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

Game profile

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

By model and setting

GB2-08: Tumbleweed 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: GB2-08: Tumbleweed

GB2-08: Tumbleweed - Reasoning Variants
Rank	Model	Reasoning	Score	Raw Elo	W / D / L	Uncertainty
1	Claude Fable 5	XHigh	100.0	2047.1	95 / 1 / 4	6.0
2	Claude Opus 5	Medium	82.8	1902.1	174 / 0 / 28	5.8
3	Grok 4.5	Medium	80.5	1882.1	87 / 1 / 14	5.5
4	Claude Fable 5	Medium	72.2	1814.5	80 / 0 / 12	8.1
5	Claude Opus 4.5	Medium	69.0	1789.3	66 / 1 / 17	10.5
6	GPT-5.5	XHigh	68.8	1783.5	62 / 16 / 24	5.5
7	Kimi K3	Low	68.6	1801.7	84 / 0 / 6	30.6
8	Claude Opus 4.5	None	68.2	1781.2	65 / 4 / 19	9.2
9	GPT-5.6 Sol	Medium	67.8	1778.4	64 / 5 / 19	9.2
10	Claude Opus 5	XHigh	67.5	1776.1	131 / 0 / 39	10.2
11	Claude Opus 4.8	XHigh	67.0	1769.8	73 / 0 / 23	7.0
12	Grok 4.5	High	66.9	1788.3	73 / 1 / 14	31.0
13	Claude Opus 4.8	None	66.5	1767.4	63 / 0 / 25	9.2
14	Inkling	None	63.3	1735.2	68 / 7 / 37	3.3
15	Grok 4.5	Low	62.9	1755.6	71 / 0 / 15	32.8
16	Claude Opus 5	None	58.6	1700.8	127 / 7 / 48	9.4
17	Claude Opus 4.5	Historical	54.4	1668.7	66 / 25 / 59	13.6
18	Kimi K2.7 Code	Enabled	53.7	1674.7	58 / 10 / 30	28.3
19	GPT-5.6 Luna	XHigh	52.1	1645.2	55 / 6 / 31	8.1
20	Gemini 3.6 Flash	Medium	51.8	1654.2	30 / 9 / 17	22.5
21	GPT-5.6 Terra	XHigh	48.7	1615.1	51 / 15 / 32	6.5
22	GPT-5.4 Nano	Medium	48.1	1610.5	77 / 52 / 59	7.5
23	GPT-5.5	Medium	47.9	1605.8	38 / 50 / 24	3.3
24	Gemini 3.6 Flash	High	47.7	1642.1	44 / 12 / 12	51.2
25	GPT-5.4	XHigh	47.3	1602.6	43 / 26 / 31	6.0
26	GLM-5.2	None	45.2	1592.1	53 / 62 / 31	14.5
27	GPT-5.6 Sol	None	39.6	1539.1	43 / 15 / 34	8.1
28	GPT-5.4 Nano	None	39.2	1535.7	54 / 93 / 45	7.2
29	DeepSeek V4 Pro	None	38.4	1525.9	9 / 82 / 17	4.1
30	Minimax M3	None	37.8	1523.1	40 / 7 / 49	7.0
31	GPT-5.6 Terra	Medium	33.6	1485.6	21 / 53 / 34	4.1
32	MiMo-V2.5	Reasoning	33.1	1502.1	21 / 51 / 30	30.4
33	O3	Medium	31.6	1466.4	29 / 63 / 32	1.0
34	O3	High	30.5	1498.6	59 / 83 / 63	51.8
35	GPT-5.4	Medium	30.3	1459.2	31 / 38 / 31	6.0
36	Hy3 Preview	High	29.6	1468.7	33 / 26 / 43	25.7
37	GPT-5.4	None	29.4	1450.8	12 / 72 / 20	5.0
38	GPT-OSS 120B	Medium	29.0	1444.8	9 / 86 / 23	2.1
39	Nemotron 3 Ultra 550B A55B	None	28.6	1448.7	1 / 76 / 5	11.1
40	Nemotron 3 Ultra 550B A55B	Medium	28.3	1440.8	9 / 72 / 27	4.1
41	Gemini 3.1 Flash Lite	Medium	28.2	1436.6	39 / 40 / 51	0.0
42	GPT-5.5	None	28.0	1439.5	4 / 81 / 19	5.0
43	Gemma 4 31B	None	27.9	1436.4	3 / 92 / 21	2.5
44	GPT-5.4 Mini	Medium	27.9	1436.7	35 / 41 / 38	2.9
45	LongCat 2.0	None	27.9	1436.9	8 / 192 / 22	3.5
46	Hy3 Preview	None	27.8	1436.4	3 / 88 / 21	3.3
47	GPT-5.6 Luna	None	27.6	1435.5	1 / 87 / 18	4.6
48	GPT-5.4 Mini	None	27.6	1439.4	0 / 74 / 12	9.9
49	Qwen3.7 Max	Enabled	27.4	1447.8	11 / 76 / 31	22.0
50	Inkling	Medium	27.4	1442.2	4 / 55 / 12	15.2
51	Nex N2 Pro	None	27.1	1431.0	0 / 94 / 14	4.1
52	GPT-5.6 Luna	Medium	27.0	1429.4	7 / 87 / 18	3.3
53	Ling 3.0 Flash	None	26.8	1421.9	5 / 262 / 37	0.0
54	MiMo-V2.5	High	26.6	1434.8	2 / 69 / 3	14.0
55	Claude Sonnet 5	Medium	26.6	1426.3	7 / 83 / 20	3.7
56	DeepSeek V4 Flash	None	26.4	1424.5	6 / 86 / 18	3.7
57	Laguna S 2.1	None	26.3	1423.3	6 / 189 / 29	3.3
58	North Mini Code	None	26.3	1422.2	4 / 94 / 20	2.1
59	Claude Opus 4.8	Medium	26.2	1423.0	5 / 82 / 21	4.1
60	MiMo-V2.5	Reasoning	26.2	1426.5	2 / 72 / 16	8.7
61	Kimi K3	High	26.1	1440.8	5 / 78 / 19	26.8
62	Laguna S 2.1	Enabled	26.0	1444.6	6 / 139 / 23	32.6
63	DeepSeek V4 Flash	Medium	26.0	1427.7	4 / 140 / 16	11.8
64	Gemini 3.5 Flash Lite	Medium	26.0	1429.8	5 / 116 / 23	14.8
65	Grok Build 0.1	Enabled	25.9	1436.8	6 / 91 / 15	24.0
66	Gemini 3.5 Flash Lite	Minimal	25.9	1444.3	6 / 134 / 24	33.7
67	Minimax M3	Enabled	25.9	1436.5	7 / 86 / 19	24.0
68	GLM-5.2	Medium	25.8	1428.0	1 / 62 / 11	14.0
69	Gemini 3.6 Flash	Minimal	25.4	1440.3	4 / 133 / 27	33.5
70	Qwen3.7 Plus	Enabled	25.4	1433.0	0 / 94 / 20	24.8
71	Qwen3.7 Max	None	25.4	1416.2	4 / 74 / 30	4.1
72	GPT 4.1	None	25.3	1415.6	11 / 79 / 16	4.6
73	Claude Opus 4.5	High	24.8	1431.3	9 / 50 / 35	28.5
74	GPT-5.6 Terra	None	24.6	1411.7	3 / 72 / 23	6.5
75	DeepSeek V4 Flash	XHigh	24.6	1410.4	2 / 73 / 29	5.0
76	O3	Low	24.1	1435.8	1 / 57 / 14	42.0
77	Mistral Medium 3.5	None	23.9	1403.2	2 / 90 / 22	2.9
78	DeepSeek V4 Pro	XHigh	23.6	1405.5	4 / 59 / 25	9.2
79	GPT 5	High	23.5	1415.6	16 / 62 / 32	23.1
80	GPT-OSS 120B	Low	22.3	1427.9	3 / 46 / 19	51.2
81	GPT-OSS 120B	High	22.1	1410.1	5 / 63 / 22	31.1
82	Gemini 3.5 Flash Lite	High	22.0	1413.2	3 / 52 / 27	35.5
83	Step 3.7 Flash	Low	22.0	1425.7	0 / 52 / 16	51.2
84	Nemotron 3 Ultra 550B A55B	High	21.9	1407.3	15 / 124 / 49	29.3
85	Gemini 3.1 Flash Lite	High	21.7	1402.1	6 / 68 / 28	25.7
86	GPT 5	Medium	21.5	1387.4	8 / 54 / 26	9.2
87	Step 3.7 Flash	High	21.4	1405.0	1 / 66 / 21	32.2
88	Gemini 3.6 Flash	High	21.1	1416.6	5 / 33 / 26	50.1
89	North Mini Code	Enabled	20.4	1394.6	0 / 78 / 22	29.9
90	GPT-5.6 Sol	XHigh	20.3	1378.9	22 / 12 / 50	10.5
91	MiMo-V2.5-Pro	Enabled	19.8	1388.5	2 / 73 / 25	27.8
92	Gemini 3.5 Flash	Medium	19.2	1368.3	0 / 67 / 21	9.2
93	Inkling	Max	19.1	1384.5	3 / 53 / 34	31.1
94	LongCat 2.0	Enabled	18.8	1408.1	18 / 41 / 65	51.4
95	MiMo-V2.5	Reasoning	16.9	1347.1	2 / 58 / 34	7.5
96	Gemini 3.5 Flash	High	13.6	1336.8	0 / 60 / 34	29.0
97	MiMo-V2.5	Medium	12.0	1325.2	3 / 43 / 46	31.1
98	Nex N2 Pro	Enabled	5.7	1274.3	8 / 13 / 69	34.2

Underlying results

Individual player programs

Each row is one accepted player program for GB2-08: Tumbleweed. 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 119 player programs.

Player ID	Model	Reasoning	Status	Score	Elo	Confidence	W / D / L	Rated / attempted	Opponents	Capped draws	Faults / players	Generation
E-12891afa894223fd	Claude Fable 5	XHigh	Rated	100.0	2047	—	95 / 1 / 4	100 / 100	48	1	0 / 1	Repaired · 2026-07-02
E-9ccf296d44d35675	Claude Fable 5	Medium	Rated	72.2	1815	—	80 / 0 / 12	92 / 92	46	0	0 / 1	First try · 2026-07-02
E-01b57d5e6655f927	Claude Opus 4.5	Thinking field omitted	Rated	68.2	1781	—	65 / 4 / 19	88 / 88	44	4	0 / 1	First try · 2026-07-02
E-355427eb0d526f34	Claude Opus 4.5	Legacy_shared_thinking_budget	Waiting	—	—	—	0 / 0 / 0	0 / 0	0	0	0 / 1	First try · 2026-07-02
E-6a0c04b4335bfea0	Claude Opus 4.5	Legacy_shared_thinking_budget	Waiting	—	—	—	0 / 0 / 0	0 / 0	0	0	0 / 1	First try · 2026-07-02
E-72233463ddce5549	Claude Opus 4.5	Medium effort + 16,000 thinking tokens	Rated	69.0	1789	—	66 / 1 / 17	84 / 84	42	1	0 / 1	First try · —
E-877eec51affacb3a	Claude Opus 4.5	High effort + 32,000 thinking tokens	Rated	24.0	1423	—	6 / 24 / 20	50 / 50	25	24	0 / 1	First try · —
E-22dc6fe5ae5fb8b1	Claude Opus 4.8	XHigh	Rated	67.0	1770	—	73 / 0 / 23	96 / 96	46	0	0 / 1	First try · 2026-07-03
E-c2dade0b97891d8a	Claude Opus 4.8	Medium	Rated	26.2	1423	—	5 / 82 / 21	108 / 108	54	82	0 / 1	First try · 2026-07-02
E-c9d7578e8375d994	Claude Opus 4.8	Thinking field omitted	Rated	66.5	1767	—	63 / 0 / 25	88 / 88	44	0	0 / 1	First try · 2026-07-02
E-35a5bf9b35d5e1e8	Claude Opus 5	Medium	Rated	76.2	1847	—	80 / 0 / 20	100 / 100	50	0	0 / 1	First try · 2026-07-25
E-43cc1c89fa5720b3	Claude Opus 5	Thinking disabled	Rated	65.6	1765	—	51 / 7 / 12	70 / 70	35	7	0 / 1	First try · 2026-07-25
E-5a7942274854aaa6	Claude Opus 5	Thinking disabled	Rated	51.6	1637	—	76 / 0 / 36	112 / 112	56	0	0 / 1	First try · 2026-07-25
E-a40851c4f03704e5	Claude Opus 5	XHigh	Rated	78.0	1865	—	71 / 0 / 13	84 / 84	38	0	0 / 1	First try · 2026-07-25
E-e73b6fb78880341d	Claude Opus 5	Medium	Rated	89.4	1958	—	94 / 0 / 8	102 / 102	51	0	0 / 1	First try · 2026-07-25
E-f5914ca845403384	Claude Opus 5	XHigh	Rated	56.9	1687	—	60 / 0 / 26	86 / 86	40	0	0 / 1	First try · 2026-07-25
E-130fb40b1c7a4d39	Claude Sonnet 5	Medium	Rated	26.6	1426	—	7 / 83 / 20	110 / 110	55	83	0 / 1	First try · 2026-07-02
E-c36a98e057c264eb	North Mini Code	Baseline track (legacy evidence incomplete)	Rated	26.3	1422	—	4 / 94 / 20	118 / 118	52	94	0 / 1	First try · 2026-07-11
E-efd7b75d5cd3b538	North Mini Code	Enabled	Rated	21.4	1393	—	0 / 50 / 18	68 / 68	34	50	0 / 1	First try · 2026-07-02
E-4375cf96eeb624e2	DeepSeek V4 Flash	Reasoning disabled	Rated	26.4	1425	—	6 / 86 / 18	110 / 110	53	86	0 / 1	Repaired · 2026-07-02
E-43aba68125a9abc5	DeepSeek V4 Flash	High	Rated	28.0	1445	—	2 / 69 / 7	78 / 78	39	69	0 / 1	First try · 2026-07-02
E-a7310645c3b96434	DeepSeek V4 Flash	XHigh	Rated	24.6	1410	—	2 / 73 / 29	104 / 104	52	73	0 / 1	Repaired · 2026-07-02
E-d28ef17ff6995c62	DeepSeek V4 Flash	High	Rated	24.0	1411	—	2 / 71 / 9	82 / 82	41	71	0 / 1	Repaired · 2026-07-01
E-3a5b5c4507a989d3	DeepSeek V4 Pro	XHigh	Rated	23.6	1405	—	4 / 59 / 25	88 / 88	43	59	0 / 1	Repaired · 2026-07-02
E-c296a7abab6975d7	DeepSeek V4 Pro	Reasoning disabled	Rated	38.4	1526	—	9 / 82 / 17	108 / 108	53	82	0 / 1	First try · 2026-07-02
E-b335c9f92035f80b	Gemini 3.1 Flash Lite	High	Rated	15.9	1352	—	2 / 27 / 25	54 / 54	27	27	0 / 1	Repaired · 2026-07-02
E-cc6fb78c96472032	Gemini 3.1 Flash Lite	Medium	Rated	28.2	1437	—	39 / 40 / 51	130 / 130	65	40	0 / 1	First try · 2026-07-02
E-5aa593158b0d8b3a	Gemini 3.5 Flash	Low	Waiting	—	—	—	0 / 0 / 0	0 / 0	0	0	0 / 1	First try · 2026-07-21
E-bd0bbefbbd252fc5	Gemini 3.5 Flash	Medium	Rated	19.2	1368	—	0 / 67 / 21	88 / 88	44	67	0 / 1	Repaired · 2026-07-02
E-fa332e578ae97122	Gemini 3.5 Flash	High	Rated	10.0	1302	—	0 / 26 / 28	54 / 54	27	26	0 / 1	Repaired · 2026-07-02
E-284d554eca16e6f6	Gemini 3.5 Flash Lite	Minimal	Limited data	26.5	1453	—	1 / 31 / 4	36 / 36	18	31	0 / 1	First try · 2026-07-24
E-2a14d2f80ade1bda	Gemini 3.5 Flash Lite	High	Rated	15.7	1351	—	1 / 28 / 23	52 / 52	26	28	0 / 2	First try · 2026-07-24
E-2f2aa5b1beafd6e6	Gemini 3.5 Flash Lite	Medium	Rated	26.3	1432	—	3 / 62 / 11	76 / 76	38	62	0 / 1	First try · 2026-07-24
E-9b50de854a87d3c6	Gemini 3.5 Flash Lite	Medium	Rated	25.6	1428	—	2 / 54 / 12	68 / 68	34	54	0 / 1	First try · 2026-07-24
E-af119b49b8f1d63d	Gemini 3.5 Flash Lite	Minimal	Limited data	27.0	1455	—	1 / 33 / 4	38 / 38	19	33	0 / 1	First try · 2026-07-24
E-620b5ca2bcd82419	Gemini 3.6 Flash	High	Rated	54.3	1677	—	34 / 8 / 10	52 / 52	26	8	0 / 1	First try · 2026-07-24
E-657c523bc9e9f80c	Gemini 3.6 Flash	Minimal	Limited data	26.5	1451	—	1 / 33 / 4	38 / 38	19	33	0 / 1	Repaired · 2026-07-24
E-ab7ee826f8050f04	Gemini 3.6 Flash	Medium	Rated	51.8	1654	—	30 / 9 / 17	56 / 56	28	9	0 / 1	First try · 2026-07-24
E-c694a36a5e4e3f09	Gemini 3.6 Flash	Minimal	Rated	24.7	1432	—	1 / 37 / 6	44 / 44	22	37	0 / 1	First try · 2026-07-24
E-efad9f3f4e9183a0	Gemini 3.6 Flash	High	Rated	18.6	1379	—	3 / 23 / 20	46 / 46	23	23	0 / 1	First try · 2026-07-24
E-8546650b7690a81a	Gemma 4 31B	Reasoning disabled	Rated	27.9	1436	—	3 / 92 / 21	116 / 116	56	92	0 / 1	First try · 2026-07-02
E-eabc996d553eebe0	GPT 4.1	None	Rated	25.3	1416	—	11 / 79 / 16	106 / 106	50	79	0 / 1	First try · 2026-07-02
E-04ae9f2b42e0e036	GPT 5	Medium	Rated	21.5	1387	—	8 / 54 / 26	88 / 88	44	54	0 / 1	First try · 2026-07-02
E-ae3a897b3420bcfb	GPT 5	Low	Waiting	—	—	—	0 / 0 / 0	0 / 0	0	0	0 / 1	First try · 2026-07-21
E-ebca8ea756b4a4ad	GPT 5	High	Rated	19.4	1381	—	6 / 25 / 23	54 / 54	27	25	0 / 1	First try · 2026-07-02
E-95f891d54f35bb4a	GPT-5.4	None	Rated	29.4	1451	—	12 / 72 / 20	104 / 104	51	72	0 / 1	Repaired · 2026-07-02
E-b13a2be40d59c1ea	GPT-5.4	Medium	Rated	30.3	1459	—	31 / 38 / 31	100 / 100	50	38	0 / 1	First try · 2026-07-02
E-ddc1f3e68bf1e74a	GPT-5.4	XHigh	Rated	47.3	1603	—	43 / 26 / 31	100 / 100	47	26	0 / 1	First try · 2026-07-02
E-b5171a15f0048555	GPT-5.4 Mini	Medium	Rated	27.9	1437	—	35 / 41 / 38	114 / 114	57	41	0 / 1	First try · 2026-07-02
E-bb8ac98c284a38ce	GPT-5.4 Mini	None	Rated	27.6	1439	—	0 / 74 / 12	86 / 88	43	74	2 / 1	First try · 2026-07-02
E-024aff0a983df40d	GPT-5.4 Nano	None	Rated	24.8	1411	—	0 / 89 / 17	106 / 106	52	89	0 / 1	First try · 2026-07-09
E-26fa12e871bd8f3a	GPT-5.4 Nano	Medium	Rated	19.3	1368	—	5 / 52 / 37	94 / 94	47	52	0 / 1	Repaired · 2026-07-02
E-e361d8cbba2abd67	GPT-5.4 Nano	Medium	Rated	76.9	1853	—	72 / 0 / 22	94 / 94	47	0	0 / 1	Repaired · 2026-07-09
E-fd5a36e5fd795426	GPT-5.4 Nano	None	Rated	53.7	1660	—	54 / 4 / 28	86 / 86	43	4	0 / 1	Repaired · 2026-07-02
E-0d83a3c5c5e66085	GPT-5.5	Medium	Rated	47.9	1606	—	38 / 50 / 24	112 / 112	56	50	0 / 1	First try · 2026-07-02
E-3e859a6b27767128	GPT-5.5	XHigh	Rated	68.8	1784	—	62 / 16 / 24	102 / 102	46	16	0 / 1	First try · 2026-07-02
E-c42fbee03a029c83	GPT-5.5	None	Rated	28.0	1439	—	4 / 81 / 19	104 / 104	50	81	0 / 1	First try · 2026-07-02
E-0fb7de4e8156a229	GPT-5.6 Luna	XHigh	Rated	52.1	1645	—	55 / 6 / 31	92 / 92	45	6	0 / 1	First try · 2026-07-10
E-8feb37d0677409f2	GPT-5.6 Luna	None	Rated	27.6	1435	—	1 / 87 / 18	106 / 106	52	87	0 / 1	First try · 2026-07-10
E-e6198d88365e0492	GPT-5.6 Luna	Medium	Rated	27.0	1429	—	7 / 87 / 18	112 / 112	56	87	0 / 1	First try · 2026-07-10
E-0385f0602a8e29e2	GPT-5.6 Sol	Medium	Rated	67.8	1778	—	64 / 5 / 19	88 / 88	44	5	0 / 1	First try · 2026-07-10
E-3ae62f195160add3	GPT-5.6 Sol	XHigh	Rated	20.3	1379	—	22 / 12 / 50	84 / 84	42	12	0 / 1	First try · 2026-07-10
E-994624d0bc2e266d	GPT-5.6 Sol	None	Rated	39.6	1539	—	43 / 15 / 34	92 / 92	46	15	0 / 1	First try · 2026-07-10
E-44cace55a6126cdf	GPT-5.6 Terra	None	Rated	24.6	1412	—	3 / 72 / 23	98 / 100	49	72	2 / 1	First try · 2026-07-10
E-b061663dc342c859	GPT-5.6 Terra	XHigh	Rated	48.7	1615	—	51 / 15 / 32	98 / 98	46	15	0 / 1	Repaired · 2026-07-10
E-d004e78844cdd202	GPT-5.6 Terra	Medium	Rated	33.6	1486	—	21 / 53 / 34	108 / 108	54	53	0 / 1	First try · 2026-07-10
E-11d1ae7d9526f835	Ling 3.0 Flash	Baseline track (legacy evidence incomplete)	Rated	28.3	1435	—	0 / 136 / 16	152 / 156	59	136	0 / 1	First try · 2026-07-24
E-28bcc8394e411616	Ling 3.0 Flash	Baseline track (legacy evidence incomplete)	Rated	25.2	1409	—	5 / 126 / 21	152 / 152	63	126	0 / 1	Repaired · 2026-07-24
E-87d69837bf65e78b	LongCat 2.0	None	Rated	27.5	1434	—	1 / 99 / 10	110 / 110	52	99	0 / 1	First try · 2026-07-24
E-d724da56cbc06da7	LongCat 2.0	Enabled	Rated	10.8	1316	—	1 / 17 / 24	42 / 42	21	17	0 / 1	First try · 2026-07-24
E-df8e0fab4bf8bb33	LongCat 2.0	None	Rated	28.2	1440	—	7 / 93 / 12	112 / 112	53	93	0 / 1	First try · 2026-07-24
E-ef389910f6cc07cc	LongCat 2.0	Enabled	Rated	42.8	1585	—	17 / 15 / 10	42 / 42	21	15	0 / 1	First try · 2026-07-24
E-d169e7b29be70652	Minimax M3	Reasoning enabled	Rated	26.4	1434	—	7 / 47 / 16	70 / 70	35	47	0 / 1	Repaired · 2026-07-02
E-e67e41d4491d7ad3	Minimax M3	Reasoning disabled	Rated	37.8	1523	—	40 / 7 / 49	96 / 96	48	7	0 / 1	First try · 2026-07-02
E-ba85be2fa53925f5	Mistral Medium 3.5	None	Rated	23.9	1403	—	2 / 90 / 22	114 / 114	57	90	0 / 1	First try · 2026-07-02
E-251b5d53a5f89562	Kimi K2.7 Code	Reasoning enabled	Rated	60.2	1723	—	45 / 4 / 11	60 / 60	30	4	0 / 1	Repaired · 2026-07-02
E-151c4ee6a2d1838e	Kimi K3	High	Rated	23.6	1413	—	2 / 43 / 17	62 / 62	31	43	0 / 1	First try · 2026-07-24
E-3e1be56b9d966ded	Kimi K3	Low	Rated	71.0	1818	—	49 / 0 / 3	52 / 52	26	0	0 / 1	First try · 2026-07-24
E-506d972b5c69a00d	Nex N2 Pro	Reasoning disabled	Rated	27.1	1431	—	0 / 94 / 14	108 / 108	53	94	0 / 1	Repaired · 2026-07-11
E-92332f4d765b2297	Nex N2 Pro	Reasoning enabled	Rated	0.0	1214	—	4 / 9 / 49	62 / 62	31	9	0 / 1	Repaired · 2026-07-02
E-15cf0dede27b7e1b	Nemotron 3 Ultra 550B A55B	Medium	Rated	28.3	1441	—	9 / 72 / 27	108 / 108	54	72	0 / 1	Repaired · 2026-07-02
E-2e3c01d0103fc439	Nemotron 3 Ultra 550B A55B	High	Rated	17.3	1364	—	4 / 27 / 23	54 / 54	27	27	0 / 1	Repaired · 2026-07-11
E-8c24e8bcbe9b1228	Nemotron 3 Ultra 550B A55B	High	Rated	17.1	1362	—	4 / 27 / 23	54 / 54	27	27	0 / 1	First try · 2026-07-02
E-ada32b27ea6ffedd	Nemotron 3 Ultra 550B A55B	Reasoning disabled	Rated	28.6	1449	—	1 / 76 / 5	82 / 82	41	76	0 / 1	First try · 2026-07-02
E-2270b9df7d2b32cc	O3	High	Rated	62.2	1744	—	41 / 0 / 11	52 / 52	26	0	0 / 1	First try · 2026-07-03
E-335ae90fdc702bd6	O3	Low	Rated	28.3	1460	—	1 / 43 / 4	48 / 48	24	43	0 / 1	First try · 2026-07-21
E-35de956c8305ff90	O3	Medium	Rated	31.6	1466	—	29 / 63 / 32	124 / 124	62	63	0 / 1	First try · 2026-07-02
E-9fbb8e6c69f575f4	O3	High	Rated	14.9	1344	—	2 / 29 / 21	52 / 52	26	29	0 / 1	First try · 2026-07-03
E-afa6c09eebc859c4	O3	High	Rated	19.5	1383	—	4 / 27 / 21	52 / 52	26	27	0 / 1	First try · 2026-07-02
E-24a75273941e6ea3	GPT-OSS 120B	High	Rated	16.6	1358	—	3 / 29 / 22	54 / 54	27	29	0 / 1	Repaired · 2026-07-02
E-6e65dec497ff2de3	GPT-OSS 120B	Medium	Rated	29.0	1445	—	9 / 86 / 23	118 / 118	59	86	0 / 1	Repaired · 2026-07-02
E-f6e9da46c61ad315	GPT-OSS 120B	Low	Rated	20.2	1389	—	3 / 32 / 17	52 / 52	26	32	0 / 1	First try · 2026-07-21
E-0fab95afbec0dd98	Laguna S 2.1	Enabled	Rated	25.6	1440	—	3 / 32 / 9	44 / 44	22	32	0 / 1	First try · 2026-07-24
E-4030acdbccf3ca03	Laguna S 2.1	None	Rated	26.1	1422	—	3 / 96 / 13	112 / 112	53	96	0 / 1	Repaired · 2026-07-24
E-e90a3ce84847ba43	Laguna S 2.1	None	Rated	26.5	1425	—	3 / 93 / 16	112 / 112	53	93	0 / 1	First try · 2026-07-24
E-f72c72b8f264c57a	Laguna S 2.1	Enabled	Rated	25.4	1437	—	1 / 35 / 8	44 / 44	22	35	0 / 1	First try · 2026-07-24
E-64624689e7cbd439	Qwen3.7 Max	Reasoning enabled	Rated	25.5	1426	—	5 / 48 / 19	72 / 72	36	48	0 / 1	Repaired · 2026-07-02
E-a667eb7d15f7f43e	Qwen3.7 Max	Reasoning disabled	Rated	25.4	1416	—	4 / 74 / 30	108 / 108	53	74	0 / 1	First try · 2026-07-02
E-6c2a9942e92223c8	Qwen3.7 Plus	Reasoning enabled	Rated	26.0	1429	—	0 / 58 / 18	76 / 76	38	58	0 / 1	First try · 2026-07-02
E-8b265019ada47f24	Step 3.7 Flash	High	Rated	17.4	1365	—	1 / 32 / 21	54 / 54	27	32	0 / 1	Repaired · 2026-07-02
E-c38fe2712e69333b	Step 3.7 Flash	Low	Rated	19.3	1382	—	0 / 37 / 15	52 / 52	26	37	0 / 1	First try · 2026-07-21
E-56487337fad4192f	Hy3 Preview	None	Rated	27.8	1436	—	3 / 88 / 21	112 / 112	54	88	0 / 1	First try · 2026-07-02
E-81a5e5ef15f371dc	Hy3 Preview	High	Rated	28.4	1457	—	18 / 12 / 24	54 / 54	27	12	0 / 1	First try · 2026-07-02
E-68669040dc891a7d	Inkling	None	Rated	63.3	1735	—	68 / 7 / 37	112 / 112	54	7	0 / 1	Repaired · 2026-07-24
E-9f74dab09049a473	Inkling	Medium	Rated	27.4	1442	—	4 / 55 / 12	71 / 71	36	55	0 / 1	First try · 2026-07-24
E-d21921560d198b28	Inkling	Max	Rated	13.7	1333	—	2 / 24 / 28	54 / 54	27	24	0 / 1	Repaired · 2026-07-24
E-707dd709e358a173	Grok 4.5	High	Rated	68.6	1800	—	42 / 0 / 6	48 / 48	24	0	0 / 1	First try · 2026-07-24
E-73422318071a105c	Grok 4.5	Medium	Rated	80.5	1882	—	87 / 1 / 14	102 / 102	51	1	0 / 1	First try · 2026-07-24
E-b914d026c7631fcb	Grok 4.5	Low	Rated	65.8	1774	—	44 / 0 / 8	52 / 52	26	0	0 / 1	First try · 2026-07-24
E-3e2fe948d2bcebb0	Grok Build 0.1	Reasoning enabled	Rated	24.9	1421	—	5 / 50 / 15	70 / 70	35	50	0 / 1	Repaired · 2026-07-02
E-5f664f9580459829	MiMo-V2.5	High	Rated	26.6	1435	—	2 / 69 / 3	74 / 74	37	69	0 / 1	Repaired · 2026-07-02
E-650d06103e7fa176	MiMo-V2.5	Reasoning enabled	Rated	35.3	1508	—	15 / 42 / 15	72 / 72	36	42	0 / 1	Repaired · 2026-07-03
E-b5eb7da0f5021b69	MiMo-V2.5	Reasoning enabled	Rated	9.6	1297	—	1 / 25 / 32	58 / 58	29	25	0 / 1	Repaired · 2026-07-02
E-cabbf604f15eb575	MiMo-V2.5	Reasoning disabled	Rated	16.9	1347	—	2 / 58 / 34	94 / 94	47	58	0 / 1	First try · 2026-07-02
E-d51fce0298267f96	MiMo-V2.5	Reasoning disabled	Rated	26.2	1427	—	2 / 72 / 16	90 / 90	45	72	0 / 1	First try · 2026-07-01
E-bd1bb7ac29877b8f	MiMo-V2.5-Pro	Reasoning enabled	Rated	15.8	1348	—	2 / 37 / 23	62 / 62	31	37	0 / 1	Repaired · 2026-07-02
E-6a361d88d8c1fb48	GLM-5.2	Reasoning disabled	Rated	26.3	1431	—	3 / 62 / 13	78 / 78	39	62	0 / 1	First try · 2026-07-11
E-97efd9455394f6d7	GLM-5.2	Reasoning disabled	Rated	64.2	1754	—	50 / 0 / 18	68 / 68	34	0	0 / 1	Repaired · 2026-07-02
E-da1e9a6be31e371f	GLM-5.2	High	Rated	25.8	1428	—	1 / 62 / 11	74 / 74	37	62	0 / 1	Repaired · 2026-07-11