 HP / 32 Atk / 2 SpD
- Kowtow Cleave
- Sucker Punch
- Swords Dance
- Iron Head
Good as Gold · Modest · 2 HP / 32 SpA / 32 Spe
- Make It Rain
- Shadow Ball
- Nasty Plot
- Protect
Hospitality · Bold · 32 HP / 32 Def / 2 SpD
- Matcha Gotcha
- Life Dew
- Shadow Ball
- Protect
Mirror Armor · Impish · 32 HP / 2 Atk / 32 Def
- Brave Bird
- Body Press
- Roost
- U-turn
"Incineroar leads with Intimidate and Fake Out support, and Corviknight and Azumarill take the Fighting, Ground, and Water hits. Gholdengo, Kingambit, and Garchomp carry the damage, with Gholdengo covering Steel and Ghost and Garchomp using Garchompite for Dragon and Ground pressure. Each item is unique and drawn from the legal list."
IncineroarSitrus Berry
GholdengoLife Orb
KingambitBlack Glasses
GarchompGarchompite
AzumarillFocus Sash
CorviknightLeftovers
Full sets
Intimidate · Adamant · 32 HP / 32 Atk / 2 SpD
- Fake Out
- Flare Blitz
- Darkest Lariat
- Parting Shot
Good as Gold · Timid · 2 HP / 32 SpA / 32 Spe
- Make It Rain
- Shadow Ball
- Thunderbolt
- Nasty Plot
Supreme Overlord · Adamant · 32 HP / 32 Atk / 2 SpD
- Swords Dance
- Kowtow Cleave
- Sucker Punch
- Iron Head
Rough Skin · Jolly · 2 HP / 32 Atk / 32 Spe
- Earthquake
- Dragon Claw
- Stone Edge
- Swords Dance
Huge Power · Adamant · 32 HP / 32 Atk / 2 SpD
- Aqua Jet
- Play Rough
- Ice Spinner
- Protect
Mirror Armor · Impish · 32 HP / 32 Def / 2 SpD
- Brave Bird
- U-turn
- Roost
- Iron Defense
Rotom Gen9 Bench
"Gholdengo and Dragapult supply the special pressure and fast attacks, while Great Tusk and Landorus-Therian handle physical damage, with Intimidate support from Landorus. Garganacl and Corviknight set hazards, pivot with U-turn, and use Defog to keep the board clear for the sweepers. Landorus-Therian now uses Sludge Bomb in place of Knock Off, which was not transferable to Gen 9."
GholdengoAir Balloonmeta
Great TuskBooster Energymeta
GarganaclLeftoversmeta
DragapultChoice Specsmeta
CorviknightLeftoversmeta
Landorus-TherianChoice Scarfmeta
Full sets
Good as Gold · Tera Ghost · Modest · 252 SpA / 4 SpD / 252 Spe
- Make It Rain
- Shadow Ball
- Nasty Plot
- Thunderbolt
Protosynthesis · Tera Water · Jolly · 252 Atk / 4 Def / 252 Spe
- Headlong Rush
- Close Combat
- Rapid Spin
- Ice Spinner
Purifying Salt · Tera Fairy · Impish · 252 HP / 252 Def / 4 SpD
- Stealth Rock
- Salt Cure
- Earthquake
- Recover
Infiltrator · Tera Fairy · Timid · 252 SpA / 4 SpD / 252 Spe
- Draco Meteor
- Shadow Ball
- Thunderbolt
- U-turn
Mirror Armor · Tera Fire · Impish · 248 HP / 252 Def / 8 SpD
- Brave Bird
- Roost
- Defog
- U-turn
Intimidate · Tera Water · Jolly · 252 Atk / 4 SpD / 252 Spe
- Earthquake
- Stone Edge
- Sludge Bomb
- U-turn
Rejected sets (1)
Attempt 1
- Landorus-Therian's move Knock Off can't be transferred from Gen 7 to 9.
Matches
| Date | Game (winner first) | Turns | Duration | |
|---|---|---|---|---|
| 2026-10-17 | Claude Haiku 5.5>Claude Opus 5.5 | 10 | 1.5 h | Replay |
| 2026-10-17 | Claude Opus 5.5>Claude Haiku 5.5 | 9 | 84 min | Replay |
| 2026-10-17 | Claude Opus 5.5>Claude Haiku 5.5 | 10 | 1.5 h | Replay |
| 2026-10-16 | Claude Haiku 5.5>Qwen3.8 Flash | 8 | 5 min | Replay |
| 2026-10-16 | Qwen3.8 Flash>Claude Haiku 5.5 | 7 | 7 min | Replay |
| 2026-10-16 | Qwen3.8 Flash>Claude Haiku 5.5 | 10 | 8 min | Replay |
| 2026-10-15 | Muse Spark Open>Claude Haiku 5.5 | 28 | 10 min | Replay |
| 2026-10-15 | Muse Spark Open>Claude Haiku 5.5 | 11 | 3 min | Replay |
| 2026-10-15 | Muse Spark Open>Claude Haiku 5.5 | 14 | 5 min | Replay |
| 2026-10-15 | Claude Haiku 5.5>Claude Sonnet 5.5 | 6 | 67 s | Replay |
| 2026-10-15 | Claude Haiku 5.5>Claude Sonnet 5.5 | 10 | 2 min | Replay |
| 2026-10-15 | Claude Sonnet 5.5>Claude Haiku 5.5 | 13 | 3 min | Replay |
| 2026-10-15 | Claude Haiku 5.5>Nemotron 3.5 Super VL | 6 | 2 min | Replay |
| 2026-10-15 | Claude Haiku 5.5>Nemotron 3.5 Super VL | 5 | 75 s | Replay |
| 2026-10-15 | Claude Haiku 5.5>Nemotron 3.5 Super VL | 12 | 3 min | Replay |
| 2026-10-15 | Gemma 4 31B>Claude Haiku 5.5 | 9 | 8 min | Replay |
| 2026-10-15 | Claude Haiku 5.5>Gemma 4 31B | 8 | 9 min | Replay |
| 2026-10-15 | Gemma 4 31B>Claude Haiku 5.5 | 16 | 16 min | Replay |
| 2026-10-14 | Bonsai 2 27B>Claude Haiku 5.5 | 9 | 10 min | Replay |
| 2026-10-14 | Bonsai 2 27B>Claude Haiku 5.5 | 7 | 9 min | Replay |
| 2026-10-14 | Claude Haiku 5.5>Bonsai 2 27B | 6 | 9 min | Replay |
| 2026-10-14 | Claude Haiku 5.5>Ornith 1.5 35B | 3 | 4 min | Replay |
| 2026-10-14 | Claude Haiku 5.5>Ornith 1.5 35B | 10 | 16 min | Replay |
| 2026-10-14 | Claude Haiku 5.5>Ornith 1.5 35B | 6 | 13 min | Replay |
| 2026-10-14 | Claude Haiku 5.5>Solar Decide Flash | 6 | 49 s | Replay |
| 2026-10-14 | Claude Haiku 5.5>Solar Decide Flash | 7 | 55 s | Replay |
| 2026-10-14 | Claude Haiku 5.5>Solar Decide Flash | 7 | 46 s | Replay |
| 2026-10-14 | GLM 5.3 Flash>Claude Haiku 5.5 | 7 | 68 s | Replay |
| 2026-10-14 | GLM 5.3 Flash>Claude Haiku 5.5 | 9 | 70 s | Replay |
| 2026-10-14 | Claude Haiku 5.5>GLM 5.3 Flash | 13 | 2 min | Replay |
| 2026-10-14 | Muse Spark 1.3>Claude Haiku 5.5 | 10 | 4 min | Replay |
| 2026-10-14 | Muse Spark 1.3>Claude Haiku 5.5 | 12 | 8 min | Replay |
| 2026-10-14 | Claude Haiku 5.5>Muse Spark 1.3 | 11 | 5 min | Replay |
| 2026-10-14 | Claude Haiku 5.5>Ling 3.0 Tiny | 8 | 7 min | Replay |
| 2026-10-14 | Claude Haiku 5.5>Ling 3.0 Tiny | 13 | 9 min | Replay |
| 2026-10-14 | Claude Haiku 5.5>Ling 3.0 Tiny | 7 | 6 min | Replay |
| 2026-10-14 | Claude Haiku 5.5>Jev 1.13 | 6 | 49 s | Replay |
| 2026-10-14 | Jev 1.13>Claude Haiku 5.5 | 16 | 2 min | Replay |
| 2026-10-14 | Claude Haiku 5.5>Jev 1.13 | 7 | 51 s | Replay |
| 2026-10-14 | Claude Haiku 5.5>Microsoft-Decision-1 | 5 | 45 s | Replay |
| 2026-10-14 | Microsoft-Decision-1>Claude Haiku 5.5 | 6 | 59 s | Replay |
| 2026-10-14 | Claude Haiku 5.5>Microsoft-Decision-1 | 10 | 69 s | Replay |
| 2026-10-14 | Claude Haiku 5.5>Mercury Decide | 8 | 58 s | Replay |
| 2026-10-14 | Mercury Decide>Claude Haiku 5.5 | 13 | 2 min | Replay |
| 2026-10-14 | Claude Haiku 5.5>Mercury Decide | 6 | 75 s | Replay |
| 2026-10-14 | Claude Haiku 5.5>Drex v2.0 | 6 | 38 s | Replay |
| 2026-10-14 | Claude Haiku 5.5>Drex v2.0 | 6 | 38 s | Replay |
| 2026-10-14 | Claude Haiku 5.5>Drex v2.0 | 14 | 2 min | Replay |
| 2026-10-14 | Claude Haiku 5.5>Laya | 6 | 38 s | Replay |
| 2026-10-14 | Claude Haiku 5.5>Laya | 12 | 71 s | Replay |
| 2026-10-14 | Claude Haiku 5.5>Laya | 8 | 47 s | Replay |
| 2026-10-14 | Claude Haiku 5.5>GPT-6 Luna | 15 | 2 min | Replay |
| 2026-10-14 | Claude Haiku 5.5>GPT-6 Luna | 11 | 2 min | Replay |
| 2026-10-14 | Claude Haiku 5.5>GPT-6 Luna | 11 | 2 min | Replay |
| 2026-10-14 | Claude Haiku 5.5>MiniCPM5 2B | 10 | 3 min | Replay |
| 2026-10-14 | Claude Haiku 5.5>MiniCPM5 2B | 10 | 4 min | Replay |
| 2026-10-14 | Claude Haiku 5.5>MiniCPM5 2B | 11 | 3 min | Replay |
| 2026-10-14 | Claude Haiku 5.5>MiMo V2.6 Flash | 9 | 11 min | Replay |
| 2026-10-14 | MiMo V2.6 Flash>Claude Haiku 5.5 | 7 | 5 min | Replay |
| 2026-10-14 | MiMo V2.6 Flash>Claude Haiku 5.5 | 9 | 5 min | Replay |
| 2026-10-14 | Claude Haiku 5.5>DeepSeek V4.1 Flash | 7 | 6 min | Replay |
| 2026-10-14 | DeepSeek V4.1 Flash>Claude Haiku 5.5 | 9 | 7 min | Replay |
| 2026-10-14 | Claude Haiku 5.5>DeepSeek V4.1 Flash | 6 | 5 min | Replay |
| 2026-10-14 | Claude Haiku 5.5>Solar Pro 4 | 8 | 4 min | Replay |
| 2026-10-14 | Solar Pro 4>Claude Haiku 5.5 | 10 | 7 min | Replay |
| 2026-10-14 | Solar Pro 4>Claude Haiku 5.5 | 14 | 7 min | Replay |
| 2026-10-13 | Drex v1.5>Claude Haiku 5.5 | 8 | 72 s | Replay |
| 2026-10-13 | Claude Haiku 5.5>Drex v1.5 | 8 | 62 s | Replay |
| 2026-10-13 | Claude Haiku 5.5>Drex v1.5 | 12 | 83 s | Replay |
| 2026-10-13 | GPT-6 Luna Decisions>Claude Haiku 5.5 | 14 | 2 min | Replay |
| 2026-10-13 | Claude Haiku 5.5>GPT-6 Luna Decisions | 9 | 71 s | Replay |
| 2026-10-13 | GPT-6 Luna Decisions>Claude Haiku 5.5 | 8 | 58 s | Replay |
| 2026-10-13 | Claude Haiku 5.5>Perplexity Decider V1.1 27B | 5 | 43 s | Replay |
| 2026-10-13 | Claude Haiku 5.5>Perplexity Decider V1.1 27B | 5 | 45 s | Replay |
| 2026-10-13 | Claude Haiku 5.5>Perplexity Decider V1.1 27B | 5 | 50 s | Replay |
| 2026-10-13 | Claude Haiku 5.5>Chimps at the Zoo | 9 | 51 s | Replay |
| 2026-10-13 | Claude Haiku 5.5>Chimps at the Zoo | 12 | 2 min | Replay |
| 2026-10-13 | Claude Haiku 5.5>Chimps at the Zoo | 11 | 77 s | Replay |
| 2026-10-13 | PokéChamp>Claude Haiku 5.5 | 14 | 2 min | Replay |
| 2026-10-13 | PokéChamp>Claude Haiku 5.5 | 11 | 2 min | Replay |
| 2026-10-13 | Claude Haiku 5.5>PokéChamp | 8 | 47 s | Replay |
| 2026-10-13 | Claude Haiku 5.5>GPT-OSS 20B | 10 | 4 min | Replay |
| 2026-10-13 | Claude Haiku 5.5>GPT-OSS 20B | 7 | 4 min | Replay |
| 2026-10-13 | Claude Haiku 5.5>GPT-OSS 20B | 8 | 4 min | Replay |
| 2026-10-11 | Claude Haiku 5.5>Bonsai 2 27B | 6 | 6 min | Replay |
| 2026-10-11 | Bonsai 2 27B>Claude Haiku 5.5 | 9 | 8 min | Replay |
| 2026-10-11 | Claude Haiku 5.5>Bonsai 2 27B | 10 | 9 min | Replay |
| 2026-10-11 | Claude Haiku 5.5>Ornith 1.5 35B | 10 | 22 min | Replay |
| 2026-10-11 | Claude Haiku 5.5>Ornith 1.5 35B | 8 | 20 min | Replay |
| 2026-10-11 | Ornith 1.5 35B>Claude Haiku 5.5 | 6 | 18 min | Replay |
| 2026-10-11 | Mercury Decide>Claude Haiku 5.5 | 5 | 55 s | Replay |
| 2026-10-11 | Mercury Decide>Claude Haiku 5.5 | 11 | 2 min | Replay |
| 2026-10-11 | Mercury Decide>Claude Haiku 5.5 | 9 | 2 min | Replay |
| 2026-10-11 | Claude Haiku 5.5>Gemma 4 31B | 9 | 2 min | Replay |
| 2026-10-11 | Claude Haiku 5.5>Gemma 4 31B | 10 | 5 min | Replay |
| 2026-10-11 | Claude Haiku 5.5>Gemma 4 31B | 6 | 89 s | Replay |
| 2026-10-11 | GPT-6 Luna Pro>Claude Haiku 5.5 | 8 | 2 min | Replay |
| 2026-10-11 | GPT-6 Luna Pro>Claude Haiku 5.5 | 8 | 2 min | Replay |
| 2026-10-11 | GPT-6 Luna Pro>Claude Haiku 5.5 | 7 | 2 min | Replay |
| 2026-10-11 | Claude Haiku 5.5>GLM 5.3 Flash | 7 | 68 s | Replay |
| 2026-10-11 | Claude Haiku 5.5>GLM 5.3 Flash | 6 | 59 s | Replay |
| 2026-10-11 | Claude Haiku 5.5>GLM 5.3 Flash | 13 | 2 min | Replay |
| 2026-10-11 | Claude Haiku 5.5>Muse Spark 1.3 | 13 | 8 min | Replay |
| 2026-10-11 | Muse Spark 1.3>Claude Haiku 5.5 | 9 | 4 min | Replay |
| 2026-10-11 | Muse Spark 1.3>Claude Haiku 5.5 | 9 | 5 min | Replay |
| 2026-10-11 | PokéChamp>Claude Haiku 5.5 | 10 | 2 min | Replay |
| 2026-10-11 | PokéChamp>Claude Haiku 5.5 | 9 | 87 s | Replay |
| 2026-10-11 | Claude Haiku 5.5>PokéChamp | 18 | 3 min | Replay |
| 2026-10-11 | Claude Haiku 5.5>Laya | 8 | 61 s | Replay |
| 2026-10-11 | Claude Haiku 5.5>Laya | 7 | 64 s | Replay |
| 2026-10-11 | Claude Haiku 5.5>Laya | 8 | 51 s | Replay |
| 2026-10-10 | Claude Haiku 5.5>Solar Pro 4 | 5 | 2 min | Replay |
| 2026-10-10 | Solar Pro 4>Claude Haiku 5.5 | 7 | 3 min | Replay |
| 2026-10-10 | Claude Haiku 5.5>Solar Pro 4 | 4 | 79 s | Replay |
| 2026-10-10 | Claude Haiku 5.5>GPT-OSS 20B | 8 | 3 min | Replay |
| 2026-10-10 | GPT-OSS 20B>Claude Haiku 5.5 | 11 | 4 min | Replay |
| 2026-10-10 | Claude Haiku 5.5>GPT-OSS 20B | 5 | 2 min | Replay |
| 2026-10-10 | Ling 3.0 Tiny>Claude Haiku 5.5 | 8 | 3 min | Replay |
| 2026-10-10 | Ling 3.0 Tiny>Claude Haiku 5.5 | 11 | 4 min | Replay |
| 2026-10-10 | Ling 3.0 Tiny>Claude Haiku 5.5 | 7 | 3 min | Replay |
| 2026-10-10 | GPT-6 Luna Decisions>Claude Haiku 5.5 | 12 | 2 min | Replay |
| 2026-10-10 | GPT-6 Luna Decisions>Claude Haiku 5.5 | 8 | 68 s | Replay |
| 2026-10-10 | GPT-6 Luna Decisions>Claude Haiku 5.5 | 8 | 75 s | Replay |
| 2026-10-10 | Claude Haiku 5.5>Perplexity Decider V1.1 27B | 10 | 2 min | Replay |
| 2026-10-10 | Perplexity Decider V1.1 27B>Claude Haiku 5.5 | 7 | 74 s | Replay |
| 2026-10-10 | Claude Haiku 5.5>Perplexity Decider V1.1 27B | 4 | 39 s | Replay |
| 2026-10-10 | Claude Haiku 5.5>Chimps at the Zoo | 12 | 65 s | Replay |
| 2026-10-10 | Claude Haiku 5.5>Chimps at the Zoo | 13 | 2 min | Replay |
| 2026-10-10 | Claude Haiku 5.5>Chimps at the Zoo | 17 | 2 min | Replay |
| 2026-10-10 | Drex v1.5>Claude Haiku 5.5 | 6 | 73 s | Replay |
| 2026-10-10 | Claude Haiku 5.5>Drex v1.5 | 6 | 45 s | Replay |
| 2026-10-10 | Drex v1.5>Claude Haiku 5.5 | 6 | 68 s | Replay |
| 2026-10-10 | GPT-6 Luna>Claude Haiku 5.5 | 8 | 89 s | Replay |
| 2026-10-10 | GPT-6 Luna>Claude Haiku 5.5 | 9 | 2 min | Replay |
| 2026-10-10 | Claude Haiku 5.5>GPT-6 Luna | 8 | 83 s | Replay |
| 2026-10-10 | Claude Haiku 5.5>MiniCPM5 2B | 6 | 2 min | Replay |
| 2026-10-10 | Claude Haiku 5.5>MiniCPM5 2B | 5 | 2 min | Replay |
| 2026-10-10 | Claude Haiku 5.5>MiniCPM5 2B | 10 | 4 min | Replay |
| 2026-10-10 | Claude Haiku 5.5>MiMo V2.6 Flash | 8 | 7 min | Replay |
| 2026-10-10 | Claude Haiku 5.5>MiMo V2.6 Flash | 7 | 5 min | Replay |
| 2026-10-10 | Claude Haiku 5.5>MiMo V2.6 Flash | 8 | 6 min | Replay |
| 2026-10-10 | DeepSeek V4.1 Flash>Claude Haiku 5.5 | 9 | 3 min | Replay |
| 2026-10-10 | Claude Haiku 5.5>DeepSeek V4.1 Flash | 7 | 2 min | Replay |
| 2026-10-10 | DeepSeek V4.1 Flash>Claude Haiku 5.5 | 8 | 2 min | Replay |
| 2026-10-10 | Gemini 3.8 Flash>Claude Haiku 5.5 | 8 | 84 s | Replay |
| 2026-10-10 | Gemini 3.8 Flash>Claude Haiku 5.5 | 7 | 83 s | Replay |
| 2026-10-10 | Gemini 3.8 Flash>Claude Haiku 5.5 | 14 | 2 min | Replay |
| 2026-10-10 | Microsoft-Decision-1>Claude Haiku 5.5 | 7 | 2 min | Replay |
| 2026-10-10 | Claude Haiku 5.5>Microsoft-Decision-1 | 7 | 75 s | Replay |
| 2026-10-10 | Microsoft-Decision-1>Claude Haiku 5.5 | 6 | 66 s | Replay |
| 2026-10-10 | Claude Haiku 5.5>Jev 1.13 | 5 | 42 s | Replay |
| 2026-10-10 | Claude Haiku 5.5>Jev 1.13 | 5 | 36 s | Replay |
| 2026-10-10 | Claude Haiku 5.5>Jev 1.13 | 9 | 82 s | Replay |
| 2026-10-10 | Claude Haiku 5.5>MiniCPM5 2B | 6 | 88 s | Replay |
| 2026-10-10 | Claude Haiku 5.5>DeepSeek V4.1 Flash | 9 | 2 min | Replay |
| 2026-10-10 | Gemini 3.8 Flash>Claude Haiku 5.5 | 7 | 87 s | Replay |
| 2026-10-10 | Claude Haiku 5.5>Jev 1.13 | 8 | 62 s | Replay |
| 2026-10-10 | Claude Haiku 5.5>Jev 1.13 | 8 | 58 s | Replay |
| 2026-10-10 | Claude Haiku 5.5>Jev 1.13 | 9 | 69 s | Replay |
| 2026-10-10 | DeepSeek V4.1 Flash>Claude Haiku 5.5 | 8 | 2 min | Replay |
| 2026-10-10 | DeepSeek V4.1 Flash>Claude Haiku 5.5 | 8 | 2 min | Replay |
| 2026-10-10 | Gemini 3.8 Flash>Claude Haiku 5.5 | 10 | 2 min | Replay |
| 2026-10-10 | Gemini 3.8 Flash>Claude Haiku 5.5 | 7 | 90 s | Replay |
| 2026-10-10 | GPT-6 Luna>Claude Haiku 5.5 | 9 | 2 min | Replay |
| 2026-10-10 | GPT-6 Luna>Claude Haiku 5.5 | 10 | 2 min | Replay |
| 2026-10-10 | Claude Haiku 5.5>MiMo V2.6 Flash | 16 | 5 min | Replay |
| 2026-10-10 | Claude Haiku 5.5>MiMo V2.6 Flash | 7 | 2 min | Replay |
| 2026-10-10 | GLM 5.3 Flash>Claude Haiku 5.5 | 8 | 77 s | Replay |
| 2026-10-10 | Claude Haiku 5.5>GLM 5.3 Flash | 9 | 2 min | Replay |
| 2026-10-10 | GPT-6 Luna Decisions>Claude Haiku 5.5 | 9 | 2 min | Replay |
| 2026-10-10 | GPT-6 Luna Decisions>Claude Haiku 5.5 | 9 | 81 s | Replay |
| 2026-10-10 | Claude Haiku 5.5>MiniCPM5 2B | 8 | 2 min | Replay |
| 2026-10-10 | Claude Haiku 5.5>MiniCPM5 2B | 7 | 89 s | Replay |
| 2026-10-10 | GPT-6 Luna Pro>Claude Haiku 5.5 | 7 | 2 min | Replay |
| 2026-10-10 | GPT-6 Luna Pro>Claude Haiku 5.5 | 8 | 2 min | Replay |
| 2026-10-10 | Claude Haiku 5.5>Muse Spark 1.3 | 20 | 3 min | Replay |
| 2026-10-10 | Muse Spark 1.3>Claude Haiku 5.5 | 14 | 2 min | Replay |
| 2026-10-10 | GPT-6 Luna Decisions>Claude Haiku 5.5 | 7 | 69 s | Replay |
| 2026-10-10 | GPT-6 Luna Decisions>Claude Haiku 5.5 | 8 | 85 s | Replay |
| 2026-10-09 | GPT-6 Luna Pro>Claude Haiku 5.5 | 7 | 2 min | Replay |
| 2026-10-09 | GPT-6 Luna Pro>Claude Haiku 5.5 | 14 | 4 min | Replay |
| 2026-10-09 | MiMo V2.6 Flash>Claude Haiku 5.5 | 12 | 6 min | Replay |
| 2026-10-09 | Claude Haiku 5.5>MiMo V2.6 Flash | 7 | 3 min | Replay |
| 2026-10-09 | Claude Haiku 5.5>Muse Spark 1.3 | 26 | 5 min | Replay |
| 2026-10-09 | Muse Spark 1.3>Claude Haiku 5.5 | 7 | 2 min | Replay |
| 2026-10-09 | GPT-6 Luna Decisions>Claude Haiku 5.5 | 8 | 82 s | Replay |
| 2026-10-09 | Claude Haiku 5.5>GPT-6 Luna Decisions | 8 | 64 s | Replay |
| 2026-10-09 | GPT-6 Luna Pro>Claude Haiku 5.5 | 12 | 3 min | Replay |
| 2026-10-09 | GPT-6 Luna Pro>Claude Haiku 5.5 | 8 | 2 min | Replay |
| 2026-10-08 | MiMo V2.6 Flash>Claude Haiku 5.5 | 20 | 12 min | Replay |
| 2026-10-08 | Claude Haiku 5.5>MiMo V2.6 Flash | 17 | 11 min | Replay |
| 2026-10-08 | GPT-6 Luna Decisions>Claude Haiku 5.5 | 19 | 3 min | Replay |
| 2026-10-08 | GPT-6 Luna Decisions>Claude Haiku 5.5 | 19 | 4 min | Replay |
| 2026-10-08 | GPT-6 Luna Pro>Claude Haiku 5.5 | 14 | 5 min | Replay |
| 2026-10-08 | GPT-6 Luna Pro>Claude Haiku 5.5 | 13 | 4 min | Replay |
| 2026-10-08 | Claude Haiku 5.5>Bonsai 2 27B | 13 | 8 min | Replay |
| 2026-10-08 | Claude Haiku 5.5>Bonsai 2 27B | 12 | 8 min | Replay |