Name: DuelLab GameBench 2 public release gb2-20260807-76d592450aec
Creator: DuelLab
License: https://creativecommons.org/licenses/by/4.0/

Game profile

Go

Go is a large-grid territory-control game with stone placement, captures, ko restrictions, passing, and final area scoring.

Scores here compare player programs using DuelLab's encoded rules for Go; they are not a broad measure of human play strength.

By model and setting

GB2-01: Go 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: GB2-01: Go

GB2-01: Go - Reasoning Variants
Rank	Model	Reasoning	Score	Raw Elo	W / D / L	Uncertainty
1	GPT-5.4	XHigh	100.0	2000.8	89 / 0 / 5	7.5
2	GPT-5.4	None	100.0	2000.8	84 / 2 / 6	8.1
3	Gemini 3.5 Flash	Medium	93.2	1939.6	75 / 0 / 9	10.5
4	GPT-5.6 Sol	XHigh	83.1	1842.1	77 / 0 / 23	6.0
5	GPT-5.6 Luna	XHigh	80.7	1821.1	62 / 0 / 32	7.5
6	Claude Fable 5	XHigh	79.7	1810.8	63 / 0 / 35	6.5
7	Grok 4.5	Medium	78.5	1799.1	73 / 8 / 21	5.5
8	GPT-5.5	XHigh	73.3	1751.4	51 / 29 / 16	7.0
9	Claude Fable 5	Medium	73.2	1753.9	59 / 0 / 25	10.5
10	Gemini 3.6 Flash	Medium	72.5	1748.2	101 / 43 / 20	11.7
11	Hy3 Preview	None	71.4	1734.3	60 / 17 / 19	7.0
12	Claude Opus 5	None	70.2	1719.3	109 / 101 / 23	2.4
13	Claude Opus 5	Medium	69.6	1716.7	124 / 19 / 59	6.0
14	GPT-5.4	Medium	67.4	1700.1	47 / 19 / 16	11.1
15	Grok 4.5	High	66.9	1714.4	56 / 14 / 10	34.6
16	GPT-5.6 Luna	Medium	65.8	1684.1	51 / 9 / 28	9.2
17	GPT-5.6 Sol	Medium	63.9	1664.2	60 / 1 / 37	6.5
18	Claude Opus 5	XHigh	63.1	1666.8	77 / 1 / 46	19.5
19	Claude Opus 4.5	Medium	61.6	1645.7	42 / 21 / 21	10.5
20	GPT-5.5	Medium	60.0	1626.4	29 / 61 / 14	5.0
21	GPT-5.4 Mini	Medium	58.4	1613.3	53 / 4 / 39	7.0
22	Claude Opus 4.8	XHigh	57.6	1604.8	52 / 14 / 36	5.5
23	GPT-5.4 Nano	None	57.2	1602.4	80 / 51 / 59	7.4
24	GPT 4.1	None	56.4	1591.6	57 / 5 / 47	3.9
25	Hy3 Preview	High	54.1	1588.8	45 / 18 / 35	27.1
26	Qwen3.7 Max	None	54.0	1572.4	43 / 23 / 30	7.0
27	Nemotron 3 Ultra 550B A55B	None	53.8	1574.0	28 / 14 / 40	11.1
28	Claude Opus 4.8	None	53.6	1571.0	40 / 20 / 24	10.5
29	Claude Opus 4.5	High	53.0	1601.3	36 / 9 / 13	55.0
30	Claude Sonnet 5	Medium	52.8	1561.2	49 / 9 / 38	7.0
31	Kimi K3	Max	52.6	1578.9	44 / 9 / 33	31.6
32	GPT-5.6 Terra	None	52.2	1555.8	29 / 30 / 35	7.5
33	GPT-5.6 Sol	None	51.9	1555.2	47 / 11 / 28	9.9
34	Minimax M3	None	51.4	1543.5	60 / 24 / 38	1.3
35	Grok 4.5	Low	49.5	1542.6	21 / 79 / 14	22.8
36	Laguna S 2.1	None	49.2	1523.7	78 / 54 / 102	2.3
37	Nemotron 3 Ultra 550B A55B	Medium	49.0	1526.0	38 / 20 / 36	7.5
38	MiMo-V2.5	Reasoning	49.0	1521.4	42 / 27 / 49	2.1
39	GPT-5.5	None	48.4	1515.6	11 / 90 / 19	1.7
40	Kimi K3	Low	48.1	1530.7	16 / 82 / 12	24.1
41	O3	High	47.9	1555.8	95 / 12 / 67	56.3
42	GPT 4.1 Nano	Reasoning	47.8	1517.3	34 / 26 / 22	11.1
43	Qwen3.7 Plus	Enabled	47.8	1530.4	40 / 18 / 40	27.5
44	GPT-5.6 Terra	Medium	47.1	1507.6	33 / 34 / 29	7.0
45	MiMo-V2.5	Reasoning	47.0	1507.4	72 / 35 / 81	7.6
46	O3	Medium	45.7	1494.2	35 / 17 / 46	6.5
47	DeepSeek V4 Pro	None	45.5	1488.6	34 / 46 / 44	1.0
48	Gemini 3.5 Flash Lite	Medium	45.5	1496.6	76 / 47 / 61	11.8
49	Claude Opus 4.8	Medium	45.4	1492.7	38 / 17 / 39	7.5
50	Grok Build 0.1	Enabled	44.9	1501.4	42 / 23 / 43	24.2
51	Claude Sonnet 5	None	44.8	1489.6	8 / 66 / 10	10.5
52	Mistral Medium 3.5	None	44.6	1483.4	43 / 9 / 49	5.8
53	Gemma 4 31B	None	44.5	1479.5	55 / 25 / 38	2.1
54	Gemini 3.5 Flash Lite	Minimal	44.4	1503.4	66 / 50 / 56	32.2
55	DeepSeek V4 Pro	XHigh	43.6	1475.5	33 / 19 / 44	7.0
56	Gemini 3.1 Flash Lite	Medium	43.0	1468.2	22 / 44 / 38	5.0
57	GPT-5.6 Terra	XHigh	42.9	1467.9	29 / 31 / 40	6.0
58	Kimi K2.7 Code	Enabled	42.9	1483.0	51 / 4 / 51	25.0
59	Gemini 3.6 Flash	High	42.8	1499.2	48 / 49 / 49	46.4
60	GLM-5.2	Medium	42.5	1469.2	43 / 7 / 30	11.8
61	Claude Opus 4.5	None	42.4	1460.8	15 / 76 / 25	2.5
62	GPT 5	High	42.2	1475.9	50 / 6 / 52	23.8
63	Kimi K3	High	42.1	1501.0	19 / 7 / 22	56.5
64	GPT-OSS 120B	Medium	41.5	1456.7	27 / 24 / 43	7.5
65	Laguna S 2.1	Enabled	41.3	1485.4	29 / 13 / 28	45.8
66	Ling 3.0 Flash	None	40.2	1435.2	93 / 101 / 114	0.0
67	MiMo-V2.5-Pro	None	38.9	1427.5	33 / 32 / 51	2.5
68	LongCat 2.0	None	36.8	1407.5	65 / 82 / 93	1.7
69	MiMo-V2.5	Medium	36.2	1421.3	30 / 16 / 56	25.6
70	Gemini 3.6 Flash	Minimal	36.0	1424.3	53 / 52 / 65	32.1
71	Gemini 3.5 Flash Lite	High	35.0	1432.1	17 / 9 / 26	52.5
72	Inkling	Medium	34.9	1407.8	14 / 13 / 27	23.7
73	GPT-5.4 Mini	None	34.9	1392.2	22 / 40 / 44	4.6
74	Claude Opus 4.5	Historical	33.8	1387.2	27 / 94 / 45	10.8
75	DeepSeek V4 Flash	XHigh	33.5	1382.0	25 / 18 / 49	8.1
76	DeepSeek V4 Flash	Medium	33.1	1382.8	31 / 37 / 80	14.0
77	MiMo-V2.5	Reasoning	32.2	1382.3	47 / 3 / 60	23.5
78	GLM-5.2	None	31.0	1362.3	51 / 29 / 76	12.6
79	Qwen3.7 Plus	None	30.4	1351.2	19 / 26 / 55	6.0
80	Nemotron 3 Ultra 550B A55B	High	29.8	1365.4	22 / 20 / 48	30.0
81	GPT-OSS 120B	Low	29.6	1366.2	19 / 20 / 49	33.7
82	O3	Low	27.7	1353.3	6 / 29 / 41	39.4
83	Inkling	Max	26.9	1354.9	4 / 24 / 26	50.8
84	Minimax M3	Enabled	26.0	1327.0	27 / 7 / 68	26.4
85	Ling 3.0 Flash	Enabled	25.9	1343.2	4 / 17 / 37	47.6
86	GPT 5	Medium	25.7	1309.4	22 / 17 / 53	8.1
87	North Mini Code	None	25.0	1299.3	23 / 98 / 101	3.8
88	Qwen3.7 Max	Enabled	23.3	1303.5	12 / 30 / 54	28.8
89	GPT-5.6 Luna	None	22.4	1277.3	14 / 30 / 55	6.2
90	MiMo-V2.5	High	18.9	1251.9	2 / 41 / 29	14.8
91	Inkling	None	15.9	1213.9	22 / 84 / 124	2.7
92	GPT-5.4 Nano	Medium	15.4	1213.8	33 / 26 / 129	8.0
93	Step 3.7 Flash	High	15.1	1232.4	14 / 6 / 60	34.4
94	Mistral Medium 3.5	High	14.6	1224.3	8 / 19 / 61	30.8
95	Gemini 3.1 Flash Lite	None	11.5	1181.4	6 / 25 / 45	13.2

Underlying results

Individual player programs

Each row is one accepted player program for GB2-01: Go. 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 118 player programs.

Player ID	Model	Reasoning	Status	Score	Elo	Confidence	W / D / L	Rated / attempted	Opponents	Capped draws	Faults / players	Generation
E-2dbc6efbd7db03b5	Claude Fable 5	Medium	Rated	73.2	1754	—	59 / 0 / 25	84 / 86	42	0	2 / 1	First try · 2026-07-02
E-8000131e469a8bb6	Claude Fable 5	XHigh	Rated	79.7	1811	—	63 / 0 / 35	98 / 98	45	0	0 / 1	First try · 2026-07-03
E-2e3eca63f7980fac	Claude Opus 4.5	Thinking field omitted	Rated	42.4	1461	—	15 / 76 / 25	116 / 116	57	76	0 / 1	First try · 2026-07-02
E-53c8add70ed7d2e7	Claude Opus 4.5	Legacy_shared_thinking_budget	Waiting	—	—	—	0 / 0 / 0	0 / 0	0	0	0 / 1	First try · 2026-07-02
E-5b675f86b98132f4	Claude Opus 4.5	High effort + 32,000 thinking tokens	Rated	57.2	1623	—	28 / 3 / 11	42 / 42	21	3	0 / 1	First try · —
E-7631f602d0516364	Claude Opus 4.5	Legacy_shared_thinking_budget	Waiting	—	—	—	0 / 0 / 0	0 / 0	0	0	0 / 1	First try · 2026-07-02
E-829b603611fbdcef	Claude Opus 4.5	Medium effort + 16,000 thinking tokens	Rated	61.6	1646	—	42 / 21 / 21	84 / 84	42	21	0 / 1	First try · —
E-13ec9509bc80f2bf	Claude Opus 4.8	Medium	Rated	45.4	1493	—	38 / 17 / 39	94 / 94	47	17	0 / 1	First try · 2026-07-02
E-3308d2952452916e	Claude Opus 4.8	XHigh	Rated	57.6	1605	—	52 / 14 / 36	102 / 102	48	14	0 / 1	First try · 2026-07-03
E-757a6149e87d8b53	Claude Opus 4.8	Thinking field omitted	Rated	53.6	1571	—	40 / 20 / 24	84 / 84	42	20	0 / 1	First try · 2026-07-02
E-0437af9582860271	Claude Opus 5	Medium	Rated	60.0	1625	—	61 / 14 / 37	112 / 112	56	14	0 / 1	First try · 2026-07-25
E-6c30dc38efb07e9e	Claude Opus 5	Thinking disabled	Rated	53.1	1560	—	18 / 85 / 14	117 / 118	57	85	0 / 1	First try · 2026-07-25
E-700f3dddd611df07	Claude Opus 5	XHigh	Rated	82.4	1844	—	50 / 0 / 18	68 / 68	30	0	0 / 1	First try · 2026-07-25
E-865d68ab219fd7ee	Claude Opus 5	Thinking disabled	Rated	87.3	1879	—	91 / 16 / 9	116 / 116	56	16	0 / 1	First try · 2026-07-25
E-93a6875407c22137	Claude Opus 5	Medium	Rated	79.2	1808	—	63 / 5 / 22	90 / 90	45	5	0 / 1	First try · 2026-07-25
E-bf06fe9df8858291	Claude Opus 5	XHigh	Rated	43.7	1489	—	27 / 1 / 28	56 / 56	27	1	0 / 1	First try · 2026-07-25
E-259fc4a9e48c81f2	Claude Sonnet 5	Thinking disabled	Rated	44.8	1490	—	8 / 66 / 10	84 / 84	42	66	0 / 1	First try · 2026-07-12
E-cd50a27a6bb44b58	Claude Sonnet 5	Medium	Rated	52.8	1561	—	49 / 9 / 38	96 / 96	48	9	0 / 1	First try · 2026-07-02
E-194759b182ce3244	North Mini Code	Baseline track (legacy evidence incomplete)	Rated	47.7	1508	—	21 / 77 / 28	126 / 126	58	77	0 / 1	First try · 2026-07-02
E-c309b463b29efb71	North Mini Code	Baseline track (legacy evidence incomplete)	Rated	2.2	1090	—	2 / 21 / 73	96 / 96	46	21	0 / 1	Repaired · 2026-07-11
E-b9882650a0cde9ac	DeepSeek V4 Flash	XHigh	Rated	33.5	1382	—	25 / 18 / 49	92 / 92	45	18	0 / 1	First try · 2026-07-02
E-f1d9dfb787d0d902	DeepSeek V4 Flash	High	Rated	13.0	1196	—	7 / 26 / 43	76 / 76	38	26	0 / 1	Repaired · 2026-07-02
E-fd9da5310ad15cac	DeepSeek V4 Flash	High	Rated	53.1	1570	—	24 / 11 / 37	72 / 72	36	11	0 / 1	First try · 2026-07-01
E-e121525dd1846069	DeepSeek V4 Pro	Reasoning disabled	Rated	45.5	1489	—	34 / 46 / 44	124 / 124	60	46	0 / 1	First try · 2026-07-02
E-e192048d4eaa3c43	DeepSeek V4 Pro	XHigh	Rated	43.6	1475	—	33 / 19 / 44	96 / 96	47	19	0 / 1	Repaired · 2026-07-02
E-7669b8a03ef19548	Gemini 3.1 Flash Lite	Medium	Rated	43.0	1468	—	22 / 44 / 38	104 / 104	52	44	0 / 1	Repaired · 2026-07-02
E-cc0af0bfa6a9a29f	Gemini 3.1 Flash Lite	Reasoning disabled	Rated	11.5	1181	—	6 / 25 / 45	76 / 76	38	25	0 / 1	Repaired · 2026-07-02
E-22f31826bcf76511	Gemini 3.5 Flash	Medium	Rated	93.2	1940	—	75 / 0 / 9	84 / 86	42	0	0 / 1	Repaired · 2026-07-02
E-b33eea8b864e22bf	Gemini 3.5 Flash	Low	Waiting	—	—	—	0 / 0 / 0	0 / 0	0	0	0 / 1	First try · 2026-07-21
E-21c0edac8ac36f2e	Gemini 3.5 Flash Lite	Minimal	Rated	52.6	1578	—	22 / 15 / 7	44 / 44	22	15	0 / 1	First try · 2026-07-24
E-4b4f303670ce9fb6	Gemini 3.5 Flash Lite	Medium	Rated	47.6	1526	—	24 / 11 / 19	54 / 54	27	11	0 / 1	First try · 2026-07-24
E-77d8df8cd762fd09	Gemini 3.5 Flash Lite	Medium	Rated	43.3	1467	—	52 / 36 / 42	130 / 130	65	36	0 / 1	First try · 2026-07-24
E-85d9dd9fbf531322	Gemini 3.5 Flash Lite	High	Limited data	30.3	1388	—	8 / 3 / 15	26 / 26	13	3	0 / 1	First try · 2026-07-24
E-cf51875df5447bc2	Gemini 3.5 Flash Lite	Minimal	Limited data	40.7	1476	—	10 / 11 / 13	34 / 34	17	11	0 / 1	First try · 2026-07-24
E-27590b9ddebe06e6	Gemini 3.6 Flash	Medium	Rated	46.9	1514	—	16 / 43 / 9	68 / 68	34	43	0 / 1	First try · 2026-07-24
E-7484f4e7d8863a3b	Gemini 3.6 Flash	Medium	Rated	98.1	1983	—	85 / 0 / 11	96 / 96	48	0	0 / 1	First try · 2026-07-24
E-df0493ecef384a6a	Gemini 3.6 Flash	High	Rated	54.7	1597	—	26 / 5 / 15	46 / 46	23	5	0 / 1	First try · 2026-07-24
E-e0c4f14c94c0a42a	Gemini 3.6 Flash	Minimal	Rated	43.5	1495	—	15 / 15 / 12	42 / 42	21	15	0 / 1	First try · 2026-07-24
E-e9260a0da3a64563	Gemini 3.6 Flash	High	Rated	39.8	1457	—	13 / 12 / 21	46 / 46	23	12	0 / 1	Repaired · 2026-07-24
E-e9733de94d982ade	Gemini 3.6 Flash	Minimal	Rated	36.0	1426	—	13 / 12 / 15	40 / 40	20	12	0 / 1	First try · 2026-07-24
E-caaa54d3c88e6570	Gemma 4 31B	Reasoning disabled	Rated	44.5	1479	—	55 / 25 / 38	118 / 118	57	25	0 / 1	First try · 2026-07-02
E-f50ec6b60d5b85da	GPT 4.1	None	Rated	56.4	1592	—	57 / 5 / 47	109 / 110	54	5	1 / 1	First try · 2026-07-02
E-e117cfcfd3d0bf38	GPT 4.1 Nano	Reasoning field omitted	Rated	47.8	1517	—	34 / 26 / 22	82 / 82	41	26	0 / 1	First try · 2026-07-12
E-3e63b136f656e976	GPT 5	High	Rated	34.8	1409	—	16 / 2 / 32	50 / 50	25	2	0 / 1	First try · 2026-07-02
E-4370194a9beec334	GPT 5	Low	Waiting	—	—	—	0 / 0 / 0	0 / 0	0	0	0 / 1	First try · 2026-07-21
E-adee794ecd761044	GPT 5	Medium	Rated	25.7	1309	—	22 / 17 / 53	92 / 92	46	17	0 / 1	First try · 2026-07-02
E-586de6c9939561c3	GPT-5.4	Medium	Rated	67.4	1700	—	47 / 19 / 16	82 / 84	41	19	2 / 1	First try · 2026-07-02
E-5d8a6b14c27539ab	GPT-5.4	XHigh	Rated	100.0	2001	—	89 / 0 / 5	94 / 94	45	0	0 / 1	First try · 2026-07-02
E-60fa13e461853992	GPT-5.4	None	Rated	100.0	2001	—	84 / 2 / 6	92 / 98	46	2	0 / 1	First try · 2026-07-02
E-62424dfd649cbac9	GPT-5.4 Mini	Medium	Rated	58.4	1613	—	53 / 4 / 39	96 / 98	48	4	2 / 1	First try · 2026-07-02
E-ea1cb793f92b3cff	GPT-5.4 Mini	None	Rated	34.9	1392	—	22 / 40 / 44	106 / 106	52	40	0 / 1	First try · 2026-07-02
E-9257cc1e94bf4b17	GPT-5.4 Nano	Medium	Rated	30.8	1354	—	31 / 22 / 55	108 / 108	54	22	0 / 1	First try · 2026-07-02
E-9eb27042bf28d67c	GPT-5.4 Nano	None	Rated	59.7	1627	—	47 / 19 / 22	88 / 88	43	19	0 / 1	First try · 2026-07-09
E-a8887794a1195b75	GPT-5.4 Nano	None	Rated	54.8	1578	—	33 / 32 / 37	102 / 108	50	32	0 / 1	Repaired · 2026-07-02
E-c48c1aed1cdecc72	GPT-5.4 Nano	Medium	Rated	0.0	1073	—	2 / 4 / 74	80 / 82	40	4	2 / 1	Repaired · 2026-07-09
E-58178b9b32a94ca0	GPT-5.5	None	Rated	48.4	1516	—	11 / 90 / 19	120 / 120	59	90	0 / 1	First try · 2026-07-02
E-8c61292c31db2722	GPT-5.5	XHigh	Rated	73.3	1751	—	51 / 29 / 16	96 / 96	44	29	0 / 1	First try · 2026-07-02
E-e4496be687faac9d	GPT-5.5	Medium	Rated	60.0	1626	—	29 / 61 / 14	104 / 104	52	61	0 / 1	Repaired · 2026-07-02
E-38187ed58fb76057	GPT-5.6 Luna	XHigh	Rated	80.7	1821	—	62 / 0 / 32	94 / 94	45	0	0 / 1	First try · 2026-07-10
E-4f775a5b7b265dae	GPT-5.6 Luna	Medium	Rated	65.8	1684	—	51 / 9 / 28	88 / 88	44	9	0 / 1	First try · 2026-07-10
E-959ed218b1c5605b	GPT-5.6 Luna	None	Rated	22.4	1277	—	14 / 30 / 55	99 / 102	49	30	0 / 1	First try · 2026-07-10
E-890c38b8e811c121	GPT-5.6 Sol	None	Rated	51.9	1555	—	47 / 11 / 28	86 / 92	43	11	0 / 1	First try · 2026-07-10
E-9e683b3cd6c7f7c3	GPT-5.6 Sol	XHigh	Rated	83.1	1842	—	77 / 0 / 23	100 / 100	46	0	0 / 1	First try · 2026-07-10
E-bc834303cebba06a	GPT-5.6 Sol	Medium	Rated	63.9	1664	—	60 / 1 / 37	98 / 98	49	1	0 / 1	First try · 2026-07-10
E-36d36f4895d90b11	GPT-5.6 Terra	XHigh	Rated	42.9	1468	—	29 / 31 / 40	100 / 100	46	31	0 / 1	First try · 2026-07-10
E-40742129939a44b5	GPT-5.6 Terra	None	Rated	52.2	1556	—	29 / 30 / 35	94 / 94	46	30	0 / 1	First try · 2026-07-10
E-46de264ad4571b48	GPT-5.6 Terra	Medium	Rated	47.1	1508	—	33 / 34 / 29	96 / 96	48	34	0 / 1	Repaired · 2026-07-10
E-3c618b88b6bdb039	Ling 3.0 Flash	Baseline track (legacy evidence incomplete)	Rated	34.4	1381	—	51 / 58 / 49	158 / 158	64	58	0 / 1	First try · 2026-07-24
E-dd34dd6c69ef6a73	Ling 3.0 Flash	Enabled	Limited data	26.4	1346	—	3 / 8 / 19	30 / 32	15	8	0 / 1	First try · 2026-07-24
E-f9af396559c3a1cd	Ling 3.0 Flash	Baseline track (legacy evidence incomplete)	Rated	46.0	1489	—	42 / 43 / 65	150 / 150	58	43	0 / 1	First try · 2026-07-24
E-9f5585b5fd96f2c3	LongCat 2.0	None	Rated	39.5	1434	—	34 / 34 / 46	114 / 114	54	34	0 / 1	First try · 2026-07-24
E-ed0f8e084958eebc	LongCat 2.0	None	Rated	34.0	1381	—	31 / 48 / 47	126 / 126	60	48	0 / 1	First try · 2026-07-24
E-444510032bc433fc	Minimax M3	Reasoning disabled	Rated	51.4	1543	—	60 / 24 / 38	122 / 122	60	24	0 / 1	First try · 2026-07-02
E-e0a841a9daa66219	Minimax M3	Reasoning enabled	Rated	20.5	1271	—	11 / 4 / 45	60 / 60	30	4	0 / 1	Repaired · 2026-07-02
E-99c7b0d758665b66	Mistral Medium 3.5	High	Rated	10.4	1186	—	1 / 2 / 41	44 / 44	22	2	0 / 1	First try · 2026-07-02
E-a0a38f5e77e983bc	Mistral Medium 3.5	None	Rated	44.6	1483	—	43 / 9 / 49	101 / 136	50	9	35 / 1	Repaired · 2026-07-02
E-4935e918b1e70ea1	Kimi K2.7 Code	Reasoning enabled	Rated	43.1	1481	—	26 / 2 / 34	62 / 62	31	2	0 / 1	Repaired · 2026-07-02
E-58aadd759ee9fa72	Kimi K3	High	Limited data	47.8	1551	—	12 / 4 / 10	26 / 34	13	4	0 / 1	First try · 2026-07-24
E-dbb89dcf5242a5a0	Kimi K3	Max	Rated	45.7	1514	—	20 / 2 / 22	44 / 44	22	2	0 / 1	Repaired · 2026-07-24
E-fb8801908d28001f	Kimi K3	Low	Rated	50.1	1544	—	12 / 47 / 7	66 / 66	33	47	0 / 1	First try · 2026-07-24
E-0ce5e196701b51f3	Nemotron 3 Ultra 550B A55B	Reasoning disabled	Rated	53.8	1574	—	28 / 14 / 40	82 / 82	41	14	0 / 1	First try · 2026-07-02
E-b851008baae8f441	Nemotron 3 Ultra 550B A55B	Medium	Rated	49.0	1526	—	38 / 20 / 36	94 / 94	47	20	0 / 1	Repaired · 2026-07-02
E-ce064a9927030b28	Nemotron 3 Ultra 550B A55B	High	Rated	18.0	1256	—	4 / 3 / 37	44 / 44	22	3	0 / 1	Repaired · 2026-07-11
E-01ad69b67b42a9e7	O3	High	Rated	52.0	1570	—	27 / 1 / 20	48 / 48	24	1	0 / 1	First try · 2026-07-03
E-21b0558e9f2190f7	O3	High	Rated	57.6	1622	—	30 / 0 / 18	48 / 48	24	0	0 / 1	First try · 2026-07-03
E-428923c2eb87dc7a	O3	Medium	Rated	45.7	1494	—	35 / 17 / 46	98 / 98	49	17	0 / 1	First try · 2026-07-02
E-5e8b87fcfa2225fd	O3	High	Limited data	37.1	1451	—	7 / 5 / 14	26 / 26	13	5	0 / 1	First try · 2026-07-03
E-cb2bd51b4adfa607	O3	Low	Rated	28.1	1346	—	5 / 18 / 27	50 / 50	25	18	0 / 1	First try · 2026-07-21
E-55f6c0e3dc8a8065	GPT-OSS 120B	Low	Rated	29.3	1354	—	12 / 14 / 32	58 / 58	29	14	0 / 1	First try · 2026-07-21
E-a3e0c8f8ea39b5ec	GPT-OSS 120B	Medium	Rated	41.5	1457	—	27 / 24 / 43	94 / 94	47	24	0 / 1	Repaired · 2026-07-02
E-8461eb1b16e40129	Laguna S 2.1	None	Rated	56.2	1589	—	41 / 20 / 57	118 / 118	58	20	0 / 1	Repaired · 2026-07-24
E-c58ec61528547516	Laguna S 2.1	None	Rated	42.2	1459	—	37 / 34 / 45	116 / 116	55	34	0 / 1	First try · 2026-07-24
E-ffd72d2c5c11728a	Laguna S 2.1	Enabled	Limited data	38.9	1478	—	10 / 2 / 8	20 / 20	10	2	0 / 1	First try · 2026-07-24
E-24581eb49b81bf8f	Qwen3.7 Max	Reasoning enabled	Rated	25.3	1317	—	7 / 11 / 40	58 / 58	29	11	0 / 1	Repaired · 2026-07-02
E-8a70cd704fcbcf6f	Qwen3.7 Max	Reasoning disabled	Rated	54.0	1572	—	43 / 23 / 30	96 / 102	48	23	0 / 1	First try · 2026-07-02
E-1e5dceaf2ba3ca9a	Qwen3.7 Plus	Reasoning enabled	Rated	50.1	1548	—	28 / 7 / 21	56 / 56	28	7	0 / 1	Repaired · 2026-07-02
E-5e09f0c994a59f3c	Qwen3.7 Plus	Reasoning disabled	Rated	30.4	1351	—	19 / 26 / 55	100 / 100	49	26	0 / 1	Repaired · 2026-07-03
E-4b0ce2bc67b08d8a	Step 3.7 Flash	High	Rated	11.4	1196	—	2 / 1 / 39	42 / 42	21	1	0 / 1	Repaired · 2026-07-02
E-29e8870e43d717e5	Hy3 Preview	High	Rated	52.1	1572	—	26 / 4 / 16	46 / 46	23	4	0 / 1	First try · 2026-07-02
E-3407ff2dd1928eb5	Hy3 Preview	None	Rated	71.4	1734	—	60 / 17 / 19	96 / 102	48	17	0 / 1	First try · 2026-07-02
E-46c7f693daaae605	Inkling	Medium	Rated	34.9	1408	—	14 / 13 / 27	54 / 54	27	13	0 / 1	First try · 2026-07-24
E-9e638fc0ac98df4f	Inkling	None	Rated	23.2	1282	—	16 / 51 / 49	116 / 116	55	51	0 / 1	First try · 2026-07-24
E-ab1de1dc51400446	Inkling	Max	Limited data	27.0	1355	—	2 / 15 / 11	28 / 28	14	15	0 / 1	First try · 2026-07-24
E-bc7c657b08ebac66	Inkling	None	Rated	8.6	1146	—	6 / 33 / 75	114 / 114	54	33	0 / 1	First try · 2026-07-24
E-1c8e452ede41ea2e	Grok 4.5	High	Limited data	62.7	1678	—	24 / 6 / 6	36 / 36	18	6	0 / 1	Repaired · 2026-07-24
E-7ee1b68d1249ac22	Grok 4.5	Low	Rated	54.1	1581	—	18 / 44 / 6	68 / 68	34	44	0 / 1	First try · 2026-07-24
E-d709aeb6802f9289	Grok 4.5	Medium	Rated	78.5	1799	—	73 / 8 / 21	102 / 104	51	8	2 / 1	First try · 2026-07-24
E-f1ded648f3ab17dc	Grok Build 0.1	Reasoning enabled	Rated	43.3	1482	—	22 / 10 / 30	62 / 62	31	10	0 / 1	Repaired · 2026-07-02
E-1208f50b0908ecb4	MiMo-V2.5	Reasoning enabled	Rated	34.4	1400	—	25 / 3 / 34	62 / 62	31	3	0 / 1	Repaired · 2026-07-02
E-2a71bee21bd7c0b9	MiMo-V2.5	Reasoning enabled	Rated	34.0	1401	—	13 / 3 / 34	50 / 50	25	3	0 / 1	Repaired · 2026-07-02
E-2cdd8ae895784956	MiMo-V2.5	Reasoning disabled	Rated	54.4	1577	—	44 / 6 / 40	90 / 90	45	6	0 / 1	First try · 2026-07-02
E-8478c64d84536b61	MiMo-V2.5	High	Rated	18.9	1252	—	2 / 41 / 29	72 / 72	36	41	0 / 1	Repaired · 2026-07-02
E-912a4a40bbdcbd45	MiMo-V2.5	Reasoning disabled	Rated	49.0	1521	—	42 / 27 / 49	118 / 118	58	27	0 / 1	First try · 2026-07-02
E-a168350bd057f924	MiMo-V2.5	Reasoning disabled	Rated	39.6	1438	—	28 / 29 / 41	98 / 98	49	29	0 / 1	First try · 2026-07-01
E-9ce4191c7f1f3b3e	MiMo-V2.5-Pro	Reasoning disabled	Rated	38.9	1428	—	33 / 32 / 51	116 / 116	57	32	0 / 1	First try · 2026-07-02
E-5c3b7f5666a38043	GLM-5.2	Reasoning disabled	Rated	43.9	1482	—	29 / 26 / 27	82 / 82	41	26	0 / 1	First try · 2026-07-11
E-c8076ea61de8da45	GLM-5.2	Reasoning disabled	Rated	18.0	1243	—	22 / 3 / 49	74 / 74	37	3	0 / 1	First try · 2026-07-02
E-f889d782e3cce209	GLM-5.2	High	Rated	42.5	1469	—	43 / 7 / 30	80 / 80	40	7	0 / 1	Repaired · 2026-07-11