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

Game profile

Chess

Chess is an 8x8 tactical piece-movement game with asymmetric pieces, castling, en passant, promotion, check, checkmate, and automatic draw rules.

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

By model and setting

GB2-02: Chess 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: GB2-02: Chess

GB2-02: Chess - Reasoning Variants
Rank	Model	Reasoning	Score	Raw Elo	W / D / L	Uncertainty
1	GPT-5.6 Sol	XHigh	100.0	1806.9	60 / 15 / 11	9.9
2	Claude Opus 4.8	XHigh	82.1	1729.1	45 / 32 / 5	11.1
3	Claude Fable 5	XHigh	75.8	1701.6	41 / 37 / 4	11.1
4	Claude Fable 5	Medium	72.9	1690.5	37 / 30 / 9	13.2
5	Claude Opus 5	XHigh	72.0	1693.5	56 / 37 / 21	21.9
6	Claude Opus 5	None	66.2	1657.5	94 / 70 / 14	9.0
7	Claude Opus 5	Medium	63.7	1651.5	65 / 64 / 15	14.8
8	GPT-5.4	XHigh	57.2	1620.5	22 / 49 / 9	11.8
9	GPT-5.6 Terra	XHigh	48.4	1580.3	16 / 50 / 20	9.9
10	GPT-5.6 Sol	Medium	48.2	1582.2	27 / 38 / 11	13.2
11	GPT-5.5	Medium	47.5	1580.4	20 / 43 / 9	14.8
12	Grok 4.5	High	36.8	1551.9	21 / 34 / 19	37.9
13	GPT-5.6 Terra	None	31.5	1502.7	4 / 87 / 9	6.0
14	Grok 4.5	Medium	30.4	1499.1	13 / 67 / 16	7.0
15	MiMo-V2.5	High	30.2	1505.1	3 / 56 / 11	15.6
16	Inkling	None	30.0	1496.2	2 / 88 / 10	6.0
17	MiMo-V2.5-Pro	None	29.3	1499.0	5 / 64 / 7	13.2
18	Gemini 3.5 Flash	Medium	29.3	1495.3	10 / 70 / 10	8.7
19	Claude Opus 4.5	None	29.0	1494.0	5 / 74 / 11	8.7
20	DeepSeek V4 Flash	XHigh	28.4	1496.9	4 / 57 / 9	15.6
21	Claude Opus 4.5	Medium	28.1	1499.3	2 / 54 / 4	20.3
22	GPT-5.6 Sol	None	28.0	1495.2	5 / 56 / 9	15.6
23	Qwen3.7 Max	None	27.6	1491.6	8 / 62 / 6	13.2
24	Claude Sonnet 5	Medium	26.8	1487.9	1 / 71 / 4	13.2
25	GPT-5.6 Terra	Medium	26.5	1484.7	0 / 75 / 9	10.5
26	Step 3.7 Flash	Medium	26.3	1483.6	1 / 74 / 9	10.5
27	GPT-OSS 120B	Medium	26.0	1482.3	4 / 75 / 5	10.5
28	GPT-5.4 Nano	Medium	25.6	1482.1	0 / 75 / 3	12.5
29	GPT-5.4 Mini	Medium	25.6	1478.9	3 / 84 / 3	8.7
30	DeepSeek V4 Pro	None	25.4	1479.2	2 / 78 / 6	9.9
31	Claude Opus 4.5	Historical	25.2	1484.3	1 / 122 / 9	17.4
32	Laguna S 2.1	None	25.2	1474.4	3 / 97 / 4	5.0
33	GPT-5.5	None	24.8	1477.8	0 / 73 / 9	11.1
34	Gemini 3.1 Flash Lite	None	24.5	1482.8	1 / 59 / 2	19.2
35	GPT-5.6 Luna	None	24.4	1475.3	0 / 82 / 2	10.5
36	LongCat 2.0	None	24.3	1471.9	0 / 93 / 5	6.5
37	Qwen3.7 Plus	None	24.1	1472.4	0 / 90 / 0	8.7
38	Gemini 3.5 Flash Lite	Medium	23.7	1494.8	0 / 36 / 0	38.4
39	GPT-5.4 Nano	None	23.6	1471.4	4 / 154 / 14	9.9
40	Qwen3.7 Plus	Enabled	23.3	1489.1	1 / 81 / 4	33.5
41	DeepSeek V4 Flash	None	23.3	1471.2	1 / 78 / 3	11.1
42	MiMo-V2.5	Reasoning	23.3	1488.1	4 / 71 / 11	32.4
43	GPT-5.4	Medium	23.3	1471.5	4 / 68 / 8	11.8
44	Grok Build 0.1	Enabled	23.2	1485.7	3 / 86 / 3	30.0
45	GPT-5.4 Mini	None	23.1	1469.6	0 / 82 / 2	10.5
46	GPT-5.6 Luna	Medium	23.1	1473.6	0 / 64 / 6	15.6
47	GPT-5.6 Luna	XHigh	23.0	1469.1	3 / 71 / 10	10.5
48	GLM-5.2	Medium	22.9	1475.8	0 / 61 / 1	19.2
49	Claude Opus 4.8	None	22.8	1470.3	3 / 68 / 5	13.2
50	MiMo-V2.5	Reasoning	22.7	1474.2	0 / 63 / 1	18.3
51	GPT-5.4	None	22.6	1467.3	1 / 79 / 4	10.5
52	Ling 3.0 Flash	None	22.4	1459.7	1 / 110 / 7	2.1
53	Kimi K2.7 Code	Enabled	22.1	1473.9	4 / 90 / 22	21.3
54	Gemini 3.6 Flash	Medium	22.0	1464.2	1 / 80 / 5	9.9
55	Nemotron 3 Ultra 550B A55B	Medium	21.9	1463.3	1 / 82 / 5	9.2
56	Nex N2 Pro	None	21.9	1464.2	2 / 71 / 11	10.5
57	MiMo-V2.5	Medium	21.7	1482.4	5 / 149 / 10	34.0
58	GPT 4.1	None	21.7	1463.4	2 / 70 / 12	10.5
59	DeepSeek V4 Flash	Medium	21.2	1466.7	2 / 111 / 19	17.4
60	Qwen3.7 Max	Enabled	20.8	1472.8	3 / 82 / 13	27.0
61	Minimax M3	None	20.7	1462.4	0 / 69 / 3	14.8
62	Kimi K3	Max	20.7	1484.2	3 / 55 / 8	42.0
63	GLM-5.2	None	20.6	1465.3	1 / 117 / 8	18.8
64	Claude Opus 4.8	Medium	20.5	1459.9	1 / 72 / 5	12.5
65	Gemini 3.5 Flash Lite	High	20.2	1503.1	5 / 30 / 3	68.2
66	Kimi K3	Low	20.2	1476.8	2 / 74 / 6	35.5
67	Gemini 3.5 Flash Lite	Minimal	19.2	1480.7	1 / 114 / 7	45.6
68	Laguna S 2.1	Enabled	19.0	1490.2	0 / 101 / 1	58.9
69	Gemini 3.6 Flash	Minimal	18.7	1478.9	0 / 115 / 5	46.2
70	Hy3 Preview	None	18.6	1454.1	0 / 64 / 6	15.6
71	LongCat 2.0	Enabled	18.4	1491.3	1 / 42 / 1	63.3
72	Nemotron 3 Ultra 550B A55B	High	17.5	1470.8	2 / 112 / 16	42.7
73	Inkling	Max	16.7	1482.6	1 / 47 / 2	61.9
74	GPT 5	High	16.5	1462.5	2 / 57 / 15	37.9
75	Kimi K3	High	16.2	1502.6	4 / 22 / 6	78.1
76	Ling 3.0 Flash	Enabled	14.9	1466.9	2 / 44 / 8	51.9
77	Minimax M3	Enabled	13.6	1445.3	1 / 71 / 14	32.0
78	Grok 4.5	Low	13.5	1491.9	2 / 37 / 5	68.2
79	Claude Opus 4.5	High	11.2	1446.0	1 / 43 / 16	46.1
80	GPT-OSS 120B	High	10.9	1438.6	0 / 58 / 14	38.8
81	Hy3 Preview	High	9.4	1436.1	1 / 51 / 12	43.8

Underlying results

Individual player programs

Each row is one accepted player program for GB2-02: Chess. 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 94 player programs.

Player ID	Model	Reasoning	Status	Score	Elo	Confidence	W / D / L	Rated / attempted	Opponents	Faults / players	Generation
E-cd3608270e8c00fd	Claude Fable 5	Medium	Rated	72.9	1690	—	37 / 30 / 9	76 / 78	38	2 / 1	First try · 2026-07-02
E-f6a30e7d9986c9b8	Claude Fable 5	XHigh	Rated	75.8	1702	—	41 / 37 / 4	82 / 82	36	0 / 1	First try · 2026-07-03
E-03472a04778e9928	Claude Opus 4.5	Medium effort + 16,000 thinking tokens	Rated	28.1	1499	—	2 / 54 / 4	60 / 60	30	0 / 1	First try · —
E-0454dbb9530f84f7	Claude Opus 4.5	Legacy_shared_thinking_budget	Waiting	—	—	—	0 / 0 / 0	0 / 0	0	0 / 1	First try · 2026-07-02
E-16462f3d1f3a7b19	Claude Opus 4.5	Thinking field omitted	Rated	29.0	1494	—	5 / 74 / 11	90 / 90	45	0 / 1	First try · 2026-07-02
E-3cbd11fb314c75e1	Claude Opus 4.5	Legacy_shared_thinking_budget	Waiting	—	—	—	0 / 0 / 0	0 / 0	0	0 / 1	First try · 2026-07-02
E-63fde27ceab11930	Claude Opus 4.5	High effort + 32,000 thinking tokens	Limited data	8.5	1434	—	0 / 23 / 7	30 / 30	15	0 / 1	First try · —
E-a81bd03e764818f6	Claude Opus 4.8	XHigh	Rated	82.1	1729	—	45 / 32 / 5	82 / 82	35	0 / 1	First try · 2026-07-03
E-c142942f4138c871	Claude Opus 4.8	Thinking field omitted	Rated	22.8	1470	—	3 / 68 / 5	76 / 76	37	0 / 1	First try · 2026-07-02
E-ed71c4ecf219b609	Claude Opus 4.8	Medium	Rated	20.5	1460	—	1 / 72 / 5	78 / 78	39	0 / 1	First try · 2026-07-02
E-50b401cafe71e710	Claude Opus 5	Medium	Rated	64.1	1653	—	33 / 31 / 8	72 / 72	36	0 / 1	First try · 2026-07-25
E-51ddad48e10b006f	Claude Opus 5	Thinking disabled	Rated	69.3	1671	—	56 / 24 / 10	90 / 90	45	0 / 1	First try · 2026-07-25
E-6b45cf5aebf0c66e	Claude Opus 5	XHigh	Rated	59.0	1637	—	21 / 25 / 10	56 / 56	22	0 / 1	First try · 2026-07-25
E-772d1a710082ddb3	Claude Opus 5	Thinking disabled	Rated	63.0	1644	—	38 / 46 / 4	88 / 88	44	0 / 1	First try · 2026-07-25
E-8a5bf2e23121edf6	Claude Opus 5	Medium	Rated	63.3	1650	—	32 / 33 / 7	72 / 72	36	0 / 1	First try · 2026-07-25
E-fcdd98d74e80134a	Claude Opus 5	XHigh	Rated	85.0	1750	—	35 / 12 / 11	58 / 58	23	0 / 1	First try · 2026-07-25
E-a1a16bb5799cfdbe	Claude Sonnet 5	Medium	Rated	26.8	1488	—	1 / 71 / 4	76 / 76	38	0 / 1	First try · 2026-07-02
E-08e2baea96c43eb4	DeepSeek V4 Flash	High	Rated	16.1	1445	—	0 / 54 / 10	64 / 64	32	0 / 1	First try · 2026-07-02
E-12dcb25370550495	DeepSeek V4 Flash	XHigh	Rated	28.4	1497	—	4 / 57 / 9	70 / 70	35	0 / 1	Repaired · 2026-07-02
E-1e168b9e73c26073	DeepSeek V4 Flash	High	Rated	26.3	1489	—	2 / 57 / 9	68 / 68	34	0 / 1	Repaired · 2026-07-01
E-3358fbcda6ab6f4d	DeepSeek V4 Flash	Reasoning disabled	Rated	23.3	1471	—	1 / 78 / 3	82 / 82	41	0 / 1	First try · 2026-07-02
E-6c3b019c1b20a09b	DeepSeek V4 Pro	Reasoning disabled	Rated	25.4	1479	—	2 / 78 / 6	86 / 86	43	0 / 1	First try · 2026-07-02
E-20b3484be872df52	Gemini 3.1 Flash Lite	Reasoning disabled	Rated	24.5	1483	—	1 / 59 / 2	62 / 62	31	0 / 1	Repaired · 2026-07-02
E-ef7a835bdb46a90e	Gemini 3.5 Flash	Medium	Rated	29.3	1495	—	10 / 70 / 10	90 / 90	45	0 / 1	Repaired · 2026-07-02
E-1010911d64a09b68	Gemini 3.5 Flash Lite	Minimal	Limited data	17.7	1479	—	1 / 22 / 3	26 / 26	13	0 / 1	Repaired · 2026-07-24
E-423f6c31467b8943	Gemini 3.5 Flash Lite	High	Limited data	13.0	1469	—	1 / 16 / 3	20 / 20	10	0 / 1	First try · 2026-07-24
E-dbbc5835674b5f2c	Gemini 3.5 Flash Lite	Medium	Limited data	23.7	1495	—	0 / 36 / 0	36 / 36	18	0 / 1	First try · 2026-07-24
E-e65fdcb71f09a611	Gemini 3.5 Flash Lite	Minimal	Limited data	18.8	1479	—	0 / 29 / 1	30 / 30	15	0 / 1	Repaired · 2026-07-24
E-4492f6d65cd6280b	Gemini 3.6 Flash	Minimal	Limited data	19.0	1482	—	0 / 27 / 1	28 / 28	14	0 / 1	First try · 2026-07-24
E-62275b0c39dda32a	Gemini 3.6 Flash	Medium	Rated	22.0	1464	—	1 / 80 / 5	86 / 86	43	0 / 1	First try · 2026-07-24
E-9c8b43dc41bad760	Gemini 3.6 Flash	Minimal	Limited data	19.5	1485	—	0 / 27 / 1	28 / 28	14	0 / 1	Repaired · 2026-07-24
E-e4707b8e4c581ede	GPT 4.1	None	Rated	21.7	1463	—	2 / 70 / 12	84 / 84	42	0 / 1	Repaired · 2026-07-02
E-4f8f0a47f75ab6b7	GPT 5	Low	Waiting	—	—	—	0 / 0 / 0	0 / 0	0	0 / 1	First try · 2026-07-21
E-5bccb9b671ce5eae	GPT 5	High	Limited data	13.0	1451	—	2 / 22 / 8	32 / 32	16	0 / 1	First try · 2026-07-02
E-4aa582caf9d9f6da	GPT-5.4	XHigh	Rated	57.2	1621	—	22 / 49 / 9	80 / 80	35	0 / 1	First try · 2026-07-02
E-98ddce22d3eb5886	GPT-5.4	None	Rated	22.6	1467	—	1 / 79 / 4	84 / 84	41	0 / 1	First try · 2026-07-02
E-f4948a32cdd115a9	GPT-5.4	Medium	Rated	23.3	1471	—	4 / 68 / 8	80 / 80	40	0 / 1	First try · 2026-07-02
E-322cbb8be1559087	GPT-5.4 Mini	None	Rated	23.1	1470	—	0 / 82 / 2	84 / 84	41	0 / 1	First try · 2026-07-02
E-6724998b59176607	GPT-5.4 Mini	Medium	Rated	25.6	1479	—	3 / 84 / 3	90 / 90	45	0 / 1	First try · 2026-07-02
E-038a95fb13c8aa94	GPT-5.4 Nano	None	Rated	22.7	1467	—	0 / 79 / 7	86 / 86	43	0 / 1	Repaired · 2026-07-09
E-be95cc83ce87847c	GPT-5.4 Nano	None	Rated	24.6	1476	—	4 / 75 / 7	86 / 86	43	0 / 1	Repaired · 2026-07-02
E-d96eaa4f1d20c47b	GPT-5.4 Nano	Medium	Rated	25.6	1482	—	0 / 75 / 3	78 / 78	39	0 / 1	Repaired · 2026-07-02
E-51e935956fa76015	GPT-5.5	None	Rated	24.8	1478	—	0 / 73 / 9	82 / 82	41	0 / 1	First try · 2026-07-02
E-8460841e3919c568	GPT-5.5	Medium	Rated	47.5	1580	—	20 / 43 / 9	72 / 72	36	0 / 1	First try · 2026-07-02
E-a30e455ba172d80e	GPT-5.6 Luna	XHigh	Rated	23.0	1469	—	3 / 71 / 10	84 / 84	42	0 / 1	Repaired · 2026-07-10
E-ba4589e1cf2c827b	GPT-5.6 Luna	None	Rated	24.4	1475	—	0 / 82 / 2	84 / 84	42	0 / 1	First try · 2026-07-10
E-e2dda893ae4363f2	GPT-5.6 Luna	Medium	Rated	23.1	1474	—	0 / 64 / 6	70 / 70	35	0 / 1	First try · 2026-07-10
E-0420ca9039edc6fb	GPT-5.6 Sol	None	Rated	28.0	1495	—	5 / 56 / 9	70 / 70	35	0 / 1	First try · 2026-07-10
E-087d760c91df7f17	GPT-5.6 Sol	Medium	Rated	48.2	1582	—	27 / 38 / 11	76 / 76	38	0 / 1	Repaired · 2026-07-10
E-33dc9365cfacf9c0	GPT-5.6 Sol	XHigh	Rated	100.0	1807	—	60 / 15 / 11	86 / 86	37	0 / 1	First try · 2026-07-10
E-1b12482867c807c9	GPT-5.6 Terra	XHigh	Rated	48.4	1580	—	16 / 50 / 20	86 / 86	37	0 / 1	First try · 2026-07-10
E-82ad98d8d570daab	GPT-5.6 Terra	Medium	Rated	26.5	1485	—	0 / 75 / 9	84 / 84	42	0 / 1	Repaired · 2026-07-10
E-c6593bd789768bdb	GPT-5.6 Terra	None	Rated	31.5	1503	—	4 / 87 / 9	100 / 100	50	0 / 1	Repaired · 2026-07-10
E-129026c5e53b35ad	Ling 3.0 Flash	Enabled	Limited data	8.3	1445	—	0 / 18 / 4	22 / 22	11	0 / 1	Repaired · 2026-07-24
E-fc495094a55d2f94	Ling 3.0 Flash	Baseline track (legacy evidence incomplete)	Rated	22.4	1460	—	1 / 110 / 7	118 / 118	51	0 / 1	First try · 2026-07-24
E-a00d8e3eb7dd07cf	LongCat 2.0	Enabled	Limited data	16.4	1494	—	0 / 16 / 0	16 / 16	8	0 / 1	Repaired · 2026-07-24
E-a0c74818516a7f27	LongCat 2.0	None	Rated	24.3	1472	—	0 / 93 / 5	98 / 98	49	0 / 1	Repaired · 2026-07-24
E-1e46941293882535	Minimax M3	Reasoning disabled	Rated	20.7	1462	—	0 / 69 / 3	72 / 72	35	0 / 1	First try · 2026-07-02
E-cad87bcb23d33fef	Minimax M3	Reasoning enabled	Rated	9.5	1423	—	0 / 37 / 11	48 / 48	24	0 / 1	Repaired · 2026-07-02
E-85c8a9372a607001	Kimi K2.7 Code	Reasoning enabled	Rated	22.2	1474	—	2 / 49 / 7	58 / 58	29	0 / 1	Repaired · 2026-07-02
E-0c4144684fc36307	Kimi K3	High	Limited data	28.5	1530	—	4 / 16 / 4	24 / 24	12	0 / 1	First try · 2026-07-24
E-1beeecccf3f2c84f	Kimi K3	Max	Limited data	18.5	1476	—	2 / 22 / 8	32 / 32	16	0 / 1	Repaired · 2026-07-24
E-d3d3da42e99695b1	Kimi K3	Low	Rated	24.0	1485	—	2 / 47 / 3	52 / 52	26	0 / 1	First try · 2026-07-24
E-811f47e902ce0d21	Nex N2 Pro	Reasoning disabled	Rated	21.9	1464	—	2 / 71 / 11	84 / 84	41	0 / 1	Repaired · 2026-07-11
E-2404d10bab26a254	Nemotron 3 Ultra 550B A55B	High	Limited data	15.3	1461	—	0 / 26 / 6	32 / 32	16	0 / 1	Repaired · 2026-07-02
E-abd2cae3e3ff9bdb	Nemotron 3 Ultra 550B A55B	High	Limited data	11.4	1443	—	1 / 23 / 10	34 / 34	17	0 / 1	Repaired · 2026-07-11
E-bd70ebbd81fdbef0	Nemotron 3 Ultra 550B A55B	Medium	Rated	21.9	1463	—	1 / 82 / 5	88 / 88	44	0 / 1	Repaired · 2026-07-02
E-8f0c6569aa132f8e	GPT-OSS 120B	Medium	Rated	26.0	1482	—	4 / 75 / 5	84 / 84	42	0 / 1	First try · 2026-07-02
E-e5b4a3586049e1c9	GPT-OSS 120B	High	Limited data	4.1	1412	—	0 / 21 / 11	32 / 32	16	0 / 1	Repaired · 2026-07-02
E-7164ee63b9dd911a	Laguna S 2.1	Enabled	Limited data	15.8	1498	—	0 / 14 / 0	14 / 16	7	0 / 1	First try · 2026-07-24
E-ba56689188a301b2	Laguna S 2.1	Enabled	Limited data	17.4	1493	—	0 / 18 / 0	18 / 18	9	0 / 1	Repaired · 2026-07-24
E-d8c7a78cc7f666dc	Laguna S 2.1	None	Rated	25.2	1474	—	3 / 97 / 4	104 / 104	51	0 / 1	Repaired · 2026-07-24
E-5f64c2ae9860ba38	Qwen3.7 Max	Reasoning disabled	Rated	27.6	1492	—	8 / 62 / 6	76 / 76	38	0 / 1	First try · 2026-07-02
E-95265340f8562bfd	Qwen3.7 Max	Reasoning enabled	Rated	26.5	1498	—	3 / 44 / 1	48 / 48	24	0 / 1	Repaired · 2026-07-02
E-010dafcd7561851a	Qwen3.7 Plus	Reasoning disabled	Rated	24.1	1472	—	0 / 90 / 0	90 / 90	44	0 / 1	Repaired · 2026-07-02
E-57293d5b71f14882	Qwen3.7 Plus	Reasoning enabled	Rated	24.9	1488	—	1 / 49 / 4	54 / 54	27	0 / 1	Repaired · 2026-07-02
E-0ccea44addccfff0	Step 3.7 Flash	Medium	Rated	26.3	1484	—	1 / 74 / 9	84 / 84	42	0 / 1	Repaired · 2026-07-02
E-d910e47dd13c2c71	Hy3 Preview	None	Rated	18.6	1454	—	0 / 64 / 6	70 / 70	35	0 / 1	Repaired · 2026-07-02
E-fbf6af15f65f01d7	Hy3 Preview	High	Limited data	0.0	1399	—	0 / 17 / 11	28 / 30	14	2 / 1	Repaired · 2026-07-02
E-66a4f0abd099d8f1	Inkling	None	Rated	30.0	1496	—	2 / 88 / 10	100 / 100	49	0 / 1	Repaired · 2026-07-24
E-9468e854340a4e9b	Inkling	Max	Limited data	14.4	1491	—	1 / 13 / 0	14 / 16	7	0 / 1	Repaired · 2026-07-24
E-0576181f89efa7a7	Grok 4.5	High	Limited data	29.1	1522	—	8 / 16 / 8	32 / 32	16	0 / 1	Repaired · 2026-07-24
E-88ab68f664bd3ea0	Grok 4.5	Low	Limited data	22.3	1487	—	2 / 31 / 5	38 / 38	19	0 / 1	First try · 2026-07-24
E-da5ea0258e71b6ab	Grok 4.5	Medium	Rated	30.4	1499	—	13 / 67 / 16	96 / 96	48	0 / 1	First try · 2026-07-24
E-99592fa0331c6679	Grok Build 0.1	Reasoning enabled	Rated	23.6	1482	—	2 / 49 / 3	54 / 54	27	0 / 1	Repaired · 2026-07-02
E-39b08fe4c0318552	MiMo-V2.5	Reasoning disabled	Rated	22.7	1474	—	0 / 63 / 1	64 / 64	32	0 / 1	First try · 2026-07-01
E-5b213ae773e821cc	MiMo-V2.5	Reasoning enabled	Rated	24.9	1490	—	2 / 45 / 3	50 / 50	25	0 / 1	Repaired · 2026-07-02
E-9077f1e8e006290b	MiMo-V2.5	High	Rated	30.2	1505	—	3 / 56 / 11	70 / 70	35	0 / 1	Repaired · 2026-07-02
E-a5f372b0e5962ee5	MiMo-V2.5	Reasoning enabled	Rated	18.9	1466	—	0 / 43 / 3	46 / 46	23	0 / 1	Repaired · 2026-07-01
E-c37f25e181320efb	MiMo-V2.5	Reasoning enabled	Rated	23.6	1487	—	2 / 39 / 5	46 / 46	23	0 / 1	Repaired · 2026-07-02
E-b9f44937a1269e8d	MiMo-V2.5-Pro	Reasoning disabled	Rated	29.3	1499	—	5 / 64 / 7	76 / 76	38	0 / 1	First try · 2026-07-02
E-32435b01ac08ed41	GLM-5.2	High	Rated	22.9	1476	—	0 / 61 / 1	62 / 62	31	0 / 1	Repaired · 2026-07-11
E-4959351a96fd2b82	GLM-5.2	Reasoning disabled	Rated	17.8	1452	—	0 / 59 / 5	64 / 64	32	0 / 1	Repaired · 2026-07-02
E-925b589068dc7268	GLM-5.2	Reasoning disabled	Rated	23.4	1478	—	1 / 58 / 3	62 / 62	31	0 / 1	Repaired · 2026-07-11