Benchmark menu

Per-game leaderboard

GB2-08: Tumbleweed

This page shows the per-game leaderboard for GB2-08: Tumbleweed in the intensive filter. Entrants are ranked by their relative per-game score within this game.

GB2-08: Tumbleweed

Tumbleweed

Tumbleweed is a hex-grid territory game where players grow visible stacks and final control is determined by line-of-sight strength.

Scores here compare generated programs on DuelLab's encoded rules for Tumbleweed; they are not a broad measure of human play strength.

Entrants

Every admitted unique code identity for GB2-08: Tumbleweed. Elo and W/L/D use the public historical sequential-Elo result universe. Confidence and coverage use only evidence compatible with the active adaptive policy and can therefore be blank or lower. Capped draws are rated; unilateral model faults are listed separately.

Showing 40 entrants.
EntrantModelStatusScoreEloConfidenceW / L / DRated / attemptedOpponentsCapped drawsFaults / pluginsGeneration
E-12891afa894223fdClaude Fable 5Under-covered91.315966 / 0 / 06 / 6300 / 1Repaired · 2026-07-02
E-877eec51affacb3aClaude Opus 4.5Pending0 / 0 / 00 / 0000 / 1First pass · —
E-22dc6fe5ae5fb8b1Claude Opus 4.8Under-covered46.514644 / 6 / 010 / 10500 / 1First pass · 2026-07-03
E-a40851c4f03704e5Claude Opus 5Under-covered100.015858 / 2 / 010 / 10500 / 1First pass · 2026-07-25
E-f5914ca845403384Claude Opus 5Under-covered26.614501 / 5 / 06 / 6300 / 1First pass · 2026-07-25
E-b5805acb90227d50Claude Sonnet 5Under-covered24.314720 / 2 / 24 / 4220 / 1First pass · 2026-07-03
E-a7310645c3b96434DeepSeek V4 FlashUnder-covered27.115312 / 0 / 02 / 2100 / 1Repaired · 2026-07-02
E-3a5b5c4507a989d3DeepSeek V4 ProUnder-covered34.414670 / 2 / 46 / 6340 / 1Repaired · 2026-07-02
E-b335c9f92035f80bGemini 3.1 Flash LitePending0 / 0 / 00 / 0000 / 1Repaired · 2026-07-02
E-fa332e578ae97122Gemini 3.5 FlashPending0 / 0 / 00 / 0000 / 1Repaired · 2026-07-02
E-0d09401e4a31ea61Gemini 3.5 Flash LitePending0 / 0 / 00 / 0000 / 1Repaired · 2026-07-24
E-96566b3cf3a15c23Gemini 3.5 Flash LitePending0 / 0 / 00 / 0000 / 1Repaired · 2026-07-24
E-37e04d4125f1d7faGemini 3.6 FlashPending0 / 0 / 00 / 0000 / 1Repaired · 2026-07-24
E-ee7ca879a02fdaf7Gemini 3.6 FlashPending0 / 0 / 00 / 0000 / 1Repaired · 2026-07-24
E-ebca8ea756b4a4adGPT 5Pending0 / 0 / 00 / 0000 / 1First pass · 2026-07-02
E-ddc1f3e68bf1e74aGPT-5.4Under-covered55.915162 / 1 / 36 / 6330 / 1First pass · 2026-07-02
E-1e5d07fc67fd8710GPT-5.4 MiniUnder-covered18.814600 / 3 / 14 / 4210 / 1Repaired · 2026-07-02
E-b63acb1096519102GPT-5.4 MiniUnder-covered50.915042 / 2 / 26 / 6320 / 1First pass · 2026-07-02
E-98e55f26cfe52488GPT-5.4 NanoUnder-covered38.515042 / 2 / 04 / 4200 / 1First pass · 2026-07-02
E-ba371b627387f273GPT-5.4 NanoUnder-covered36.014710 / 2 / 46 / 6340 / 1First pass · 2026-07-02
E-bb4437fab8180bfcGPT-5.4 NanoUnder-covered12.714980 / 0 / 22 / 2120 / 1Repaired · 2026-07-09
E-3e859a6b27767128GPT-5.5Under-covered62.415004 / 4 / 210 / 10520 / 1First pass · 2026-07-02
E-0fb7de4e8156a229GPT-5.6 LunaUnder-covered41.415112 / 1 / 14 / 4210 / 1First pass · 2026-07-10
E-3ae62f195160add3GPT-5.6 SolUnder-covered34.414670 / 2 / 46 / 6340 / 1First pass · 2026-07-10
E-b061663dc342c859GPT-5.6 TerraUnder-covered54.715133 / 2 / 16 / 6310 / 1Repaired · 2026-07-10
E-134262cb96978830Kimi K3Pending0 / 0 / 00 / 0000 / 1Repaired · 2026-07-18
E-b06cbc77b01de3b3Kimi K3Pending0 / 0 / 00 / 0000 / 1Repaired · 2026-07-17
E-2e3c01d0103fc439Nemotron 3 Ultra 550B A55BPending0 / 0 / 00 / 0000 / 1Repaired · 2026-07-11
E-8c24e8bcbe9b1228Nemotron 3 Ultra 550B A55BPending0 / 0 / 00 / 0000 / 1First pass · 2026-07-02
E-1b6fc7dfefb8cea4O3Pending0 / 0 / 00 / 0000 / 1First pass · 2026-07-03
E-24a75273941e6ea3GPT-OSS 120BPending0 / 0 / 00 / 0000 / 1Repaired · 2026-07-02
E-8b265019ada47f24Step 3.7 FlashPending0 / 0 / 00 / 0000 / 1Repaired · 2026-07-02
E-81a5e5ef15f371dcHy3 PreviewPending0 / 0 / 00 / 0000 / 1First pass · 2026-07-02
E-d21921560d198b28InklingPending0 / 0 / 00 / 0000 / 1Repaired · 2026-07-24
E-1c7222840add0cf9Grok 4.5Pending0 / 0 / 00 / 0000 / 1First pass · 2026-07-17
E-60939cc4ea338b18Grok 4.5Pending0 / 0 / 00 / 0000 / 1First pass · 2026-07-17
E-707dd709e358a173Grok 4.5Pending0 / 0 / 00 / 0000 / 1First pass · 2026-07-24
E-907d60010bf80864GLM-5.2Under-covered59.015234 / 2 / 06 / 6300 / 1Repaired · 2026-07-11
E-9e8f3e43bfd2810eGLM-5.2Under-covered13.515000 / 0 / 22 / 2120 / 1Repaired · 2026-07-02
E-bc28f817090c9f60GLM-5.2Under-covered0.014690 / 2 / 02 / 2100 / 1Repaired · 2026-07-02

GB2-08: Tumbleweed leaderboard

Entrants are ranked by relative per-game score (0–100). Raw rating is shown as an advanced per-game metric, alongside match record (wins/losses/draws) and a per-game uncertainty index (0–100, fixed scale from rating uncertainty).

Reasoning level: Intensive Game: GB2-08: Tumbleweed

Scroll sideways to see every column.

GB2-08: Tumbleweed - Intensive filter
Rank Model Score Contributing programs Raw Elo W / L / D Uncertainty
1Claude Opus 5100.011584.68/2/0100.0
2Claude Fable 591.311595.66/0/0100.0
3GPT-5.562.411499.84/4/2100.0
4GLM-5.259.011522.84/2/0100.0
5GPT-5.455.911515.62/1/3100.0
6GPT-5.6 Terra54.711513.03/2/1100.0
7GPT-5.4 Mini50.911504.42/2/2100.0
8Claude Opus 4.846.511464.04/6/0100.0
9GPT-5.6 Luna41.411510.82/1/1100.0
10GPT-5.4 Nano38.511504.12/2/0100.0
11GPT-5.4 Nano36.011470.90/2/4100.0
12GPT-5.6 Sol34.411467.30/2/4100.0
13DeepSeek V4 Pro34.411467.30/2/4100.0
14DeepSeek V4 Flash27.111530.52/0/0100.0
15Claude Opus 526.611449.71/5/0100.0
16Claude Sonnet 524.311472.10/2/2100.0
17GPT-5.4 Mini18.811459.90/3/1100.0
18GLM-5.213.511500.00/0/2100.0
19GPT-5.4 Nano12.711498.10/0/2100.0
20GLM-5.20.011469.50/2/0100.0