Name: DuelLab GameBench 2 public release gb2-20260726-11fb0891c89b
Creator: DuelLab
License: https://creativecommons.org/licenses/by/4.0/

Game profile

International Draughts

International Draughts is a 10x10 capture game with mandatory maximum captures, backward captures by men, flying kings, promotion, and automatic draw rules.

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

Entrants

Every admitted unique code identity for GB2-06: International Draughts. 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.

Search model Status Sort Showing 35 entrants.

Entrant	Model	Status	Score	Elo	Confidence	W / L / D	Rated / attempted	Opponents	Faults / plugins	Generation
E-499fbc92ee0778fb	Claude Fable 5	Under-covered	55.7	1490	—	3 / 4 / 3	10 / 10	5	0 / 1	Repaired · 2026-07-02
E-df9bde92610963b7	Claude Opus 4.5	Under-covered	59.4	1529	—	3 / 1 / 2	6 / 6	3	0 / 1	First pass · —
E-e804041031295d93	Claude Opus 4.8	Under-covered	75.7	1538	—	6 / 4 / 0	10 / 10	5	0 / 1	First pass · 2026-07-03
E-51f3682dc3b76107	Claude Sonnet 5	Under-covered	45.0	1495	—	3 / 3 / 0	6 / 6	3	0 / 1	First pass · 2026-07-03
E-5f5fd61f4544b8d7	DeepSeek V4 Flash	Under-covered	23.1	1443	—	1 / 5 / 0	6 / 6	3	0 / 1	First pass · 2026-07-02
E-f527097ad30176f4	DeepSeek V4 Flash	Under-covered	23.8	1472	—	1 / 3 / 0	4 / 4	2	0 / 1	First pass · 2026-07-02
E-c9778645f1bbd12c	DeepSeek V4 Pro	Under-covered	25.5	1529	—	2 / 0 / 0	2 / 2	1	0 / 1	First pass · 2026-07-02
E-6238c7d8dc9e77d9	Gemini 3.1 Flash Lite	Pending	—	—	—	0 / 0 / 0	0 / 0	0	0 / 1	Repaired · 2026-07-02
E-5dcb27eaa0273049	Gemini 3.5 Flash	Pending	—	—	—	0 / 0 / 0	0 / 0	0	0 / 1	Repaired · 2026-07-02
E-48cc2611d5aa8816	Gemini 3.5 Flash Lite	Pending	—	—	—	0 / 0 / 0	0 / 0	0	0 / 1	Repaired · 2026-07-24
E-9c3a169358692b43	Gemini 3.5 Flash Lite	Pending	—	—	—	0 / 0 / 0	0 / 0	0	0 / 1	Repaired · 2026-07-24
E-280a7de63c992141	Gemini 3.6 Flash	Pending	—	—	—	0 / 0 / 0	0 / 0	0	0 / 1	Repaired · 2026-07-24
E-905531e52a8460f5	Gemini 3.6 Flash	Pending	—	—	—	0 / 0 / 0	0 / 0	0	0 / 1	Repaired · 2026-07-24
E-1b082700b3692175	GPT 5	Pending	—	—	—	0 / 0 / 0	0 / 0	0	0 / 1	Repaired · 2026-07-02
E-6e5bbab022d4d9fa	GPT-5.4	Under-covered	100.0	1596	—	8 / 1 / 1	10 / 10	5	0 / 1	Repaired · 2026-07-02
E-0b7e07d12feb8fb5	GPT-5.4 Mini	Under-covered	44.8	1454	—	4 / 7 / 1	12 / 12	6	0 / 1	First pass · 2026-07-02
E-eca073d7ce610515	GPT-5.4 Mini	Under-covered	0.0	1468	—	0 / 2 / 0	2 / 2	1	0 / 1	First pass · 2026-07-02
E-f9bb09fb2842dd1f	GPT-5.4 Nano	Under-covered	67.9	1519	—	6 / 4 / 0	10 / 10	5	0 / 1	First pass · 2026-07-02
E-4175a77ccf4c269b	GPT-5.5	Under-covered	14.8	1503	—	1 / 1 / 0	2 / 2	1	0 / 1	First pass · 2026-07-02
E-9eafeacabdedfdba	GPT-5.6 Luna	Under-covered	23.5	1471	—	0 / 2 / 2	4 / 4	2	0 / 1	First pass · 2026-07-10
E-eb315c759774ef38	GPT-5.6 Sol	Under-covered	58.3	1509	—	4 / 4 / 0	8 / 8	4	0 / 1	First pass · 2026-07-10
E-e6571a10c1120fab	GPT-5.6 Terra	Under-covered	32.5	1465	—	2 / 4 / 0	6 / 6	3	0 / 1	First pass · 2026-07-10
E-6c35f5ff426e7ada	Mistral Medium 3.5	Pending	—	—	—	0 / 0 / 0	0 / 0	0	0 / 1	Repaired · 2026-07-02
E-026a38fa3b1622ee	Kimi K3	Pending	—	—	—	0 / 0 / 0	0 / 0	0	0 / 1	Repaired · 2026-07-17
E-3f2124a8621f4c67	Kimi K3	Pending	—	—	—	0 / 0 / 0	0 / 0	0	0 / 1	Repaired · 2026-07-17
E-ba2fb1c121873708	Nemotron 3 Ultra 550B A55B	Pending	—	—	—	0 / 0 / 0	0 / 0	0	0 / 1	Repaired · 2026-07-11
E-4162fe183e6383e1	O3	Pending	—	—	—	0 / 0 / 0	0 / 0	0	0 / 1	First pass · 2026-07-03
E-a97b527d9b41a80c	GPT-OSS 120B	Pending	—	—	—	0 / 0 / 0	0 / 0	0	0 / 1	Repaired · 2026-07-02
E-2d684425ca56be18	Step 3.7 Flash	Pending	—	—	—	0 / 0 / 0	0 / 0	0	0 / 1	Repaired · 2026-07-02
E-3627e3dbf7a48738	Hy3 Preview	Pending	—	—	—	0 / 0 / 0	0 / 0	0	0 / 1	First pass · 2026-07-02
E-56e54327930d2f64	Inkling	Pending	—	—	—	0 / 0 / 0	0 / 0	0	0 / 1	Repaired · 2026-07-24
E-5a1e23bce371a184	Grok 4.5	Under-covered	6.9	1484	—	0 / 1 / 1	2 / 2	1	0 / 1	First pass · 2026-07-24
E-5bedcf6c046c3b54	Grok 4.5	Under-covered	7.5	1485	—	0 / 1 / 1	2 / 2	1	0 / 1	First pass · 2026-07-17
E-cc9d4b5c56aea8b6	Grok 4.5	Under-covered	14.1	1501	—	1 / 1 / 0	2 / 2	1	0 / 1	Repaired · 2026-07-17
E-f94d63d03c820dac	GLM-5.2	Under-covered	74.9	1549	—	5 / 2 / 1	8 / 8	4	0 / 1	Repaired · 2026-07-11

Leaderboard

GB2-06: International Draughts 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: GB2-06: International Draughts

Scroll sideways to see every column.

GB2-06: International Draughts - Intensive filter
Rank	Model	Score	Contributing programs	Raw Elo	W / L / D	Uncertainty
1	GPT-5.4	100.0	1	1595.6	8/1/1	100.0
2	Claude Opus 4.8	75.7	1	1537.7	6/4/0	100.0
3	GLM-5.2	74.9	1	1548.5	5/2/1	100.0
4	GPT-5.4 Nano	67.9	1	1519.1	6/4/0	100.0
5	Claude Opus 4.5	59.4	1	1529.4	3/1/2	100.0
6	GPT-5.6 Sol	58.3	1	1508.8	4/4/0	100.0
7	Claude Fable 5	55.7	1	1490.1	3/4/3	100.0
8	Claude Sonnet 5	45.0	1	1495.0	3/3/0	100.0
9	GPT-5.4 Mini	44.8	1	1454.3	4/7/1	94.9
10	GPT-5.6 Terra	32.5	1	1465.3	2/4/0	100.0
11	DeepSeek V4 Pro	25.5	1	1528.5	2/0/0	100.0
12	DeepSeek V4 Flash	23.8	1	1472.4	1/3/0	100.0
13	GPT-5.6 Luna	23.5	1	1471.4	0/2/2	100.0
14	DeepSeek V4 Flash	23.1	1	1442.9	1/5/0	100.0
15	GPT-5.5	14.8	1	1502.9	1/1/0	100.0
16	Grok 4.5	14.1	1	1501.2	1/1/0	100.0
17	Grok 4.5	7.5	1	1485.4	0/1/1	100.0
18	Grok 4.5	6.9	1	1484.0	0/1/1	100.0
19	GPT-5.4 Mini	0.0	1	1467.6	0/2/0	100.0