Name: DuelLab GameBench 2 public release gb2-20260807-76d592450aec
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 player programs using DuelLab's encoded rules for International Draughts; they are not a broad measure of human play strength.

By model and setting

GB2-06: International Draughts by model and setting

Each model and reasoning setting appears once. If a model produced more than one accepted player program, DuelLab averages them before ranking. Raw rating, W / D / L, and uncertainty combine those contributing programs.

Reasoning level: Reasoning Variants Game: GB2-06: International Draughts

GB2-06: International Draughts - Reasoning Variants
Rank	Model	Reasoning	Score	Raw Elo	W / D / L	Uncertainty
1	GPT-5.4	XHigh	100.0	1935.9	65 / 10 / 7	11.1
2	Claude Opus 5	None	99.2	1924.1	84 / 11 / 5	6.0
3	GPT-5.4	Medium	95.4	1892.9	68 / 9 / 5	11.1
4	GPT-5.5	XHigh	94.1	1880.1	62 / 4 / 16	11.1
5	Claude Fable 5	XHigh	93.8	1877.9	63 / 9 / 10	11.1
6	Gemini 3.6 Flash	Medium	91.7	1862.9	111 / 10 / 11	17.3
7	Gemini 3.5 Flash	Medium	90.3	1843.4	63 / 11 / 12	9.9
8	Claude Opus 4.8	XHigh	85.7	1802.1	62 / 2 / 16	11.8
9	GPT-5.6 Sol	Medium	85.1	1793.0	64 / 12 / 16	8.1
10	GPT-5.6 Sol	XHigh	84.2	1786.9	58 / 3 / 23	10.5
11	Claude Fable 5	Medium	84.0	1783.3	65 / 5 / 22	8.1
12	Claude Opus 4.8	Medium	83.1	1774.7	67 / 1 / 22	8.7
13	GPT-5.6 Luna	XHigh	81.1	1757.9	52 / 10 / 22	10.5
14	GPT-5.6 Terra	XHigh	79.0	1736.3	56 / 0 / 34	8.7
15	Gemini 3.5 Flash	High	77.6	1743.6	60 / 5 / 17	33.4
16	Gemini 3.6 Flash	High	74.5	1721.3	103 / 8 / 25	42.5
17	Qwen3.7 Plus	Enabled	74.2	1706.4	64 / 5 / 31	27.8
18	GPT-5.4	None	72.5	1677.2	52 / 8 / 22	11.1
19	GPT-5.6 Luna	Medium	70.7	1655.1	64 / 8 / 34	4.6
20	GLM-5.2	Medium	69.7	1655.2	35 / 8 / 25	16.4
21	MiMo-V2.5-Pro	Enabled	69.2	1656.4	63 / 2 / 45	23.5
22	DeepSeek V4 Pro	None	68.9	1642.2	54 / 8 / 24	9.9
23	GPT 5	High	68.2	1653.2	49 / 8 / 31	30.8
24	GPT-OSS 120B	High	66.6	1639.4	48 / 6 / 30	33.5
25	Nemotron 3 Ultra 550B A55B	Medium	66.1	1613.9	51 / 8 / 37	7.0
26	GPT-5.4 Nano	Medium	65.7	1608.7	118 / 6 / 86	4.8
27	O3	Medium	65.5	1607.6	50 / 10 / 42	5.5
28	GLM-5.2	None	64.3	1603.6	66 / 16 / 62	14.8
29	GPT 5	Medium	63.5	1589.1	53 / 7 / 40	6.0
30	MiMo-V2.5	High	62.6	1588.9	34 / 6 / 28	16.4
31	Claude Opus 4.8	None	62.6	1583.1	50 / 9 / 29	9.2
32	GPT-5.4 Mini	Medium	62.1	1574.1	52 / 12 / 42	4.6
33	Step 3.7 Flash	Low	61.2	1592.8	47 / 3 / 26	37.6
34	Qwen3.7 Max	Enabled	61.2	1583.3	56 / 11 / 41	26.0
35	Gemini 3.5 Flash Lite	Minimal	60.7	1596.6	68 / 1 / 49	48.4
36	GPT 4.1	None	60.7	1564.8	44 / 10 / 34	9.2
37	Claude Opus 4.5	Historical	60.0	1565.1	57 / 11 / 64	17.3
38	Claude Opus 4.5	Medium	59.4	1549.9	53 / 9 / 42	5.0
39	Kimi K3	Low	58.8	1564.0	47 / 10 / 33	30.1
40	Kimi K3	High	58.5	1560.1	52 / 8 / 40	29.1
41	Claude Opus 4.5	High	55.4	1536.7	37 / 8 / 37	36.4
42	Grok 4.5	Low	55.3	1539.2	37 / 9 / 24	40.8
43	MiMo-V2.5	Reasoning	55.2	1514.4	85 / 1 / 80	10.8
44	GPT-5.4 Nano	None	54.9	1508.7	107 / 1 / 86	6.8
45	GPT-5.6 Terra	Medium	54.9	1507.5	47 / 12 / 41	6.0
46	Inkling	Max	54.7	1536.1	34 / 3 / 29	43.4
47	Grok 4.5	High	54.4	1522.5	45 / 6 / 39	30.0
48	GPT-5.5	Medium	53.7	1493.1	47 / 1 / 72	1.7
49	LongCat 2.0	None	51.8	1478.3	88 / 17 / 103	5.2
50	Claude Opus 4.5	None	51.1	1474.2	47 / 5 / 40	8.1
51	O3	High	51.0	1506.3	120 / 7 / 95	49.9
52	Claude Sonnet 5	Medium	50.8	1466.2	61 / 4 / 51	2.5
53	Gemini 3.1 Flash Lite	Medium	49.4	1451.1	50 / 0 / 80	0.0
54	Grok 4.5	Medium	48.3	1442.1	51 / 8 / 61	1.7
55	MiMo-V2.5-Pro	None	47.9	1441.9	55 / 1 / 44	6.0
56	Gemini 3.5 Flash Lite	High	47.7	1474.8	51 / 8 / 55	49.1
57	Gemini 3.1 Flash Lite	None	46.3	1432.5	43 / 1 / 34	12.5
58	GPT-5.6 Terra	None	46.3	1426.7	47 / 2 / 51	6.0
59	DeepSeek V4 Pro	XHigh	45.7	1418.6	51 / 2 / 61	2.9
60	GPT-5.6 Sol	None	45.2	1417.5	38 / 3 / 57	6.5
61	GPT-OSS 120B	Low	44.4	1436.1	35 / 0 / 48	39.3
62	LongCat 2.0	Enabled	44.4	1428.1	40 / 5 / 47	29.4
63	Grok Build 0.1	Enabled	44.1	1417.6	51 / 0 / 71	20.3
64	Step 3.7 Flash	High	42.1	1403.6	40 / 2 / 60	25.6
65	GPT-OSS 120B	Medium	42.1	1384.1	42 / 1 / 78	1.5
66	Gemini 3.6 Flash	Minimal	41.7	1409.9	53 / 19 / 79	38.7
67	Mistral Medium 3.5	None	40.9	1378.8	35 / 8 / 47	8.7
68	Gemma 4 31B	None	40.6	1373.4	41 / 2 / 59	5.5
69	MiMo-V2.5	Reasoning	40.2	1370.1	41 / 3 / 56	6.0
70	Nemotron 3 Ultra 550B A55B	High	39.9	1387.8	25 / 6 / 56	31.6
71	Inkling	None	39.8	1364.1	53 / 1 / 56	3.7
72	GPT-5.4 Mini	None	39.7	1365.5	46 / 6 / 46	6.5
73	MiMo-V2.5	Reasoning	37.4	1354.3	42 / 5 / 77	19.6
74	Gemma 4 31B	Enabled	37.1	1353.4	41 / 1 / 76	21.6
75	LongCat 2.0	Enabled	37.0	1368.5	23 / 4 / 45	42.0
76	Minimax M3	Enabled	36.9	1350.3	41 / 0 / 79	20.9
77	O3	Low	36.0	1354.9	18 / 18 / 42	36.2
78	Laguna S 2.1	Enabled	33.2	1323.6	30 / 4 / 54	31.0
79	Step 3.7 Flash	Medium	32.9	1299.6	33 / 1 / 76	3.7
80	DeepSeek V4 Flash	XHigh	32.5	1301.3	24 / 1 / 57	11.1
81	DeepSeek V4 Flash	Medium	32.5	1301.7	58 / 1 / 101	11.8
82	Mistral Medium 3.5	High	32.0	1312.5	28 / 0 / 60	30.8
83	Nemotron 3 Ultra 550B A55B	None	31.8	1295.6	31 / 0 / 49	11.8
84	Gemini 3.1 Flash Lite	High	31.2	1303.5	29 / 0 / 64	28.8
85	Ling 3.0 Flash	Enabled	30.9	1300.0	28 / 1 / 67	27.9
86	Hy3 Preview	High	30.7	1299.9	25 / 0 / 63	30.8
87	Qwen3.7 Max	None	30.5	1279.3	33 / 2 / 63	6.5
88	North Mini Code	Enabled	30.4	1291.5	34 / 1 / 79	23.2
89	Qwen3.7 Plus	None	30.3	1276.5	26 / 2 / 71	6.2
90	Laguna S 2.1	None	29.8	1270.3	46 / 4 / 58	4.1
91	Nex N2 Pro	None	29.5	1271.6	23 / 2 / 65	8.7
92	Nex N2 Pro	Enabled	26.1	1253.8	20 / 10 / 76	27.0
93	DeepSeek V4 Flash	None	19.6	1177.8	19 / 1 / 70	8.7
94	Ling 3.0 Flash	None	19.5	1170.1	62 / 4 / 192	0.1
95	Gemini 3.5 Flash Lite	Medium	19.3	1180.6	25 / 2 / 113	15.6
96	GPT-5.6 Luna	None	4.6	1036.9	9 / 0 / 81	8.7

Underlying results

Individual player programs

Each row is one accepted player program for GB2-06: International Draughts. A model can appear more than once when it produced more than one program. Score is the normalized 0–100 result; Elo and W / D / L show the underlying play record. Confidence and evidence can be blank when too few compatible matches are available. Draws at the move limit count; one-sided model faults are listed separately.

Search model Reasoning Status Sort Showing 114 player programs.

Player ID	Model	Reasoning	Status	Score	Elo	Confidence	W / D / L	Rated / attempted	Opponents	Faults / players	Generation
E-499fbc92ee0778fb	Claude Fable 5	XHigh	Rated	93.8	1878	—	63 / 9 / 10	82 / 82	39	0 / 1	Repaired · 2026-07-02
E-e1ca3ac536f3eb1e	Claude Fable 5	Medium	Rated	84.0	1783	—	65 / 5 / 22	92 / 92	46	0 / 1	First try · 2026-07-02
E-1ff6d6f973c7157d	Claude Opus 4.5	Medium effort + 16,000 thinking tokens	Rated	59.4	1550	—	53 / 9 / 42	104 / 104	52	0 / 1	First try · —
E-40a259ca8a40b5b4	Claude Opus 4.5	Thinking field omitted	Rated	51.1	1474	—	47 / 5 / 40	92 / 92	46	0 / 1	First try · 2026-07-02
E-41f8f2b491917557	Claude Opus 4.5	Legacy_shared_thinking_budget	Waiting	—	—	—	0 / 0 / 0	0 / 0	0	0 / 1	Repaired · 2026-07-02
E-8e040f66441f7747	Claude Opus 4.5	Legacy_shared_thinking_budget	Waiting	—	—	—	0 / 0 / 0	0 / 0	0	0 / 1	First try · 2026-07-02
E-df9bde92610963b7	Claude Opus 4.5	High effort + 32,000 thinking tokens	Rated	55.2	1525	—	24 / 5 / 25	54 / 54	27	0 / 1	First try · —
E-39e283268f14261d	Claude Opus 4.8	Medium	Rated	83.1	1775	—	67 / 1 / 22	90 / 90	45	0 / 1	First try · 2026-07-02
E-db414178442322d3	Claude Opus 4.8	Thinking field omitted	Rated	62.6	1583	—	50 / 9 / 29	88 / 88	44	0 / 1	First try · 2026-07-02
E-e804041031295d93	Claude Opus 4.8	XHigh	Rated	85.7	1802	—	62 / 2 / 16	80 / 80	38	0 / 1	First try · 2026-07-03
E-ca8985adf5006428	Claude Opus 5	Thinking disabled	Rated	99.2	1924	—	84 / 11 / 5	100 / 100	50	0 / 1	First try · 2026-07-25
E-01597b81edc004dd	Claude Sonnet 5	Medium	Rated	50.8	1466	—	61 / 4 / 51	116 / 116	58	0 / 1	First try · 2026-07-02
E-78dfcb6ce8b3efaa	North Mini Code	Enabled	Rated	26.3	1247	—	14 / 1 / 55	70 / 70	35	0 / 1	First try · 2026-07-02
E-5f5fd61f4544b8d7	DeepSeek V4 Flash	XHigh	Rated	32.5	1301	—	24 / 1 / 57	82 / 82	40	0 / 1	First try · 2026-07-02
E-6f20412107151172	DeepSeek V4 Flash	High	Rated	43.4	1405	—	38 / 1 / 41	80 / 80	40	0 / 1	First try · 2026-07-02
E-d8ca2fcf88af96c7	DeepSeek V4 Flash	High	Rated	21.5	1199	—	20 / 0 / 60	80 / 80	40	0 / 1	Repaired · 2026-07-01
E-db0efb02339d9e80	DeepSeek V4 Flash	Reasoning disabled	Rated	19.6	1178	—	19 / 1 / 70	90 / 90	44	0 / 1	First try · 2026-07-02
E-945bebaa34963e03	DeepSeek V4 Pro	Reasoning disabled	Rated	68.9	1642	—	54 / 8 / 24	86 / 86	43	0 / 1	First try · 2026-07-02
E-c9778645f1bbd12c	DeepSeek V4 Pro	XHigh	Rated	45.7	1419	—	51 / 2 / 61	114 / 114	56	0 / 1	First try · 2026-07-02
E-6238c7d8dc9e77d9	Gemini 3.1 Flash Lite	High	Rated	25.9	1255	—	6 / 0 / 39	45 / 45	23	0 / 1	Repaired · 2026-07-02
E-a10101fbca309818	Gemini 3.1 Flash Lite	Medium	Rated	49.4	1451	—	50 / 0 / 80	130 / 130	65	0 / 1	First try · 2026-07-02
E-dc1c0f46738d1091	Gemini 3.1 Flash Lite	Reasoning disabled	Rated	46.3	1432	—	43 / 1 / 34	78 / 78	39	0 / 1	First try · 2026-07-02
E-35d6e87056063577	Gemini 3.5 Flash	Medium	Rated	90.3	1843	—	63 / 11 / 12	86 / 86	43	0 / 1	Repaired · 2026-07-02
E-5dcb27eaa0273049	Gemini 3.5 Flash	High	Rated	69.7	1668	—	29 / 3 / 10	42 / 42	21	0 / 1	Repaired · 2026-07-02
E-8d5209853815321d	Gemini 3.5 Flash	Low	Waiting	—	—	—	0 / 0 / 0	0 / 0	0	0 / 1	First try · 2026-07-21
E-09a450a1726f909a	Gemini 3.5 Flash Lite	High	Limited data	38.2	1386	—	11 / 0 / 17	28 / 28	14	0 / 1	First try · 2026-07-24
E-3d6c386b0f48e1c1	Gemini 3.5 Flash Lite	Medium	Rated	19.3	1181	—	10 / 0 / 60	70 / 70	35	0 / 1	First try · 2026-07-24
E-3efea50fdbbd1829	Gemini 3.5 Flash Lite	Minimal	Limited data	62.7	1621	—	14 / 0 / 10	24 / 24	12	0 / 1	First try · 2026-07-24
E-46f1468c28505bfe	Gemini 3.5 Flash Lite	Minimal	Limited data	67.4	1669	—	16 / 0 / 6	22 / 22	11	0 / 1	Repaired · 2026-07-24
E-48cc2611d5aa8816	Gemini 3.5 Flash Lite	High	Limited data	52.7	1527	—	11 / 2 / 11	24 / 24	12	0 / 1	Repaired · 2026-07-24
E-892a28a528dad9c8	Gemini 3.5 Flash Lite	Medium	Rated	19.2	1180	—	15 / 2 / 53	70 / 70	35	0 / 1	First try · 2026-07-24
E-280a7de63c992141	Gemini 3.6 Flash	High	Rated	62.4	1600	—	25 / 3 / 14	42 / 42	21	0 / 1	Repaired · 2026-07-24
E-33485e8cce3184c3	Gemini 3.6 Flash	Medium	Rated	87.4	1823	—	53 / 6 / 7	66 / 66	33	0 / 1	First try · 2026-07-24
E-5455742d003ec402	Gemini 3.6 Flash	Minimal	Limited data	47.6	1467	—	13 / 8 / 13	34 / 34	17	0 / 1	Repaired · 2026-07-24
E-905531e52a8460f5	Gemini 3.6 Flash	High	Limited data	74.1	1732	—	19 / 0 / 3	22 / 22	11	0 / 1	Repaired · 2026-07-24
E-bb2e288b40b1a588	Gemini 3.6 Flash	Minimal	Limited data	43.5	1441	—	11 / 1 / 12	24 / 24	12	0 / 1	First try · 2026-07-24
E-bdf020e4fa85b365	Gemini 3.6 Flash	Medium	Rated	96.0	1903	—	58 / 4 / 4	66 / 66	33	0 / 1	First try · 2026-07-24
E-41987f96551bf9d3	Gemma 4 31B	Reasoning enabled	Rated	32.4	1304	—	17 / 0 / 53	70 / 70	35	0 / 1	Repaired · 2026-07-02
E-da266f7bbd330107	Gemma 4 31B	Reasoning disabled	Rated	40.6	1373	—	41 / 2 / 59	102 / 102	49	0 / 1	First try · 2026-07-02
E-4dcd6d3653c67437	GPT 4.1	None	Rated	60.7	1565	—	44 / 10 / 34	88 / 88	44	0 / 1	First try · 2026-07-02
E-1b082700b3692175	GPT 5	High	Rated	71.9	1686	—	31 / 4 / 11	46 / 46	23	0 / 1	Repaired · 2026-07-02
E-816d262cd933cdb9	GPT 5	Medium	Rated	63.5	1589	—	53 / 7 / 40	100 / 100	50	0 / 1	First try · 2026-07-02
E-00a57c19a4229948	GPT-5.4	None	Rated	72.5	1677	—	52 / 8 / 22	82 / 82	41	0 / 1	First try · 2026-07-02
E-61f3ed920d3c145d	GPT-5.4	Medium	Rated	95.4	1893	—	68 / 9 / 5	82 / 82	41	0 / 1	Repaired · 2026-07-02
E-6e5bbab022d4d9fa	GPT-5.4	XHigh	Rated	100.0	1936	—	65 / 10 / 7	82 / 82	38	0 / 1	Repaired · 2026-07-02
E-144154b792c9e9a6	GPT-5.4 Mini	None	Rated	39.7	1365	—	46 / 6 / 46	98 / 98	47	0 / 1	Repaired · 2026-07-02
E-3ccfe46cbdc271eb	GPT-5.4 Mini	Medium	Rated	62.1	1574	—	52 / 12 / 42	106 / 106	53	0 / 1	First try · 2026-07-02
E-5ccde5c853d97bd9	GPT-5.4 Nano	Medium	Rated	70.6	1654	—	58 / 3 / 47	108 / 108	54	0 / 1	Repaired · 2026-07-02
E-9c5263dcfd4c2ec7	GPT-5.4 Nano	Medium	Rated	60.8	1563	—	60 / 3 / 39	102 / 102	51	0 / 1	First try · 2026-07-09
E-a1fb59d78d39d217	GPT-5.4 Nano	None	Rated	43.2	1398	—	45 / 0 / 55	100 / 100	48	0 / 1	First try · 2026-07-09
E-d5866895bf388f66	GPT-5.4 Nano	None	Rated	66.6	1619	—	62 / 1 / 31	94 / 94	47	0 / 1	First try · 2026-07-02
E-1ea2c2c23d752166	GPT-5.5	Medium	Rated	53.7	1493	—	47 / 1 / 72	120 / 120	60	0 / 1	First try · 2026-07-02
E-4175a77ccf4c269b	GPT-5.5	XHigh	Rated	94.1	1880	—	62 / 4 / 16	82 / 82	41	0 / 1	First try · 2026-07-02
E-9eafeacabdedfdba	GPT-5.6 Luna	XHigh	Rated	81.1	1758	—	52 / 10 / 22	84 / 84	40	0 / 1	First try · 2026-07-10
E-ae522f9c5c491f57	GPT-5.6 Luna	None	Rated	4.6	1037	—	9 / 0 / 81	90 / 90	44	0 / 1	First try · 2026-07-10
E-f4c50b1a9cf2c2e6	GPT-5.6 Luna	Medium	Rated	70.7	1655	—	64 / 8 / 34	106 / 106	53	0 / 1	First try · 2026-07-10
E-992b9a5ebbb74c80	GPT-5.6 Sol	None	Rated	45.2	1417	—	38 / 3 / 57	98 / 98	48	0 / 1	First try · 2026-07-10
E-acdece52463a2698	GPT-5.6 Sol	Medium	Rated	85.1	1793	—	64 / 12 / 16	92 / 92	46	0 / 1	First try · 2026-07-10
E-eb315c759774ef38	GPT-5.6 Sol	XHigh	Rated	84.2	1787	—	58 / 3 / 23	84 / 84	39	0 / 1	First try · 2026-07-10
E-22ffdca36d9bac9c	GPT-5.6 Terra	None	Rated	46.3	1427	—	47 / 2 / 51	100 / 100	49	0 / 1	First try · 2026-07-10
E-a3722334e358f0fe	GPT-5.6 Terra	Medium	Rated	54.9	1507	—	47 / 12 / 41	100 / 100	50	0 / 1	First try · 2026-07-10
E-e6571a10c1120fab	GPT-5.6 Terra	XHigh	Rated	79.0	1736	—	56 / 0 / 34	90 / 90	43	0 / 1	First try · 2026-07-10
E-6807fffacebac165	Ling 3.0 Flash	Baseline track (legacy evidence incomplete)	Rated	38.9	1353	—	56 / 4 / 70	130 / 130	53	0 / 1	First try · 2026-07-24
E-6c37c8c2b8e19c4c	Ling 3.0 Flash	Enabled	Rated	31.5	1303	—	15 / 0 / 37	52 / 52	26	0 / 1	Repaired · 2026-07-24
E-9bde0475193e2c4a	Ling 3.0 Flash	Baseline track (legacy evidence incomplete)	Rated	0.0	987	—	6 / 0 / 122	128 / 128	50	0 / 1	Repaired · 2026-07-24
E-0e252768ba2388c4	LongCat 2.0	Enabled	Rated	35.8	1346	—	17 / 3 / 28	48 / 48	24	0 / 1	First try · 2026-07-24
E-3e8b2d11481a50d7	LongCat 2.0	None	Rated	46.1	1422	—	47 / 6 / 61	114 / 114	55	0 / 1	Repaired · 2026-07-24
E-a9bdeb6a9326ac2d	LongCat 2.0	Enabled	Rated	42.9	1411	—	22 / 3 / 25	50 / 50	25	0 / 1	Repaired · 2026-07-24
E-e3023ff7ecf82fc4	LongCat 2.0	None	Rated	57.6	1534	—	41 / 11 / 42	94 / 94	47	0 / 1	Repaired · 2026-07-24
E-ef8c1a9fa3580f83	Minimax M3	Reasoning enabled	Rated	30.3	1284	—	16 / 0 / 54	70 / 70	35	0 / 1	Repaired · 2026-07-02
E-6c35f5ff426e7ada	Mistral Medium 3.5	High	Rated	27.1	1265	—	7 / 0 / 39	46 / 46	23	0 / 1	Repaired · 2026-07-02
E-cf0bc4a1e7a8d72a	Mistral Medium 3.5	None	Rated	40.9	1379	—	35 / 8 / 47	90 / 90	44	0 / 1	Repaired · 2026-07-02
E-1640f1438f9390d7	Kimi K3	High	Rated	56.8	1535	—	37 / 4 / 25	66 / 66	33	0 / 1	Repaired · 2026-07-24
E-95a5c0e17cd4b70a	Kimi K3	Low	Rated	62.2	1594	—	31 / 2 / 15	48 / 48	24	0 / 1	First try · 2026-07-24
E-209380b737b62580	Nex N2 Pro	Reasoning enabled	Rated	20.5	1192	—	8 / 5 / 57	70 / 70	35	0 / 1	Repaired · 2026-07-02
E-973417dedd770061	Nex N2 Pro	Reasoning disabled	Rated	29.5	1272	—	23 / 2 / 65	90 / 90	44	0 / 1	Repaired · 2026-07-11
E-1ea0c8193f35ca72	Nemotron 3 Ultra 550B A55B	Medium	Rated	66.1	1614	—	51 / 8 / 37	96 / 96	48	0 / 1	Repaired · 2026-07-02
E-6e76a1c11ba24bc6	Nemotron 3 Ultra 550B A55B	Reasoning disabled	Rated	31.8	1296	—	31 / 0 / 49	80 / 80	40	0 / 1	Repaired · 2026-07-02
E-ba2fb1c121873708	Nemotron 3 Ultra 550B A55B	High	Rated	33.2	1321	—	12 / 2 / 35	49 / 49	25	0 / 1	Repaired · 2026-07-11
E-2c94ff7a30958259	O3	High	Limited data	47.8	1474	—	15 / 0 / 15	30 / 30	15	0 / 1	First try · 2026-07-03
E-35751e26cd4e995d	O3	High	Limited data	41.0	1409	—	11 / 2 / 17	30 / 30	15	0 / 1	First try · 2026-07-03
E-432424671c9fea1c	O3	High	Limited data	34.3	1346	—	9 / 0 / 21	30 / 30	15	0 / 1	First try · 2026-07-02
E-69e964db7b91b1bb	O3	Medium	Rated	65.5	1608	—	50 / 10 / 42	102 / 102	51	0 / 1	First try · 2026-07-02
E-9f2773793ec1d7e3	O3	Low	Rated	40.0	1386	—	13 / 12 / 21	46 / 46	23	0 / 1	First try · 2026-07-21
E-ead4229a85e5d554	O3	High	Limited data	48.1	1479	—	13 / 1 / 14	28 / 28	14	0 / 1	First try · 2026-07-03
E-a97b527d9b41a80c	GPT-OSS 120B	High	Rated	65.0	1619	—	28 / 4 / 18	50 / 50	25	0 / 1	Repaired · 2026-07-02
E-b75de88bfc62ab22	GPT-OSS 120B	Low	Rated	51.8	1490	—	28 / 0 / 32	60 / 60	30	0 / 1	First try · 2026-07-21
E-f225b6990e542d31	GPT-OSS 120B	Medium	Rated	42.1	1384	—	42 / 1 / 78	121 / 121	61	0 / 1	Repaired · 2026-07-02
E-a29031412bc33c39	Laguna S 2.1	None	Rated	29.8	1270	—	46 / 4 / 58	108 / 108	52	0 / 1	First try · 2026-07-24
E-b582570ce841ee30	Laguna S 2.1	Enabled	Rated	34.3	1332	—	18 / 1 / 29	48 / 48	24	0 / 1	First try · 2026-07-24
E-0c7e9f6c7d4cb892	Qwen3.7 Max	Reasoning disabled	Rated	30.5	1279	—	33 / 2 / 63	98 / 98	47	0 / 1	First try · 2026-07-02
E-8283efe6f68a787e	Qwen3.7 Max	Reasoning enabled	Rated	65.5	1615	—	40 / 5 / 25	70 / 70	35	0 / 1	Repaired · 2026-07-02
E-2fb82a23fdec2792	Qwen3.7 Plus	Reasoning disabled	Rated	30.3	1276	—	26 / 2 / 71	99 / 99	48	0 / 1	First try · 2026-07-02
E-b6dd11ebe2b80c7b	Qwen3.7 Plus	Reasoning enabled	Rated	81.5	1769	—	47 / 3 / 12	62 / 62	31	0 / 1	Repaired · 2026-07-02
E-2d684425ca56be18	Step 3.7 Flash	High	Rated	32.8	1316	—	10 / 1 / 39	50 / 50	25	0 / 1	Repaired · 2026-07-02
E-6526762dce98da7c	Step 3.7 Flash	Medium	Rated	32.9	1300	—	33 / 1 / 76	110 / 110	55	0 / 1	Repaired · 2026-07-02
E-ab4ccc8ca01bc627	Step 3.7 Flash	Low	Rated	65.2	1623	—	29 / 3 / 14	46 / 46	23	0 / 1	First try · 2026-07-21
E-3627e3dbf7a48738	Hy3 Preview	High	Rated	27.3	1270	—	6 / 0 / 36	42 / 42	21	0 / 1	First try · 2026-07-02
E-02be9616e86c7055	Inkling	None	Rated	39.8	1364	—	53 / 1 / 56	110 / 110	53	0 / 1	Repaired · 2026-07-24
E-56e54327930d2f64	Inkling	Max	Limited data	51.6	1514	—	14 / 0 / 12	26 / 26	13	0 / 1	Repaired · 2026-07-24
E-3baaff3521870bef	Grok 4.5	Medium	Rated	48.3	1442	—	51 / 8 / 61	120 / 120	60	0 / 1	First try · 2026-07-24
E-5a1e23bce371a184	Grok 4.5	High	Rated	52.3	1504	—	19 / 3 / 22	44 / 44	22	0 / 1	First try · 2026-07-24
E-8dbfeb56f012d9c6	Grok 4.5	Low	Rated	60.3	1580	—	23 / 7 / 12	42 / 42	21	0 / 1	First try · 2026-07-24
E-133675db0ee21fd5	Grok Build 0.1	Reasoning enabled	Rated	37.0	1348	—	22 / 0 / 48	70 / 70	35	0 / 1	Repaired · 2026-07-02
E-51421c7ae2af8f7b	MiMo-V2.5	High	Rated	62.6	1589	—	34 / 6 / 28	68 / 68	34	0 / 1	Repaired · 2026-07-02
E-7b4c450b6850f156	MiMo-V2.5	Reasoning enabled	Rated	31.0	1291	—	14 / 4 / 52	70 / 70	35	0 / 1	Repaired · 2026-07-02
E-d572bc902e0e416b	MiMo-V2.5	Reasoning disabled	Rated	40.2	1370	—	41 / 3 / 56	100 / 100	48	0 / 1	First try · 2026-07-02
E-d79ad8bc05d1b933	MiMo-V2.5	Reasoning disabled	Rated	42.8	1398	—	34 / 0 / 48	82 / 82	41	0 / 1	Repaired · 2026-07-02
E-ff7683792b6b3363	MiMo-V2.5	Reasoning disabled	Rated	67.6	1630	—	51 / 1 / 32	84 / 84	42	0 / 1	First try · 2026-07-01
E-530f82d65699c577	MiMo-V2.5-Pro	Reasoning enabled	Rated	73.2	1691	—	45 / 0 / 17	62 / 62	31	0 / 1	Repaired · 2026-07-02
E-6b662c734cdcff91	MiMo-V2.5-Pro	Reasoning disabled	Rated	47.9	1442	—	55 / 1 / 44	100 / 100	50	0 / 1	Repaired · 2026-07-02
E-657c61c9039ce566	GLM-5.2	Reasoning disabled	Rated	56.1	1525	—	35 / 10 / 29	74 / 74	37	0 / 1	First try · 2026-07-11
E-bc40affcf893e495	GLM-5.2	High	Rated	69.7	1655	—	35 / 8 / 25	68 / 68	34	0 / 1	Repaired · 2026-07-11
E-ec1479c855f477b4	GLM-5.2	Reasoning disabled	Rated	72.6	1682	—	31 / 6 / 33	70 / 70	35	0 / 1	Repaired · 2026-07-02