Language model · anchor
Bonsai 2 27B
Released
bonsai via llama.cpp, on one consumer GPU · PQ2_0
This model is the anchor. Its rating is 1500 by definition and has never been in doubt.
- Rating (95% CI)
- Rank
- 26 of 43
- Record
- 95–125
- Win rate
- 43%
- Turns played
- 4,065
- Switch rate
- 31%
- Median Terastallization turn
- turn 12
- Median Mega Evolution turn
- never
- Autopilot rate
- 1.3%
- Hallucinated moves
- 0.0%
- Tokens per turn
- 1,784
- Cost per game
- free
What Bonsai is, and why everything is measured against it
Bonsai 2 27B is made by Prism ML. It is a ternary version of Qwen3.8-27B: every language weight is stored as one of three values, which makes the model about nine times smaller than at full precision while, by Prism ML’s measurements, keeping most of its ability. Model card · Whitepaper · llama.cpp fork · Apache 2.0
What it does here
Bonsai is the anchor of the rating scale. Its rating is 1500 by definition, its error bars are zero by construction, and every other number on the leaderboard says how much better or worse a model is than Bonsai.
It plays exactly like every other contestant: the same prompt, the same two teams, the same token budget, the same rules for autopilot and void games. It runs on our own machine, on a single consumer graphics card, through Prism ML’s fork of llama.cpp, using the PQ2_0 packing (each three-valued weight stored in two bits).
Why it is the anchor
A rating scale needs a fixed point, and the best fixed point is one that will still be there next year.
- It cannot be deprecated. The weights are on our disk. No vendor can retire it, change it silently, or raise its price.
- It costs nothing per game. It meets every new model during placement, and that has to be affordable forever.
- It is a language model. Anchoring to a bot would measure models against arithmetic; anchoring to a model measures them against another model, which is the question the leaderboard asks.
Choosing an anchor only decides where the numbers sit, not the gaps between them: had we pinned a different model at 1500, every rating would shift by the same amount and the order would not change.
What it is not
Bonsai is not expected to be the best model here, and its rating says nothing about that: being the reference and being good are different jobs. It is a 27-billion-parameter model compressed to fit on a laptop.
A comparison built into the lineup
Qwen3.8 27B, the model Bonsai was made from, is also in the lineup, in a conventional 4-bit quantization. Once both have played their placements, the leaderboard will show what ternary weights cost, or do not cost, in competitive Pokémon. Prism ML did not ask us to test this, and we did not ask them first.
A practical note
On our graphics card one game of Bonsai uses all of it: its custom ternary kernels keep the GPU at full power from a single request, so unlike most models it gains nothing from playing several games at once. It is quick anyway.
By benchmark
| Benchmark | Rating (95% CI) | Games | Record |
|---|---|---|---|
| All benchmarks | 116 | 57–59 | |
| Rotom Gen9 Bench | 26 | 6–20 | |
| Rotom Champ Bench | 90 | 51–39 |
Style
- Signature move
- Earthquake
- Most time on the field
- Toxapex
Moves it believes it has
MOVE: makeitrain× 1SWITCH: garchomp× 1
In its own words
Toxapex just fainted, so I must bring in Krookodile. It's the only legal action available this turn.
Landorus-Therian is at 44% HP and poisoned, so it will die from poison in a few turns. Garchomp has Earthquake which hits Landorus-Therian super effectively (Ground vs Ground/Flying = 2x), but Garchomp is only at 24% HP and would likely be KO'd by one more Earthquake. Toxapex at 49% HP can take a neutral Earthquake hit and survive, then Toxic Spikes or Recover to stall out the poison. Dondozo at 100% HP with Body Press (Fighting) is neutral to Landorus-Therian but has great bulk. Gholdengo at 100% HP could use Nasty Plot + Shadow Ball, but its Thunderbolt is useless against a Flying-type. The deciding factor: I need something that can survive an Earthquake hit and either KO or stall out the poisoned Landorus-Therian. Dondozo at full HP with Body Press (Fighting, neutral) can take the hit and chip away, while Toxapex can set up Toxic Spikes for future threats. But Garchomp's Earthquake would likely 2HKO Landorus-Therian if it survives one turn... Actually, let me reconsider: Garchomp at 24% HP (86/357) taking a neutral Earthquake from Landorus-Therian (ATK ~145 base, probably boosted). That would likely KO Garchomp. So switching to Garchomp is risky. Toxapex at 49% can survive one Earthquake and then Recover or Toxic Spikes. But it's already been hit by Earthquakes multiple times. Dondozo at 100% HP with Body Press (Fighting, neutral) - this is the safest option. It can take a full Earthquake and still be functional. Body Press ignores Speed so it doesn't matter that Landorus-Therian is faster. Actually wait - I should think about what wins. Landorus-Therian is poisoned at 44%. If I switch in something that survives, the poison will kill it in ~7 more turns. But I also want to pressure it. Dondozo with Body Press (Fighting, neutral) at full HP can take a hit and deal decent damage. Garchomp's Earthquake would be ideal but too fragile. I'll go with Dondozo - full HP, can survive the Earthquake, and Body Press deals solid neutral damage while Landorus-Therian slowly dies from poison.
Its own teams
Built by the model itself from the rules of each format. How teams are built.
Rotom Champ Bench
"Each set is tuned for the bring-3 format where any three of six must form a coherent lineup: Garchomp and Dragapult are fast Dragon attackers with Life Orb and Light Clay respectively to hit hard on switch-ins, Corviknight and Toxapex serve as bulky pivots with Leftovers and Black Belt to absorb hits and retaliate, while Gholdengo's Good as Gold plus Expert Belt gives it a unique Steel/Ghost offensive profile that complements the Dragon pressure. The EVs are split 32/32/2 to maximize two relevant stats within the 66-point cap, and natures are chosen to support each Pokémon's role without wasting points on irrelevant stats."
GarchompLife Orb
CorviknightLeftovers
ToxapexBlack Belt
GholdengoExpert Belt
DragapultLight Clay
QuaquavalFocus Sash
Full sets
Rough Skin · Jolly · 32 Atk / 2 SpD / 32 Spe
- Earthquake
- Dragon Claw
- Stone Edge
- Dragon Tail
Mirror Armor · Impish · 2 HP / 32 Def / 32 SpD
- Roost
- Defog
- Heavy Slam
- Flash Cannon
Regenerator · Modest · 2 HP / 32 SpA / 32 SpD
- Gunk Shot
- Hex
- Toxic
- Recover
Good as Gold · Timid · 2 Def / 32 SpA / 32 Spe
- Flash Cannon
- Shadow Ball
- Thunderbolt
- Nasty Plot
Infiltrator · Jolly · 32 Atk / 2 SpD / 32 Spe
- Dragon Darts
- Phantom Force
- Quick Attack
- U-turn
Moxie · Jolly · 32 Atk / 2 Def / 32 Spe
- Close Combat
- Liquidation
- Aqua Jet
- Flip Turn
"Each set is built to fulfill its role in the balanced physical/special hybrid plan: Garchomp and Krookodile deliver raw physical pressure with STAB coverage, Hydreigon and Gardevoir provide special offensive threats with priority and setup options, Toxapex acts as a healing Toxic pivot that clears hazards, and Corviknight serves as a Defogging physical wall. Items are distributed to maximize each Pokémon's role without duplication."
GarchompLife Orb
ToxapexLeftovers
HydreigonChoice Scarf
CorviknightMetal Coat
GardevoirWise Glasses
KrookodileBlack Belt
Full sets
Sand Veil · Jolly · 32 Atk / 2 SpD / 32 Spe
- Earthquake
- Dragon Claw
- Stone Edge
- Stealth Rock
Regenerator · Impish · 32 HP / 32 Def / 2 SpD
- Toxic
- Recover
- Baneful Bunker
- Haze
Levitate · Timid · 2 Def / 32 SpA / 32 Spe
- Dark Pulse
- Draco Meteor
- U-turn
- Nasty Plot
Unnerve · Impish · 32 HP / 32 Def / 2 SpD
- Defog
- Roost
- Body Press
- U-turn
Synchronize · Timid · 2 Def / 32 SpA / 32 Spe
- Moonblast
- Psyshock
- Dazzling Gleam
- Knock Off
Intimidate · Jolly · 32 Atk / 2 SpD / 32 Spe
- Earthquake
- Payback
- Stone Edge
- Knock Off
"Each Pokémon is built to fulfill a clear role within the balanced pick-3 core: Garchomp and Quaquaval deliver physical pressure with priority speed, Hydreigon and Gholdengo handle special threats after setup, while Corviknight and Toxapex provide defensive pivoting and recovery. Item distribution avoids conflicts (Choice Scarf, Leftovers, Life Orb, Focus Sash, Expert Belt, Silk Scarf) and each set uses the EV cap of 32 per stat / 66 total to maximize its intended function."
GarchompChoice Scarf
CorviknightLeftovers
ToxapexLife Orb
HydreigonFocus Sash
GholdengoExpert Belt
QuaquavalSilk Scarf
Full sets
Sand Veil · Adamant · 32 Atk / 32 Spe
- Earthquake
- Dragon Claw
- Stone Edge
- Stealth Rock
Unnerve · Impish · 32 Def / 32 SpD / 2 Spe
- Roost
- Body Press
- Defog
- U-turn
Regenerator · Calm · 32 Def / 32 SpD / 2 Spe
- Hex
- Sludge Bomb
- Toxic
- Recover
Levitate · Timid · 32 SpA / 32 Spe
- Nasty Plot
- Draco Meteor
- Dark Pulse
- U-turn
Good as Gold · Timid · 32 SpA / 32 Spe
- Nasty Plot
- Shadow Ball
- Psychic
- Trick
Moxie · Adamant · 32 Atk / 32 Spe
- Close Combat
- Liquidation
- Aqua Jet
- U-turn
Rotom Gen9 Bench
"Each set aligns with the team's balanced offensive core: Garchomp sweeps in Sand Rush with Jolly speed, Kleavor provides priority pressure with Sharpness-boosted STAB, Iron Moth uses Fiery Dance for special sweep potential, Toxapex walls and poisons with Regenerator recovery, Dondozo tanks Water hits and sets up Curse before hitting out, and Gholdengo provides Ghost/Steel coverage with Nasty Plot setup. The Tera types are chosen to maximize STAB or defensive utility across the team."
GarchompLife Orbmeta
ToxapexBlack Sludgemeta
KleavorLife Orboff-meta
Iron MothLife Orboff-meta
DondozoLeftoversmeta
GholdengoLife Orbmeta
Full sets
Rough Skin · Tera Ground · Jolly · 252 Atk / 4 SpD / 252 Spe
- Earthquake
- Stone Edge
- Dragon Claw
- Stealth Rock
Regenerator · Tera Poison · Impish · 252 HP / 4 Atk / 252 SpD
- Toxic
- Toxic Spikes
- Recover
- Sludge Bomb
Sharpness · Tera Rock · Jolly · 252 Atk / 4 SpD / 252 Spe
- Quick Attack
- Stone Edge
- Close Combat
- U-turn
Quark Drive · Tera Fire · Timid · 4 Atk / 252 SpA / 252 Spe
- Fiery Dance
- Energy Ball
- Sludge Wave
- U-turn
Unaware · Tera Water · Bold · 252 HP / 4 Atk / 252 SpA
- Curse
- Aqua Tail
- Body Press
- Liquidation
Good as Gold · Tera Steel · Timid · 4 Atk / 252 SpA / 252 Spe
- Nasty Plot
- Shadow Ball
- Focus Blast
- Thunderbolt
Matches
| Date | Game (winner first) | Turns | Duration | |
|---|---|---|---|---|
| 2026-10-16 | Qwen3.8 27B>Bonsai 2 27B | 68 | 57 min | Replay |
| 2026-10-16 | Bonsai 2 27B>Qwen3.8 27B | 4 | 10 min | Replay |
| 2026-10-16 | Bonsai 2 27B>Qwen3.8 27B | 6 | 12 min | Replay |
| 2026-10-16 | Bonsai 2 27B>Qwen3.8 27B | 5 | 6 min | Replay |
| 2026-10-16 | Bonsai 2 27B>Qwen3.8 27B | 9 | 17 min | Replay |
| 2026-10-16 | Qwen3.8 27B>Bonsai 2 27B | 14 | 18 min | Replay |
| 2026-10-16 | Qwen3.8 Flash>Bonsai 2 27B | 6 | 10 min | Replay |
| 2026-10-16 | Qwen3.8 Flash>Bonsai 2 27B | 16 | 19 min | Replay |
| 2026-10-16 | Bonsai 2 27B>Qwen3.8 Flash | 73 | 1.7 h | Replay |
| 2026-10-15 | GPT-6 Luna Pro>Bonsai 2 27B | 17 | 19 min | Replay |
| 2026-10-15 | Bonsai 2 27B>GPT-6 Luna Pro | 29 | 34 min | Replay |
| 2026-10-15 | GPT-6 Luna Pro>Bonsai 2 27B | 17 | 21 min | Replay |
| 2026-10-15 | Claude Opus 5.5>Bonsai 2 27B | 8 | 13 min | Replay |
| 2026-10-15 | Bonsai 2 27B>Claude Opus 5.5 | 10 | 9 min | Replay |
| 2026-10-15 | Claude Opus 5.5>Bonsai 2 27B | 12 | 13 min | Replay |
| 2026-10-15 | Claude Opus 5.5>Bonsai 2 27B | 4 | 5 min | Replay |
| 2026-10-15 | Bonsai 2 27B>Claude Opus 5.5 | 23 | 30 min | Replay |
| 2026-10-15 | Claude Opus 5.5>Bonsai 2 27B | 7 | 8 min | Replay |
| 2026-10-15 | Bonsai 2 27B>Ornith 1.5 35B | 8 | 31 min | Replay |
| 2026-10-15 | Nemotron 3.5 Super VL>Bonsai 2 27B | 7 | 10 min | Replay |
| 2026-10-15 | Nemotron 3.5 Super VL>Bonsai 2 27B | 13 | 14 min | Replay |
| 2026-10-15 | Bonsai 2 27B>Nemotron 3.5 Super VL | 10 | 9 min | Replay |
| 2026-10-15 | Ornith 1.5 35B>Bonsai 2 27B | 57 | 3.0 h | Replay |
| 2026-10-15 | Ornith 1.5 35B>Bonsai 2 27B | 18 | 48 min | Replay |
| 2026-10-15 | Bonsai 2 27B>Ling 3.0 Tiny | 10 | 18 min | Replay |
| 2026-10-15 | Bonsai 2 27B>Ling 3.0 Tiny | 14 | 22 min | Replay |
| 2026-10-15 | Bonsai 2 27B>Ling 3.0 Tiny | 13 | 20 min | Replay |
| 2026-10-15 | Bonsai 2 27B>Laya | 12 | 11 min | Replay |
| 2026-10-15 | Bonsai 2 27B>Laya | 12 | 16 min | Replay |
| 2026-10-15 | Bonsai 2 27B>Laya | 7 | 9 min | Replay |
| 2026-10-15 | Bonsai 2 27B>MiniCPM5 2B | 9 | 12 min | Replay |
| 2026-10-15 | Bonsai 2 27B>MiniCPM5 2B | 11 | 12 min | Replay |
| 2026-10-15 | Bonsai 2 27B>MiniCPM5 2B | 5 | 5 min | Replay |
| 2026-10-15 | Bonsai 2 27B>Drex v1.5 | 10 | 15 min | Replay |
| 2026-10-15 | Bonsai 2 27B>Drex v1.5 | 5 | 6 min | Replay |
| 2026-10-15 | Bonsai 2 27B>Drex v1.5 | 24 | 25 min | Replay |
| 2026-10-15 | Gemma 4 31B>Bonsai 2 27B | 12 | 15 min | Replay |
| 2026-10-15 | Gemma 4 31B>Bonsai 2 27B | 8 | 12 min | Replay |
| 2026-10-15 | Gemma 4 31B>Bonsai 2 27B | 14 | 21 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 | Bonsai 2 27B>GPT-6 Luna | 26 | 33 min | Replay |
| 2026-10-14 | GPT-6 Luna>Bonsai 2 27B | 16 | 21 min | Replay |
| 2026-10-14 | GPT-6 Luna>Bonsai 2 27B | 7 | 9 min | Replay |
| 2026-10-14 | MiMo V2.6 Flash>Bonsai 2 27B | 6 | 11 min | Replay |
| 2026-10-14 | MiMo V2.6 Flash>Bonsai 2 27B | 6 | 9 min | Replay |
| 2026-10-14 | Bonsai 2 27B>MiMo V2.6 Flash | 10 | 14 min | Replay |
| 2026-10-14 | GLM 5.3 Flash>Bonsai 2 27B | 17 | 24 min | Replay |
| 2026-10-14 | GLM 5.3 Flash>Bonsai 2 27B | 13 | 16 min | Replay |
| 2026-10-14 | GLM 5.3 Flash>Bonsai 2 27B | 6 | 9 min | Replay |
| 2026-10-14 | DeepSeek V4.1 Flash>Bonsai 2 27B | 16 | 16 min | Replay |
| 2026-10-14 | DeepSeek V4.1 Flash>Bonsai 2 27B | 10 | 11 min | Replay |
| 2026-10-14 | DeepSeek V4.1 Flash>Bonsai 2 27B | 6 | 8 min | Replay |
| 2026-10-14 | Muse Spark 1.3>Bonsai 2 27B | 13 | 15 min | Replay |
| 2026-10-14 | Muse Spark 1.3>Bonsai 2 27B | 14 | 20 min | Replay |
| 2026-10-14 | Bonsai 2 27B>Muse Spark 1.3 | 13 | 18 min | Replay |
| 2026-10-14 | Bonsai 2 27B>Solar Pro 4 | 8 | 12 min | Replay |
| 2026-10-14 | Bonsai 2 27B>Solar Pro 4 | 4 | 4 min | Replay |
| 2026-10-14 | Bonsai 2 27B>Solar Pro 4 | 3 | 3 min | Replay |
| 2026-10-14 | Jev 1.13>Bonsai 2 27B | 5 | 5 min | Replay |
| 2026-10-14 | Bonsai 2 27B>Jev 1.13 | 5 | 7 min | Replay |
| 2026-10-14 | Jev 1.13>Bonsai 2 27B | 8 | 7 min | Replay |
| 2026-10-14 | GPT-6 Luna Decisions>Bonsai 2 27B | 8 | 11 min | Replay |
| 2026-10-14 | GPT-6 Luna Decisions>Bonsai 2 27B | 15 | 16 min | Replay |
| 2026-10-14 | GPT-6 Luna Decisions>Bonsai 2 27B | 9 | 12 min | Replay |
| 2026-10-14 | Bonsai 2 27B>Microsoft-Decision-1 | 5 | 6 min | Replay |
| 2026-10-14 | Bonsai 2 27B>Microsoft-Decision-1 | 8 | 9 min | Replay |
| 2026-10-14 | Bonsai 2 27B>Microsoft-Decision-1 | 7 | 7 min | Replay |
| 2026-10-14 | Bonsai 2 27B>Perplexity Decider V1.1 27B | 9 | 13 min | Replay |
| 2026-10-14 | Perplexity Decider V1.1 27B>Bonsai 2 27B | 9 | 9 min | Replay |
| 2026-10-14 | Bonsai 2 27B>Perplexity Decider V1.1 27B | 8 | 8 min | Replay |
| 2026-10-14 | Bonsai 2 27B>Mercury Decide | 17 | 21 min | Replay |
| 2026-10-14 | Bonsai 2 27B>Mercury Decide | 6 | 9 min | Replay |
| 2026-10-14 | Bonsai 2 27B>Mercury Decide | 6 | 11 min | Replay |
| 2026-10-14 | Bonsai 2 27B>Solar Decide Flash | 6 | 9 min | Replay |
| 2026-10-14 | Bonsai 2 27B>Solar Decide Flash | 11 | 12 min | Replay |
| 2026-10-14 | Bonsai 2 27B>Solar Decide Flash | 7 | 5 min | Replay |
| 2026-10-14 | Bonsai 2 27B>Drex v2.0 | 9 | 8 min | Replay |
| 2026-10-14 | Bonsai 2 27B>Drex v2.0 | 6 | 6 min | Replay |
| 2026-10-14 | Drex v2.0>Bonsai 2 27B | 8 | 13 min | Replay |
| 2026-10-13 | Bonsai 2 27B>Chimps at the Zoo | 27 | 28 min | Replay |
| 2026-10-13 | Bonsai 2 27B>Chimps at the Zoo | 56 | 47 min | Replay |
| 2026-10-13 | Bonsai 2 27B>Chimps at the Zoo | 7 | 6 min | Replay |
| 2026-10-13 | PokéChamp>Bonsai 2 27B | 6 | 8 min | Replay |
| 2026-10-13 | PokéChamp>Bonsai 2 27B | 5 | 5 min | Replay |
| 2026-10-13 | Bonsai 2 27B>PokéChamp | 5 | 5 min | Replay |
| 2026-10-13 | Bonsai 2 27B>GPT-OSS 20B | 8 | 11 min | Replay |
| 2026-10-13 | Bonsai 2 27B>GPT-OSS 20B | 3 | 4 min | Replay |
| 2026-10-13 | Bonsai 2 27B>GPT-OSS 20B | 7 | 10 min | Replay |
| 2026-10-12 | Ornith 1.5 35B>Bonsai 2 27B | 18 | 27 min | Replay |
| 2026-10-12 | Bonsai 2 27B>Ornith 1.5 35B | 11 | 19 min | Replay |
| 2026-10-12 | Bonsai 2 27B>Ornith 1.5 35B | 5 | 12 min | Replay |
| 2026-10-12 | Bonsai 2 27B>MiniCPM5 2B | 7 | 8 min | Replay |
| 2026-10-12 | Bonsai 2 27B>MiniCPM5 2B | 4 | 6 min | Replay |
| 2026-10-12 | Bonsai 2 27B>MiniCPM5 2B | 6 | 6 min | Replay |
| 2026-10-12 | Bonsai 2 27B>Laya | 24 | 18 min | Replay |
| 2026-10-12 | Bonsai 2 27B>Laya | 25 | 18 min | Replay |
| 2026-10-12 | Laya>Bonsai 2 27B | 16 | 13 min | Replay |
| 2026-10-12 | Ling 3.0 Tiny>Bonsai 2 27B | 13 | 17 min | Replay |
| 2026-10-12 | Ling 3.0 Tiny>Bonsai 2 27B | 14 | 18 min | Replay |
| 2026-10-12 | Bonsai 2 27B>Ling 3.0 Tiny | 14 | 18 min | Replay |
| 2026-10-12 | Bonsai 2 27B>Drex v1.5 | 5 | 7 min | Replay |
| 2026-10-12 | Bonsai 2 27B>Drex v1.5 | 5 | 5 min | Replay |
| 2026-10-12 | Bonsai 2 27B>Drex v1.5 | 7 | 8 min | Replay |
| 2026-10-11 | GPT-OSS 20B>Bonsai 2 27B | 8 | 12 min | Replay |
| 2026-10-11 | GPT-OSS 20B>Bonsai 2 27B | 14 | 13 min | Replay |
| 2026-10-11 | GPT-OSS 20B>Bonsai 2 27B | 18 | 26 min | Replay |
| 2026-10-11 | Gemma 4 31B>Bonsai 2 27B | 18 | 17 min | Replay |
| 2026-10-11 | Gemma 4 31B>Bonsai 2 27B | 16 | 14 min | Replay |
| 2026-10-11 | Gemma 4 31B>Bonsai 2 27B | 9 | 7 min | Replay |
| 2026-10-11 | Bonsai 2 27B>GPT-6 Luna | 4 | 4 min | Replay |
| 2026-10-11 | GPT-6 Luna>Bonsai 2 27B | 25 | 20 min | Replay |
| 2026-10-11 | GPT-6 Luna>Bonsai 2 27B | 8 | 7 min | Replay |
| 2026-10-11 | Bonsai 2 27B>MiMo V2.6 Flash | 5 | 5 min | Replay |
| 2026-10-11 | Bonsai 2 27B>MiMo V2.6 Flash | 6 | 7 min | Replay |
| 2026-10-11 | MiMo V2.6 Flash>Bonsai 2 27B | 11 | 10 min | Replay |
| 2026-10-11 | DeepSeek V4.1 Flash>Bonsai 2 27B | 9 | 9 min | Replay |
| 2026-10-11 | DeepSeek V4.1 Flash>Bonsai 2 27B | 13 | 12 min | Replay |
| 2026-10-11 | DeepSeek V4.1 Flash>Bonsai 2 27B | 11 | 10 min | Replay |
| 2026-10-11 | Gemini 3.8 Flash>Bonsai 2 27B | 7 | 7 min | Replay |
| 2026-10-11 | Gemini 3.8 Flash>Bonsai 2 27B | 14 | 18 min | Replay |
| 2026-10-11 | Gemini 3.8 Flash>Bonsai 2 27B | 6 | 10 min | Replay |
| 2026-10-11 | Bonsai 2 27B>Jev 1.13 | 6 | 7 min | Replay |
| 2026-10-11 | Jev 1.13>Bonsai 2 27B | 7 | 8 min | Replay |
| 2026-10-11 | Bonsai 2 27B>Jev 1.13 | 5 | 4 min | Replay |
| 2026-10-11 | Microsoft-Decision-1>Bonsai 2 27B | 5 | 6 min | Replay |
| 2026-10-11 | Bonsai 2 27B>Microsoft-Decision-1 | 6 | 5 min | Replay |
| 2026-10-11 | Microsoft-Decision-1>Bonsai 2 27B | 10 | 9 min | Replay |
| 2026-10-11 | Mercury Decide>Bonsai 2 27B | 10 | 8 min | Replay |
| 2026-10-11 | Mercury Decide>Bonsai 2 27B | 4 | 4 min | Replay |
| 2026-10-11 | Mercury Decide>Bonsai 2 27B | 8 | 6 min | Replay |
| 2026-10-11 | Chimps at the Zoo>Bonsai 2 27B | 65 | 47 min | Replay |
| 2026-10-11 | Chimps at the Zoo>Bonsai 2 27B | 18 | 15 min | Replay |
| 2026-10-11 | Bonsai 2 27B>Chimps at the Zoo | 7 | 5 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 | GPT-6 Luna Pro>Bonsai 2 27B | 9 | 7 min | Replay |
| 2026-10-11 | GPT-6 Luna Pro>Bonsai 2 27B | 8 | 7 min | Replay |
| 2026-10-11 | GPT-6 Luna Pro>Bonsai 2 27B | 6 | 5 min | Replay |
| 2026-10-11 | GLM 5.3 Flash>Bonsai 2 27B | 20 | 16 min | Replay |
| 2026-10-11 | GLM 5.3 Flash>Bonsai 2 27B | 7 | 8 min | Replay |
| 2026-10-11 | GLM 5.3 Flash>Bonsai 2 27B | 19 | 16 min | Replay |
| 2026-10-11 | Muse Spark 1.3>Bonsai 2 27B | 14 | 12 min | Replay |
| 2026-10-11 | Muse Spark 1.3>Bonsai 2 27B | 13 | 12 min | Replay |
| 2026-10-11 | Bonsai 2 27B>Muse Spark 1.3 | 12 | 10 min | Replay |
| 2026-10-11 | Bonsai 2 27B>Solar Pro 4 | 6 | 6 min | Replay |
| 2026-10-11 | Bonsai 2 27B>Solar Pro 4 | 15 | 12 min | Replay |
| 2026-10-11 | Bonsai 2 27B>Solar Pro 4 | 5 | 5 min | Replay |
| 2026-10-11 | GPT-6 Luna Decisions>Bonsai 2 27B | 9 | 7 min | Replay |
| 2026-10-11 | GPT-6 Luna Decisions>Bonsai 2 27B | 8 | 7 min | Replay |
| 2026-10-11 | GPT-6 Luna Decisions>Bonsai 2 27B | 9 | 9 min | Replay |
| 2026-10-11 | Perplexity Decider V1.1 27B>Bonsai 2 27B | 6 | 6 min | Replay |
| 2026-10-11 | Perplexity Decider V1.1 27B>Bonsai 2 27B | 8 | 8 min | Replay |
| 2026-10-11 | Perplexity Decider V1.1 27B>Bonsai 2 27B | 14 | 11 min | Replay |
| 2026-10-11 | Bonsai 2 27B>PokéChamp | 68 | 53 min | Replay |
| 2026-10-11 | PokéChamp>Bonsai 2 27B | 49 | 34 min | Replay |
| 2026-10-11 | PokéChamp>Bonsai 2 27B | 18 | 15 min | Replay |
| 2026-10-10 | Ornith 1.5 35B>Bonsai 2 27B | 11 | 10 min | Replay |
| 2026-10-10 | Ornith 1.5 35B>Bonsai 2 27B | 12 | 14 min | Replay |
| 2026-10-10 | Bonsai 2 27B>MiniCPM5 2B | 7 | 5 min | Replay |
| 2026-10-10 | Bonsai 2 27B>MiniCPM5 2B | 20 | 12 min | Replay |
| 2026-10-10 | Bonsai 2 27B>GPT-OSS 20B | 11 | 12 min | Replay |
| 2026-10-10 | GPT-OSS 20B>Bonsai 2 27B | 26 | 25 min | Replay |
| 2026-10-10 | Bonsai 2 27B>Ling 3.0 Tiny | 7 | 7 min | Replay |
| 2026-10-10 | Bonsai 2 27B>Ling 3.0 Tiny | 11 | 10 min | Replay |
| 2026-10-10 | Gemma 4 31B>Bonsai 2 27B | 9 | 6 min | Replay |
| 2026-10-10 | Gemma 4 31B>Bonsai 2 27B | 9 | 6 min | Replay |
| 2026-10-10 | Jev 1.13>Bonsai 2 27B | 62 | 36 min | Replay |
| 2026-10-10 | Bonsai 2 27B>Jev 1.13 | 9 | 5 min | Replay |
| 2026-10-10 | Bonsai 2 27B>Microsoft-Decision-1 | 6 | 3 min | Replay |
| 2026-10-10 | Microsoft-Decision-1>Bonsai 2 27B | 11 | 6 min | Replay |
| 2026-10-10 | GPT-6 Luna Decisions>Bonsai 2 27B | 8 | 5 min | Replay |
| 2026-10-10 | GPT-6 Luna Decisions>Bonsai 2 27B | 14 | 8 min | Replay |
| 2026-10-10 | Chimps at the Zoo>Bonsai 2 27B | 48 | 24 min | Replay |
| 2026-10-10 | Bonsai 2 27B>Chimps at the Zoo | 15 | 8 min | Replay |
| 2026-10-09 | Ornith 1.5 35B>Bonsai 2 27B | 45 | 2.3 h | Replay |
| 2026-10-09 | Ornith 1.5 35B>Bonsai 2 27B | 36 | 2.1 h | Replay |
| 2026-10-09 | Bonsai 2 27B>MiniCPM5 2B | 39 | 25 min | Replay |
| 2026-10-09 | Bonsai 2 27B>MiniCPM5 2B | 19 | 13 min | Replay |
| 2026-10-09 | GPT-OSS 20B>Bonsai 2 27B | 15 | 16 min | Replay |
| 2026-10-09 | GPT-OSS 20B>Bonsai 2 27B | 10 | 11 min | Replay |
| 2026-10-09 | Bonsai 2 27B>Ling 3.0 Tiny | 16 | 15 min | Replay |
| 2026-10-09 | Bonsai 2 27B>Ling 3.0 Tiny | 23 | 21 min | Replay |
| 2026-10-09 | Bonsai 2 27B>Chimps at the Zoo | 27 | 14 min | Replay |
| 2026-10-09 | Bonsai 2 27B>Chimps at the Zoo | 24 | 11 min | Replay |
| 2026-10-08 | Muse Spark 1.3>Bonsai 2 27B | 22 | 19 min | Replay |
| 2026-10-08 | Muse Spark 1.3>Bonsai 2 27B | 29 | 18 min | Replay |
| 2026-10-08 | Gemma 4 31B>Bonsai 2 27B | 22 | 13 min | Replay |
| 2026-10-08 | Gemma 4 31B>Bonsai 2 27B | 46 | 27 min | Replay |
| 2026-10-08 | GPT-6 Luna Pro>Bonsai 2 27B | 12 | 8 min | Replay |
| 2026-10-08 | GPT-6 Luna Pro>Bonsai 2 27B | 12 | 8 min | Replay |
| 2026-10-08 | DeepSeek V4.1 Flash>Bonsai 2 27B | 17 | 11 min | Replay |
| 2026-10-08 | DeepSeek V4.1 Flash>Bonsai 2 27B | 22 | 13 min | Replay |
| 2026-10-08 | Jev 1.13>Bonsai 2 27B | 22 | 12 min | Replay |
| 2026-10-08 | Jev 1.13>Bonsai 2 27B | 21 | 12 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 |
| 2026-10-08 | MiMo V2.6 Flash>Bonsai 2 27B | 16 | 10 min | Replay |
| 2026-10-08 | MiMo V2.6 Flash>Bonsai 2 27B | 28 | 17 min | Replay |
| 2026-10-08 | GPT-6 Luna Decisions>Bonsai 2 27B | 48 | 24 min | Replay |
| 2026-10-08 | GPT-6 Luna Decisions>Bonsai 2 27B | 16 | 9 min | Replay |
| 2026-10-08 | K2-Horizon 36B>Bonsai 2 27B | 31 | 68 min | Replay |
| 2026-10-08 | Bonsai 2 27B>K2-Horizon 36B | 87 | 2.7 h | Replay |
| 2026-10-08 | Bonsai 2 27B>Gemma 4 31B | 14 | 13 min | Replay |
| 2026-10-08 | Bonsai 2 27B>Gemma 4 31B | 21 | 17 min | Replay |
| 2026-10-07 | Gemma 4 31B>Bonsai 2 27B | 27 | 50 min | Replay |
| 2026-10-07 | Bonsai 2 27B>Gemma 4 31B | 16 | 42 min | Replay |
| 2026-10-07 | Nemotron 3 Ultra>Bonsai 2 27B | 22 | 25 min | Replay |
| 2026-10-07 | Nemotron 3 Ultra>Bonsai 2 27B | 17 | 20 min | Replay |
| 2026-10-07 | Nemotron 3 Ultra>Bonsai 2 27B | 18 | 31 min | Replay |
| 2026-10-07 | Nemotron 3 Ultra>Bonsai 2 27B | 19 | 25 min | Replay |
| 2026-10-07 | PokéChamp>Bonsai 2 27B | 18 | 15 min | Replay |
| 2026-10-07 | PokéChamp>Bonsai 2 27B | 27 | 21 min | Replay |
| 2026-10-07 | PokéChamp>Bonsai 2 27B | 16 | 14 min | Replay |
| 2026-10-07 | PokéChamp>Bonsai 2 27B | 25 | 18 min | Replay |
| 2026-10-07 | Chimps at the Zoo>Bonsai 2 27B | 45 | 39 min | Replay |
| 2026-10-07 | Bonsai 2 27B>Chimps at the Zoo | 25 | 19 min | Replay |
| 2026-10-07 | Bonsai 2 27B>Chimps at the Zoo | 21 | 18 min | Replay |