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

Game profile

Xiangqi

Xiangqi is a 9x10 chess-family game with palaces, river restrictions, cannon screens, horse-leg and elephant-eye blocking, and flying-general legality.

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

By model and setting

GB2-04: Xiangqi 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: GB2-04: Xiangqi

GB2-04: Xiangqi - Reasoning Variants
Rank	Model	Reasoning	Score	Raw Elo	W / D / L	Uncertainty
1	Claude Fable 5	XHigh	100.0	1865.8	76 / 17 / 5	6.5
2	Claude Opus 5	XHigh	79.5	1757.1	116 / 25 / 19	11.8
3	GPT-5.6 Sol	XHigh	61.7	1656.1	46 / 42 / 6	7.5
4	GPT-5.4	XHigh	58.0	1635.6	36 / 34 / 24	7.5
5	Claude Opus 4.8	XHigh	55.7	1623.2	40 / 35 / 17	8.1
6	Kimi K3	Max	51.7	1625.6	38 / 23 / 13	38.4
7	Gemini 3.6 Flash	High	51.3	1620.1	40 / 22 / 18	34.3
8	LongCat 2.0	None	49.2	1586.4	22 / 54 / 22	6.5
9	Claude Fable 5	Medium	47.8	1583.0	30 / 33 / 17	11.8
10	GPT-5.4 Nano	Medium	45.3	1565.0	25 / 62 / 9	7.0
11	Claude Opus 5	Medium	45.0	1562.8	58 / 85 / 55	6.3
12	GPT-5.6 Terra	XHigh	44.5	1562.0	31 / 41 / 18	8.7
13	GPT-5.4 Mini	Medium	44.4	1561.8	20 / 61 / 9	8.7
14	Gemini 3.5 Flash	Medium	43.7	1556.1	27 / 56 / 15	6.5
15	Claude Opus 5	None	43.1	1552.5	63 / 79 / 56	6.3
16	Claude Opus 4.5	None	42.2	1552.9	14 / 48 / 14	13.2
17	MiMo-V2.5-Pro	Enabled	40.1	1555.3	22 / 50 / 22	30.5
18	GPT-5.6 Sol	Medium	39.3	1530.4	15 / 85 / 6	4.6
19	Step 3.7 Flash	Medium	37.9	1524.4	11 / 74 / 11	7.0
20	Kimi K3	Low	37.5	1546.7	20 / 43 / 11	37.9
21	GPT-5.6 Terra	None	37.3	1523.2	8 / 72 / 6	9.9
22	GPT-5.6 Terra	Medium	36.0	1514.0	13 / 74 / 9	7.0
23	GPT-5.4	Medium	35.3	1509.4	22 / 65 / 13	6.0
24	GPT-5.6 Luna	Medium	34.9	1508.2	6 / 85 / 5	7.0
25	GPT-5.6 Sol	None	34.5	1509.0	13 / 63 / 6	11.1
26	Gemini 3.1 Flash Lite	Medium	34.2	1505.6	8 / 76 / 4	9.2
27	Hy3 Preview	None	34.0	1509.6	15 / 42 / 13	15.6
28	Gemini 3.5 Flash Lite	Medium	33.7	1507.4	14 / 128 / 19	14.9
29	Ling 3.0 Flash	None	33.4	1496.1	7 / 101 / 6	2.9
30	GLM-5.2	None	32.7	1501.7	24 / 95 / 29	14.1
31	GPT 5	Medium	32.7	1495.7	17 / 60 / 19	7.0
32	MiMo-V2.5	High	32.5	1502.1	6 / 52 / 10	16.4
33	Nemotron 3 Ultra 550B A55B	None	32.3	1504.5	7 / 46 / 7	20.3
34	GLM-5.2	Medium	32.2	1501.1	7 / 49 / 10	17.3
35	Grok 4.5	Medium	31.9	1488.9	12 / 80 / 16	4.1
36	GPT-5.5	None	31.7	1490.9	12 / 64 / 18	7.5
37	Gemma 4 31B	None	31.5	1491.4	10 / 67 / 9	9.9
38	Claude Sonnet 5	Medium	31.5	1488.3	19 / 70 / 11	6.0
39	GPT-5.6 Luna	XHigh	31.5	1492.3	16 / 42 / 24	11.1
40	Claude Opus 4.8	None	31.3	1491.0	9 / 60 / 15	10.5
41	GPT-5.4	None	31.2	1489.5	11 / 69 / 8	9.2
42	GPT-5.5	Medium	31.1	1486.0	22 / 63 / 17	5.5
43	MiMo-V2.5	Reasoning	30.8	1492.2	21 / 110 / 9	15.7
44	Claude Opus 4.5	Medium	30.7	1483.7	11 / 76 / 16	5.3
45	Claude Opus 4.8	Medium	30.4	1481.5	5 / 87 / 12	5.0
46	GPT-5.6 Luna	None	30.0	1483.0	7 / 66 / 13	9.9
47	Gemini 3.6 Flash	Medium	29.9	1482.8	25 / 137 / 19	10.4
48	Claude Opus 4.5	Historical	29.6	1486.5	11 / 110 / 15	16.6
49	Minimax M3	Enabled	29.4	1500.5	7 / 76 / 7	35.4
50	Qwen3.7 Max	Enabled	28.9	1490.4	17 / 64 / 23	26.3
51	Nex N2 Pro	None	28.9	1475.1	5 / 81 / 8	7.5
52	Gemini 3.5 Flash Lite	Minimal	28.8	1514.9	17 / 64 / 16	57.5
53	DeepSeek V4 Flash	Medium	28.8	1482.6	4 / 53 / 9	17.3
54	Gemma 4 31B	Enabled	28.5	1492.9	9 / 73 / 6	32.2
55	Inkling	Medium	28.4	1492.5	3 / 35 / 4	32.5
56	Inkling	None	28.2	1473.1	22 / 122 / 32	9.3
57	Kimi K3	High	28.1	1511.8	9 / 39 / 8	58.9
58	GPT-5.4 Mini	None	27.8	1470.8	16 / 57 / 15	9.2
59	Qwen3.7 Plus	None	27.5	1474.1	5 / 57 / 8	15.6
60	GPT 4.1	None	27.4	1469.3	4 / 66 / 14	10.5
61	Grok Build 0.1	Enabled	27.3	1485.0	5 / 84 / 7	30.8
62	GPT-OSS 120B	Medium	27.1	1465.2	2 / 83 / 11	7.0
63	MiMo-V2.5	Reasoning	27.0	1478.9	4 / 90 / 12	25.0
64	DeepSeek V4 Pro	XHigh	26.7	1465.1	9 / 52 / 25	9.9
65	O3	Medium	26.5	1463.7	9 / 67 / 12	9.2
66	Gemini 3.6 Flash	Minimal	26.5	1494.3	10 / 102 / 12	47.6
67	North Mini Code	Enabled	25.8	1474.2	7 / 80 / 15	27.3
68	Grok 4.5	Low	25.6	1491.6	7 / 40 / 7	50.8
69	MiMo-V2.5	Medium	24.2	1467.5	12 / 127 / 45	30.2
70	Kimi K2.7 Code	Enabled	23.5	1461.4	8 / 79 / 15	27.3
71	Inkling	Max	23.4	1493.9	15 / 27 / 12	65.4
72	GPT-OSS 120B	High	22.7	1465.3	14 / 39 / 23	37.6
73	GPT 5	High	22.6	1457.9	7 / 66 / 19	29.2
74	Gemini 3.1 Flash Lite	High	21.8	1455.4	6 / 60 / 20	31.8
75	Gemini 3.5 Flash Lite	High	21.2	1475.7	18 / 60 / 32	59.4
76	Ling 3.0 Flash	Enabled	20.9	1449.7	6 / 70 / 14	30.3
77	Nemotron 3 Ultra 550B A55B	High	20.7	1449.5	6 / 61 / 19	31.8
78	Laguna S 2.1	Enabled	20.3	1450.4	6 / 50 / 22	35.3
79	Hy3 Preview	High	19.4	1443.4	7 / 58 / 19	32.7
80	Gemini 3.5 Flash	High	18.8	1438.6	21 / 30 / 37	30.8
81	Gemini 3.6 Flash	High	18.7	1450.3	16 / 18 / 28	46.3
82	Grok 4.5	High	17.7	1436.7	12 / 37 / 27	36.4
83	LongCat 2.0	Enabled	17.5	1448.0	4 / 45 / 17	51.9
84	GPT-5.5	XHigh	15.1	1401.9	6 / 45 / 33	10.5
85	GPT-OSS 120B	Low	11.8	1420.1	4 / 26 / 22	55.9
86	DeepSeek V4 Flash	None	9.9	1376.1	4 / 44 / 26	14.0
87	LongCat 2.0	Enabled	9.9	1409.8	5 / 24 / 19	56.5
88	Claude Opus 4.5	High	7.7	1383.5	6 / 29 / 37	38.8

Underlying results

Individual player programs

Each row is one accepted player program for GB2-04: Xiangqi. 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 102 player programs.

Player ID	Model	Reasoning	Status	Score	Elo	Confidence	W / D / L	Rated / attempted	Opponents	Faults / players	Generation
E-0ca15b39b465b370	Claude Fable 5	XHigh	Rated	100.0	1866	—	76 / 17 / 5	98 / 98	44	0 / 1	First try · 2026-07-03
E-eb1f17ce19beffd0	Claude Fable 5	Medium	Rated	47.8	1583	—	30 / 33 / 17	80 / 80	40	0 / 1	First try · 2026-07-02
E-8c9e611d78967342	Claude Opus 4.5	Legacy_shared_thinking_budget	Waiting	—	—	—	0 / 0 / 0	0 / 0	0	0 / 1	First try · 2026-07-02
E-9a77e43e752532c8	Claude Opus 4.5	Thinking field omitted	Rated	42.2	1553	—	14 / 48 / 14	76 / 76	38	0 / 1	First try · 2026-07-02
E-cbae2963ded72d76	Claude Opus 4.5	Medium effort + 16,000 thinking tokens	Rated	30.7	1484	—	11 / 76 / 16	103 / 104	52	0 / 1	First try · —
E-e3449ff084425b16	Claude Opus 4.5	Legacy_shared_thinking_budget	Waiting	—	—	—	0 / 0 / 0	0 / 0	0	0 / 1	First try · 2026-07-02
E-f40463f635c43598	Claude Opus 4.5	High effort + 32,000 thinking tokens	Rated	0.0	1338	—	1 / 17 / 22	40 / 40	20	0 / 1	First try · —
E-6344242dae68be1b	Claude Opus 4.8	XHigh	Rated	55.7	1623	—	40 / 35 / 17	92 / 92	41	0 / 1	First try · 2026-07-03
E-688a139ef8557587	Claude Opus 4.8	Thinking field omitted	Rated	31.3	1491	—	9 / 60 / 15	84 / 84	41	0 / 1	First try · 2026-07-02
E-caf91ab5b69b1e64	Claude Opus 4.8	Medium	Rated	30.4	1482	—	5 / 87 / 12	104 / 104	52	0 / 1	First try · 2026-07-02
E-048d3dcf802043b4	Claude Opus 5	Medium	Rated	44.0	1558	—	17 / 52 / 29	98 / 98	49	0 / 1	First try · 2026-07-25
E-4c98514bdb0eaf10	Claude Opus 5	XHigh	Rated	68.0	1694	—	55 / 10 / 13	78 / 78	35	0 / 1	First try · 2026-07-25
E-72e9307528761b35	Claude Opus 5	Thinking disabled	Rated	34.4	1505	—	17 / 54 / 27	98 / 98	49	0 / 1	First try · 2026-07-25
E-9e7782014171d35f	Claude Opus 5	Thinking disabled	Rated	51.8	1600	—	46 / 25 / 29	100 / 100	50	0 / 1	First try · 2026-07-25
E-a02883202d334eec	Claude Opus 5	XHigh	Rated	91.0	1820	—	61 / 15 / 6	82 / 82	36	0 / 1	First try · 2026-07-25
E-d0f0a2b1c4bbddae	Claude Opus 5	Medium	Rated	45.9	1568	—	41 / 33 / 26	100 / 100	50	0 / 1	First try · 2026-07-25
E-b1fc5b99a5deb881	Claude Sonnet 5	Medium	Rated	31.5	1488	—	19 / 70 / 11	100 / 100	50	0 / 1	Repaired · 2026-07-02
E-1460cf3cd86be35c	North Mini Code	Enabled	Rated	26.3	1470	—	3 / 50 / 11	64 / 64	32	0 / 1	Repaired · 2026-07-02
E-5d143d6301429619	DeepSeek V4 Flash	High	Rated	28.8	1483	—	4 / 53 / 9	66 / 66	33	0 / 1	First try · 2026-07-01
E-81bc9a578754f220	DeepSeek V4 Flash	Reasoning disabled	Rated	9.9	1376	—	4 / 44 / 26	74 / 74	37	0 / 1	First try · 2026-07-02
E-38bc194a470fbf62	DeepSeek V4 Pro	XHigh	Rated	26.7	1465	—	9 / 52 / 25	86 / 86	43	0 / 1	Repaired · 2026-07-02
E-2be6f5c895691cb3	Gemini 3.1 Flash Lite	High	Rated	12.8	1404	—	3 / 28 / 15	46 / 46	23	0 / 1	Repaired · 2026-07-02
E-860c31323fa5eda7	Gemini 3.1 Flash Lite	Medium	Rated	34.2	1506	—	8 / 76 / 4	88 / 90	44	2 / 1	Repaired · 2026-07-02
E-32cfa6c9dfb1d16f	Gemini 3.5 Flash	Medium	Rated	43.7	1556	—	27 / 56 / 15	98 / 98	49	0 / 1	Repaired · 2026-07-02
E-33e6ff93f425b731	Gemini 3.5 Flash	Low	Waiting	—	—	—	0 / 0 / 0	0 / 0	0	0 / 1	First try · 2026-07-21
E-8e95359e4cbd1851	Gemini 3.5 Flash	High	Rated	14.9	1416	—	11 / 10 / 25	46 / 46	23	0 / 1	Repaired · 2026-07-02
E-39ebef34ae0ea1cb	Gemini 3.5 Flash Lite	High	Rated	13.0	1409	—	4 / 20 / 16	40 / 40	20	0 / 1	First try · 2026-07-24
E-5c270e2afa7b70f5	Gemini 3.5 Flash Lite	Medium	Rated	34.7	1504	—	10 / 86 / 15	111 / 114	56	0 / 1	First try · 2026-07-24
E-6098de52ddfabfb1	Gemini 3.5 Flash Lite	Medium	Rated	32.7	1511	—	4 / 42 / 4	50 / 51	26	0 / 1	First try · 2026-07-24
E-6a79049fd9ab6f5d	Gemini 3.5 Flash Lite	Minimal	Limited data	29.8	1527	—	4 / 14 / 2	20 / 20	10	0 / 1	First try · 2026-07-24
E-953992515ec1424d	Gemini 3.5 Flash Lite	High	Rated	31.7	1511	—	10 / 21 / 11	42 / 42	21	0 / 1	First try · 2026-07-24
E-b05b0185d0e8dc2a	Gemini 3.5 Flash Lite	Minimal	Limited data	23.0	1494	—	4 / 10 / 4	18 / 18	9	0 / 1	Repaired · 2026-07-24
E-0b528ba96380a3b5	Gemini 3.6 Flash	Minimal	Limited data	25.1	1501	—	2 / 17 / 1	20 / 20	10	0 / 1	First try · 2026-07-24
E-846809faa1345207	Gemini 3.6 Flash	Minimal	Limited data	20.9	1470	—	1 / 19 / 4	24 / 24	12	0 / 1	Repaired · 2026-07-24
E-a5a73c81dfcf4540	Gemini 3.6 Flash	High	Limited data	8.2	1384	—	6 / 11 / 21	38 / 38	19	0 / 1	First try · 2026-07-24
E-ccfb6c993d1622b0	Gemini 3.6 Flash	High	Rated	43.9	1579	—	19 / 7 / 14	40 / 40	20	0 / 1	Repaired · 2026-07-24
E-cefb1dec9ce36375	Gemini 3.6 Flash	Medium	Rated	25.4	1465	—	5 / 51 / 7	63 / 63	32	0 / 1	First try · 2026-07-24
E-d109ab12db58a65f	Gemini 3.6 Flash	Medium	Rated	34.3	1501	—	20 / 86 / 12	118 / 118	59	0 / 1	First try · 2026-07-24
E-62ca2464f2212fc9	Gemma 4 31B	Reasoning enabled	Rated	32.7	1509	—	6 / 44 / 4	54 / 56	27	2 / 1	Repaired · 2026-07-02
E-ec0cf4b37c805eee	Gemma 4 31B	Reasoning disabled	Rated	31.5	1491	—	10 / 67 / 9	86 / 86	42	0 / 1	First try · 2026-07-02
E-ecb06954153be8d5	GPT 4.1	None	Rated	27.4	1469	—	4 / 66 / 14	84 / 84	42	0 / 1	First try · 2026-07-02
E-6f1aae863396df76	GPT 5	Medium	Rated	32.7	1496	—	17 / 60 / 19	96 / 96	48	0 / 1	First try · 2026-07-02
E-7e3da77777a95e31	GPT 5	High	Rated	16.3	1423	—	4 / 27 / 15	46 / 46	23	0 / 1	Repaired · 2026-07-02
E-0b4132559ee98caf	GPT-5.4	Medium	Rated	35.3	1509	—	22 / 65 / 13	100 / 100	50	0 / 1	First try · 2026-07-02
E-8d62bf1b340a70dc	GPT-5.4	None	Rated	31.2	1490	—	11 / 69 / 8	88 / 88	43	0 / 1	First try · 2026-07-02
E-9279285adff8ed29	GPT-5.4	XHigh	Rated	58.0	1636	—	36 / 34 / 24	94 / 94	42	0 / 1	First try · 2026-07-02
E-0880cdf1a43cb90c	GPT-5.4 Mini	None	Rated	27.8	1471	—	16 / 57 / 15	88 / 88	43	0 / 1	First try · 2026-07-02
E-74f5bcc8ad3796a5	GPT-5.4 Mini	Medium	Rated	44.4	1562	—	20 / 61 / 9	90 / 90	45	0 / 1	First try · 2026-07-02
E-a32cb67d48c62b3b	GPT-5.4 Nano	Medium	Rated	45.3	1565	—	25 / 62 / 9	96 / 96	48	0 / 1	Repaired · 2026-07-09
E-64bf5daf186f8119	GPT-5.5	XHigh	Rated	15.1	1402	—	6 / 45 / 33	84 / 84	41	0 / 1	First try · 2026-07-02
E-9e7bdad81107b7e4	GPT-5.5	Medium	Rated	31.1	1486	—	22 / 63 / 17	102 / 102	51	0 / 1	First try · 2026-07-02
E-ba1aa87056709e9a	GPT-5.5	None	Rated	31.7	1491	—	12 / 64 / 18	94 / 94	46	0 / 1	First try · 2026-07-02
E-5389e160269f5ceb	GPT-5.6 Luna	Medium	Rated	34.9	1508	—	6 / 85 / 5	96 / 96	48	0 / 1	First try · 2026-07-10
E-71a01107bf3f9fc1	GPT-5.6 Luna	None	Rated	30.0	1483	—	7 / 66 / 13	86 / 86	42	0 / 1	First try · 2026-07-10
E-e348813cda8b38b7	GPT-5.6 Luna	XHigh	Rated	31.5	1492	—	16 / 42 / 24	82 / 82	40	0 / 1	First try · 2026-07-10
E-270a233119b6cc62	GPT-5.6 Sol	XHigh	Rated	61.7	1656	—	46 / 42 / 6	94 / 94	43	0 / 1	First try · 2026-07-10
E-c81bf4d15f3d48f1	GPT-5.6 Sol	Medium	Rated	39.3	1530	—	15 / 85 / 6	106 / 106	53	0 / 1	First try · 2026-07-10
E-f0b7195272d6417e	GPT-5.6 Sol	None	Rated	34.5	1509	—	13 / 63 / 6	82 / 82	41	0 / 1	First try · 2026-07-10
E-50ee0aadbc66fe0e	GPT-5.6 Terra	None	Rated	37.3	1523	—	8 / 72 / 6	86 / 86	43	0 / 1	First try · 2026-07-10
E-89c18d144e85d89f	GPT-5.6 Terra	Medium	Rated	36.0	1514	—	13 / 74 / 9	96 / 96	48	0 / 1	First try · 2026-07-10
E-b85c80e7475ef9ec	GPT-5.6 Terra	XHigh	Rated	44.5	1562	—	31 / 41 / 18	90 / 90	43	0 / 1	First try · 2026-07-10
E-20e94e7276184071	Ling 3.0 Flash	Enabled	Rated	17.9	1430	—	4 / 36 / 10	50 / 50	25	0 / 1	Repaired · 2026-07-24
E-f38039bb8cc277a1	Ling 3.0 Flash	Baseline track (legacy evidence incomplete)	Rated	33.4	1496	—	7 / 101 / 6	114 / 114	47	0 / 1	First try · 2026-07-24
E-4ccf296e55b59be3	LongCat 2.0	Enabled	Limited data	9.6	1411	—	1 / 13 / 8	22 / 24	12	2 / 1	Repaired · 2026-07-24
E-9c9e87bb30b3cb99	LongCat 2.0	Enabled	Rated	14.8	1412	—	2 / 35 / 13	50 / 50	25	0 / 1	First try · 2026-07-24
E-9e1d4bf411e97fa6	LongCat 2.0	None	Rated	49.2	1586	—	22 / 54 / 22	98 / 98	49	0 / 1	First try · 2026-07-24
E-c60620c3c72a6064	Minimax M3	Reasoning enabled	Rated	31.2	1496	—	6 / 51 / 7	64 / 64	32	0 / 1	Repaired · 2026-07-02
E-eb97811a38950c20	Kimi K2.7 Code	Reasoning enabled	Rated	28.5	1482	—	5 / 52 / 7	64 / 64	32	0 / 1	Repaired · 2026-07-02
E-3c06949f23d4a77f	Kimi K3	Low	Limited data	39.5	1562	—	11 / 17 / 4	32 / 32	16	0 / 1	Repaired · 2026-07-24
E-601725df2c678708	Kimi K3	Max	Rated	43.4	1574	—	19 / 16 / 9	44 / 44	22	0 / 1	Repaired · 2026-07-24
E-7c724729d138057b	Kimi K3	High	Rated	36.1	1535	—	7 / 30 / 5	42 / 46	21	0 / 1	First try · 2026-07-24
E-6f4b3b55e4ec7cf5	Nex N2 Pro	Reasoning disabled	Rated	28.9	1475	—	5 / 81 / 8	94 / 94	46	0 / 1	Repaired · 2026-07-11
E-958dea26b779a042	Nemotron 3 Ultra 550B A55B	High	Rated	15.1	1417	—	4 / 27 / 15	46 / 46	23	0 / 1	Repaired · 2026-07-11
E-f36b99b3d76fbb35	Nemotron 3 Ultra 550B A55B	Reasoning disabled	Rated	32.3	1504	—	7 / 46 / 7	60 / 60	30	0 / 1	First try · 2026-07-02
E-7e92e17a121661f4	O3	Medium	Rated	26.5	1464	—	9 / 67 / 12	88 / 88	44	0 / 1	First try · 2026-07-02
E-3a27113d21c73b01	GPT-OSS 120B	High	Rated	14.6	1414	—	6 / 22 / 18	46 / 46	23	0 / 1	Repaired · 2026-07-02
E-f1288f2abfdbbfe4	GPT-OSS 120B	Medium	Rated	27.1	1465	—	2 / 83 / 11	96 / 96	48	0 / 1	Repaired · 2026-07-02
E-f6de1ce39e48807c	GPT-OSS 120B	Low	Limited data	9.5	1395	—	2 / 18 / 14	34 / 34	17	0 / 1	Repaired · 2026-07-21
E-e996fd38983e3b7f	Laguna S 2.1	Enabled	Rated	27.3	1488	—	4 / 27 / 9	40 / 40	20	0 / 1	Repaired · 2026-07-24
E-ea08328e287de1ad	Qwen3.7 Max	Reasoning enabled	Rated	28.7	1483	—	10 / 38 / 16	64 / 64	32	0 / 1	First try · 2026-07-02
E-84b9a07f75f324e2	Qwen3.7 Plus	Reasoning disabled	Rated	27.5	1474	—	5 / 57 / 8	70 / 70	34	0 / 1	First try · 2026-07-02
E-25e56c6bfae33c62	Step 3.7 Flash	Medium	Rated	37.9	1524	—	11 / 74 / 11	96 / 96	48	0 / 1	Repaired · 2026-07-02
E-3fd10f7865cc280e	Hy3 Preview	None	Rated	34.0	1510	—	15 / 42 / 13	70 / 70	35	0 / 1	Repaired · 2026-07-02
E-51c104b34ef2a244	Hy3 Preview	High	Rated	19.5	1441	—	6 / 26 / 14	46 / 46	23	0 / 1	First try · 2026-07-02
E-646ff33c7bab8b13	Inkling	None	Rated	24.0	1450	—	18 / 47 / 21	86 / 86	42	0 / 1	First try · 2026-07-24
E-ddc16fa197bfc7c5	Inkling	None	Rated	32.5	1496	—	4 / 75 / 11	90 / 90	44	0 / 1	First try · 2026-07-24
E-f130161523da1e6b	Inkling	Max	Rated	29.0	1494	—	14 / 19 / 11	44 / 44	22	0 / 1	First try · 2026-07-24
E-fce01db31ecf26d2	Inkling	Medium	Rated	28.4	1493	—	3 / 35 / 4	42 / 42	21	0 / 1	First try · 2026-07-24
E-07caaa12175b0b3c	Grok 4.5	High	Rated	16.5	1429	—	7 / 17 / 16	40 / 40	20	0 / 1	First try · 2026-07-24
E-5a4033db1131bf1d	Grok 4.5	Low	Limited data	24.9	1487	—	3 / 22 / 3	28 / 28	14	0 / 1	First try · 2026-07-24
E-ba6a8e6d7fc9a48d	Grok 4.5	Medium	Rated	31.9	1489	—	12 / 80 / 16	108 / 108	54	0 / 1	First try · 2026-07-24
E-85934b32572399da	Grok Build 0.1	Reasoning enabled	Rated	27.1	1474	—	3 / 56 / 5	64 / 64	32	0 / 1	Repaired · 2026-07-02
E-00e6914e513b1656	MiMo-V2.5	Reasoning enabled	Rated	28.3	1485	—	3 / 38 / 13	54 / 54	27	0 / 1	Repaired · 2026-07-02
E-23e877112cb95491	MiMo-V2.5	Reasoning enabled	Rated	20.0	1439	—	1 / 37 / 16	54 / 54	27	0 / 1	Repaired · 2026-07-01
E-2f7e15b8aa123825	MiMo-V2.5	Reasoning enabled	Rated	25.6	1467	—	3 / 50 / 9	62 / 62	31	0 / 1	Repaired · 2026-07-02
E-7ad356726cce2b22	MiMo-V2.5	Reasoning disabled	Rated	34.2	1510	—	18 / 52 / 4	74 / 74	37	0 / 1	Repaired · 2026-07-01
E-d58c55e107783a21	MiMo-V2.5	Reasoning disabled	Rated	27.4	1475	—	3 / 58 / 5	66 / 66	33	0 / 1	Repaired · 2026-07-02
E-f8929b12716a2221	MiMo-V2.5	High	Rated	32.5	1502	—	6 / 52 / 10	68 / 68	34	0 / 1	Repaired · 2026-07-02
E-ffdebde8a72ed049	MiMo-V2.5-Pro	Reasoning enabled	Rated	42.2	1558	—	15 / 36 / 9	60 / 60	30	0 / 1	Repaired · 2026-07-02
E-1d5f5ff0402ff944	GLM-5.2	Reasoning disabled	Rated	37.8	1531	—	9 / 49 / 10	68 / 68	34	0 / 1	Repaired · 2026-07-02
E-912f31ad14c4bf0a	GLM-5.2	High	Rated	32.2	1501	—	7 / 49 / 10	66 / 66	33	0 / 1	Repaired · 2026-07-11
E-f776c26a98306f5d	GLM-5.2	Reasoning disabled	Rated	27.7	1472	—	15 / 46 / 19	80 / 80	40	0 / 1	First try · 2026-07-11