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

Game profile

Hex

Hex is a connection game on a hexagonal grid where players race to join opposite board edges, with a swap option after the first move.

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

By model and setting

GB2-05: Hex 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: GB2-05: Hex

GB2-05: Hex - Reasoning Variants
Rank	Model	Reasoning	Score	Raw Elo	W / D / L	Uncertainty
1	GPT-5.4	XHigh	92.5	2032.6	84 / 0 / 8	8.1
2	Claude Fable 5	XHigh	90.3	2007.6	82 / 0 / 16	6.5
3	Claude Opus 5	None	86.5	1965.1	206 / 0 / 24	2.7
4	Claude Opus 5	XHigh	85.2	1962.0	114 / 0 / 22	16.4
5	Claude Opus 5	Medium	82.1	1918.5	194 / 0 / 28	3.5
6	GPT-5.5	XHigh	81.4	1913.8	76 / 0 / 20	7.0
7	DeepSeek V4 Pro	XHigh	71.1	1805.1	61 / 0 / 35	7.0
8	Gemini 3.6 Flash	Medium	69.9	1798.5	105 / 0 / 39	14.8
9	GPT-5.4	None	68.4	1777.6	65 / 0 / 25	8.7
10	GPT-5.5	Medium	64.4	1734.0	66 / 0 / 30	7.0
11	GPT-5.6 Sol	XHigh	63.9	1729.2	59 / 0 / 33	8.1
12	Claude Fable 5	Medium	58.9	1673.6	64 / 0 / 42	4.6
13	GPT-5.6 Sol	Medium	58.6	1672.1	61 / 0 / 37	6.5
14	Grok 4.5	Medium	58.0	1662.8	70 / 0 / 46	2.5
15	GPT-5.6 Sol	None	57.7	1662.7	59 / 0 / 39	6.5
16	GPT-5.6 Terra	XHigh	56.4	1650.0	52 / 0 / 42	7.5
17	MiMo-V2.5	Reasoning	55.7	1644.4	52 / 0 / 34	9.9
18	GPT-5.6 Luna	XHigh	53.7	1618.2	50 / 0 / 56	4.6
19	Kimi K3	Low	53.1	1631.6	61 / 0 / 33	28.7
20	Claude Opus 4.5	Historical	53.0	1616.4	88 / 0 / 78	10.8
21	Laguna S 2.1	None	52.6	1609.0	122 / 0 / 70	7.0
22	GPT-5.6 Terra	Medium	52.4	1604.4	64 / 0 / 44	4.1
23	GPT 5	Medium	52.1	1602.5	50 / 0 / 52	5.5
24	GPT 5	High	52.1	1619.4	51 / 0 / 47	27.0
25	GPT-5.6 Luna	Medium	52.0	1599.0	57 / 0 / 59	2.5
26	Grok Build 0.1	Enabled	51.8	1611.8	64 / 0 / 58	20.8
27	Gemini 3.6 Flash	High	51.6	1640.8	71 / 0 / 25	60.0
28	Nemotron 3 Ultra 550B A55B	None	51.3	1597.7	53 / 0 / 33	9.9
29	Claude Sonnet 5	Medium	51.2	1592.6	66 / 0 / 38	5.0
30	Claude Opus 4.5	None	51.2	1592.2	66 / 0 / 38	5.0
31	Kimi K2.7 Code	Enabled	50.5	1601.2	57 / 0 / 51	24.5
32	GPT-5.6 Terra	None	49.5	1578.2	53 / 0 / 35	9.2
33	GPT-5.4 Mini	Medium	49.2	1568.9	72 / 0 / 48	1.7
34	GLM-5.2	Medium	49.1	1575.1	42 / 0 / 40	11.1
35	Grok 4.5	High	49.1	1613.5	30 / 0 / 20	59.1
36	Qwen3.7 Plus	Enabled	48.8	1579.9	60 / 0 / 64	21.3
37	LongCat 2.0	Enabled	48.2	1582.6	54 / 0 / 32	32.8
38	Gemini 3.6 Flash	Minimal	48.1	1587.4	92 / 0 / 60	39.5
39	DeepSeek V4 Flash	XHigh	48.0	1559.8	52 / 0 / 44	7.0
40	Gemini 3.5 Flash	Medium	47.3	1549.9	58 / 0 / 54	3.3
41	Kimi K3	High	47.3	1574.5	54 / 0 / 32	34.3
42	GPT-5.5	None	47.2	1553.3	52 / 0 / 38	8.7
43	O3	Medium	47.0	1546.9	64 / 0 / 48	3.3
44	GPT-5.4 Nano	Medium	47.0	1548.7	112 / 0 / 94	5.5
45	Claude Opus 4.8	Medium	46.7	1542.3	65 / 0 / 55	1.7
46	Gemma 4 31B	Enabled	45.9	1549.7	65 / 0 / 57	21.6
47	Claude Opus 4.8	XHigh	45.7	1532.5	53 / 0 / 63	2.5
48	Qwen3.7 Max	Enabled	45.4	1546.0	59 / 0 / 61	23.7
49	Qwen3.7 Max	None	44.9	1525.4	52 / 0 / 52	5.0
50	Hy3 Preview	High	44.8	1543.0	46 / 0 / 48	28.4
51	GLM-5.2	None	44.6	1528.0	80 / 0 / 82	11.5
52	North Mini Code	Enabled	43.6	1525.0	72 / 0 / 54	21.0
53	Qwen3.7 Plus	None	42.8	1504.7	48 / 0 / 52	6.0
54	Claude Opus 4.5	High	42.8	1519.2	56 / 0 / 48	25.0
55	Nex N2 Pro	None	42.5	1500.9	52 / 0 / 52	5.0
56	Step 3.7 Flash	Medium	41.8	1490.9	52 / 0 / 64	2.5
57	Claude Opus 4.5	Medium	41.6	1490.8	60 / 0 / 46	4.6
58	Gemini 3.5 Flash	High	41.2	1504.9	43 / 0 / 53	27.7
59	GPT-5.4	Medium	40.3	1475.0	50 / 0 / 68	2.1
60	O3	High	40.2	1511.1	145 / 0 / 123	48.0
61	Grok 4.5	Low	40.1	1507.8	33 / 0 / 35	46.5
62	Minimax M3	None	39.7	1469.2	54 / 0 / 58	3.3
63	GPT-OSS 120B	Medium	38.4	1455.3	47 / 0 / 67	2.9
64	MiMo-V2.5-Pro	None	37.6	1450.3	50 / 0 / 46	7.0
65	Step 3.7 Flash	High	37.5	1463.1	54 / 0 / 50	25.0
66	DeepSeek V4 Pro	None	35.8	1431.2	46 / 0 / 50	7.0
67	DeepSeek V4 Flash	None	35.5	1424.9	48 / 0 / 64	3.3
68	Claude Opus 4.8	None	35.3	1426.0	42 / 0 / 54	7.0
69	Nemotron 3 Ultra 550B A55B	High	34.8	1435.4	88 / 0 / 114	26.2
70	MiMo-V2.5	Reasoning	33.3	1413.8	61 / 0 / 67	18.5
71	Mistral Medium 3.5	None	32.0	1391.2	44 / 0 / 52	7.0
72	MiMo-V2.5	Reasoning	31.2	1385.2	71 / 0 / 97	10.5
73	Hy3 Preview	None	31.0	1379.0	39 / 0 / 63	5.5
74	Step 3.7 Flash	Low	30.5	1408.7	21 / 0 / 35	49.3
75	Laguna S 2.1	Enabled	29.8	1384.6	72 / 0 / 122	28.1
76	Inkling	None	28.7	1354.4	71 / 0 / 139	4.8
77	MiMo-V2.5	Medium	28.3	1363.4	41 / 0 / 71	22.5
78	MiMo-V2.5-Pro	Enabled	28.2	1365.3	39 / 0 / 71	25.0
79	GPT-5.4 Mini	None	27.9	1348.5	28 / 0 / 64	8.1
80	DeepSeek V4 Flash	Medium	27.3	1345.8	65 / 0 / 89	12.9
81	Inkling	Medium	26.9	1331.9	44 / 0 / 78	1.3
82	LongCat 2.0	Enabled	26.7	1359.5	23 / 0 / 55	38.7
83	Gemini 3.5 Flash Lite	High	25.6	1355.1	38 / 0 / 82	47.5
84	GPT-OSS 120B	Low	24.3	1326.3	26 / 0 / 70	28.4
85	Nex N2 Pro	Enabled	23.4	1315.6	32 / 0 / 72	26.8
86	Gemini 3.5 Flash Lite	Medium	22.5	1295.8	38 / 0 / 110	14.0
87	Inkling	Max	20.6	1298.1	36 / 0 / 98	42.0
88	Mistral Medium 3.5	High	19.9	1282.4	23 / 0 / 63	32.0
89	Gemini 3.5 Flash Lite	Minimal	18.9	1281.4	31 / 0 / 113	43.4
90	Gemini 3.1 Flash Lite	Medium	17.8	1239.9	28 / 0 / 70	6.5
91	GPT-5.4 Nano	None	17.3	1236.7	42 / 0 / 136	9.0
92	Gemini 3.1 Flash Lite	High	16.4	1245.7	18 / 0 / 68	31.8
93	Gemma 4 31B	None	14.5	1206.2	27 / 0 / 67	7.5
94	LongCat 2.0	None	13.6	1198.1	48 / 0 / 126	9.6
95	Gemini 3.1 Flash Lite	None	13.5	1199.7	19 / 0 / 57	13.2
96	GPT 4.1	None	12.5	1184.9	28 / 0 / 64	8.1
97	Minimax M3	Enabled	2.3	1091.8	3 / 0 / 103	26.4
98	GPT-5.6 Luna	None	0.5	1059.7	7 / 0 / 79	9.9

Underlying results

Individual player programs

Each row is one accepted player program for GB2-05: Hex. 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 124 player programs.

Player ID	Model	Reasoning	Status	Score	Elo	Confidence	W / D / L	Rated / attempted	Opponents	Faults / players	Generation
E-5aa4402ccce7b855	Claude Fable 5	XHigh	Rated	90.3	2008	—	82 / 0 / 16	98 / 98	42	0 / 1	Repaired · 2026-07-02
E-ad7cf41c05ec3f64	Claude Fable 5	Medium	Rated	58.9	1674	—	64 / 0 / 42	106 / 106	53	0 / 1	First try · 2026-07-02
E-7e9bc3ebc12ef500	Claude Opus 4.5	Legacy_shared_thinking_budget	Waiting	—	—	—	0 / 0 / 0	0 / 0	0	0 / 1	First try · 2026-07-02
E-934b5bc34a7e20b9	Claude Opus 4.5	Thinking field omitted	Rated	51.2	1592	—	66 / 0 / 38	104 / 104	52	0 / 1	First try · 2026-07-02
E-a75e9d71efa4a6bc	Claude Opus 4.5	Medium effort + 16,000 thinking tokens	Rated	41.6	1491	—	60 / 0 / 46	106 / 106	53	0 / 1	First try · —
E-ccacc93776fb7c88	Claude Opus 4.5	High effort + 32,000 thinking tokens	Rated	37.7	1465	—	28 / 0 / 26	54 / 54	27	0 / 1	First try · —
E-ff0722d17402bafa	Claude Opus 4.5	Legacy_shared_thinking_budget	Waiting	—	—	—	0 / 0 / 0	0 / 0	0	0 / 1	First try · 2026-07-02
E-233f9cae6335e53d	Claude Opus 4.8	Thinking field omitted	Rated	35.3	1426	—	42 / 0 / 54	96 / 96	48	0 / 1	First try · 2026-07-02
E-6774d700e60de31a	Claude Opus 4.8	XHigh	Rated	45.7	1533	—	53 / 0 / 63	116 / 116	58	0 / 1	Repaired · 2026-07-02
E-924d7e6ee41b562e	Claude Opus 4.8	Medium	Rated	46.7	1542	—	65 / 0 / 55	120 / 120	60	0 / 1	First try · 2026-07-02
E-09963ffe0b0fa5fd	Claude Opus 5	Thinking disabled	Rated	88.5	1986	—	104 / 0 / 12	116 / 116	58	0 / 1	First try · 2026-07-25
E-32c377b229530444	Claude Opus 5	Medium	Rated	78.1	1876	—	94 / 0 / 18	112 / 112	56	0 / 1	First try · 2026-07-25
E-3f3686d02d1503fa	Claude Opus 5	XHigh	Rated	100.0	2119	—	68 / 0 / 0	68 / 68	29	0 / 1	First try · 2026-07-25
E-a35dfc1adc62e4eb	Claude Opus 5	XHigh	Rated	70.4	1805	—	46 / 0 / 22	68 / 68	31	0 / 1	First try · 2026-07-25
E-b53cb955b1d8baab	Claude Opus 5	Thinking disabled	Rated	84.6	1945	—	102 / 0 / 12	114 / 114	57	0 / 1	First try · 2026-07-25
E-d7111b534ebcaba2	Claude Opus 5	Medium	Rated	86.1	1961	—	100 / 0 / 10	110 / 110	55	0 / 1	First try · 2026-07-25
E-e0a09b1ea3f11175	Claude Sonnet 5	Medium	Rated	51.2	1593	—	66 / 0 / 38	104 / 104	52	0 / 1	First try · 2026-07-02
E-a0518a43c688d1e2	North Mini Code	Enabled	Rated	47.1	1554	—	46 / 0 / 36	82 / 82	41	0 / 1	First try · 2026-07-02
E-06a41d0e11b18b77	DeepSeek V4 Flash	High	Rated	30.2	1376	—	30 / 0 / 46	76 / 76	38	0 / 1	First try · 2026-07-01
E-0dca18c79b6ac9d7	DeepSeek V4 Flash	Reasoning disabled	Rated	35.5	1425	—	48 / 0 / 64	112 / 112	56	0 / 1	First try · 2026-07-02
E-2c1cbd253f3a9d69	DeepSeek V4 Flash	High	Rated	24.5	1315	—	35 / 0 / 43	78 / 78	39	0 / 1	First try · 2026-07-02
E-b3d889b0631db85f	DeepSeek V4 Flash	XHigh	Rated	48.0	1560	—	52 / 0 / 44	96 / 96	48	0 / 1	Repaired · 2026-07-02
E-0ca4798825ceaccb	DeepSeek V4 Pro	XHigh	Rated	71.1	1805	—	61 / 0 / 35	96 / 96	45	0 / 1	Repaired · 2026-07-02
E-da5f3b1a4e370e1a	DeepSeek V4 Pro	Reasoning disabled	Rated	35.8	1431	—	46 / 0 / 50	96 / 96	48	0 / 1	Repaired · 2026-07-02
E-7603462aff103041	Gemini 3.1 Flash Lite	Medium	Rated	17.8	1240	—	28 / 0 / 70	98 / 98	49	0 / 1	Repaired · 2026-07-02
E-a72dd193e1dc4331	Gemini 3.1 Flash Lite	High	Rated	13.2	1210	—	4 / 0 / 42	46 / 46	23	0 / 1	Repaired · 2026-07-02
E-d979b43c3aeea657	Gemini 3.1 Flash Lite	Reasoning disabled	Rated	13.5	1200	—	19 / 0 / 57	76 / 76	38	0 / 1	First try · 2026-07-02
E-a13c4c9fdf6b244d	Gemini 3.5 Flash	Low	Waiting	—	—	—	0 / 0 / 0	0 / 0	0	0 / 1	First try · 2026-07-21
E-a7ce764239377b3f	Gemini 3.5 Flash	Medium	Rated	47.3	1550	—	58 / 0 / 54	112 / 112	56	0 / 1	Repaired · 2026-07-02
E-b50da126631c1ea1	Gemini 3.5 Flash	High	Rated	37.1	1460	—	24 / 0 / 26	50 / 50	25	0 / 1	Repaired · 2026-07-02
E-06abb3c93d2072c8	Gemini 3.5 Flash Lite	High	Limited data	16.6	1255	—	7 / 0 / 27	34 / 34	17	0 / 1	First try · 2026-07-24
E-214f636367cbdac4	Gemini 3.5 Flash Lite	Minimal	Limited data	24.5	1354	—	6 / 0 / 16	22 / 24	11	0 / 1	Repaired · 2026-07-24
E-3dd83d6fa9f8f758	Gemini 3.5 Flash Lite	Medium	Rated	19.2	1261	—	18 / 0 / 56	74 / 74	37	0 / 1	First try · 2026-07-24
E-5b803013ec40d15d	Gemini 3.5 Flash Lite	High	Limited data	15.3	1238	—	7 / 0 / 31	38 / 38	19	0 / 1	First try · 2026-07-24
E-8826ab29e7591ece	Gemini 3.5 Flash Lite	Medium	Rated	25.8	1331	—	20 / 0 / 54	74 / 74	37	0 / 1	First try · 2026-07-24
E-a870d09d3e1a40d4	Gemini 3.5 Flash Lite	Minimal	Limited data	19.0	1296	—	4 / 0 / 18	22 / 22	11	0 / 1	First try · 2026-07-24
E-5bcc61f900210bfa	Gemini 3.6 Flash	Medium	Rated	83.7	1945	—	69 / 0 / 3	72 / 72	36	0 / 1	First try · 2026-07-24
E-8b9ff59d79afb558	Gemini 3.6 Flash	High	Limited data	55.0	1665	—	23 / 0 / 7	30 / 30	15	0 / 1	First try · 2026-07-24
E-9bef179ce22a6c93	Gemini 3.6 Flash	Minimal	Limited data	46.1	1587	—	13 / 0 / 7	20 / 20	10	0 / 1	First try · 2026-07-24
E-c4f143aad203feb3	Gemini 3.6 Flash	High	Limited data	46.9	1577	—	18 / 0 / 14	32 / 32	16	0 / 1	First try · 2026-07-24
E-d95a1da824d70f6d	Gemini 3.6 Flash	Medium	Rated	56.1	1652	—	36 / 0 / 36	72 / 72	36	0 / 1	First try · 2026-07-24
E-e23af86eb5787555	Gemini 3.6 Flash	Minimal	Rated	58.3	1692	—	29 / 0 / 11	40 / 40	20	0 / 1	First try · 2026-07-24
E-e8e17fbbdd12faa4	Gemma 4 31B	Reasoning disabled	Rated	14.5	1206	—	27 / 0 / 67	94 / 94	47	0 / 1	First try · 2026-07-02
E-fd1bc1e2e6ac48fb	Gemma 4 31B	Reasoning enabled	Rated	45.2	1535	—	45 / 0 / 33	78 / 78	39	0 / 1	Repaired · 2026-07-02
E-1b9f1f7b70f02927	GPT 4.1	None	Rated	12.5	1185	—	28 / 0 / 64	92 / 92	46	0 / 1	First try · 2026-07-02
E-9e5b308c41a36374	GPT 5	Medium	Rated	52.1	1603	—	50 / 0 / 52	102 / 102	51	0 / 1	First try · 2026-07-02
E-c5ad048b6fb4e93d	GPT 5	High	Rated	51.1	1610	—	27 / 0 / 21	48 / 48	24	0 / 1	First try · 2026-07-02
E-d03d2c6a69fc3e16	GPT 5	Low	Waiting	—	—	—	0 / 0 / 0	0 / 0	0	0 / 1	Repaired · 2026-07-21
E-6d3546010ef68f50	GPT-5.4	None	Rated	68.4	1778	—	65 / 0 / 25	90 / 90	45	0 / 1	Repaired · 2026-07-02
E-cafab3c275850d3b	GPT-5.4	Medium	Rated	40.3	1475	—	50 / 0 / 68	118 / 118	59	0 / 1	First try · 2026-07-02
E-f6403f7a30e19e82	GPT-5.4	XHigh	Rated	92.5	2033	—	84 / 0 / 8	92 / 92	42	0 / 1	First try · 2026-07-02
E-0791f6b66243ec1a	GPT-5.4 Mini	Medium	Rated	49.2	1569	—	72 / 0 / 48	120 / 120	60	0 / 1	First try · 2026-07-02
E-427bdffeacc6c394	GPT-5.4 Mini	None	Rated	27.9	1349	—	28 / 0 / 64	92 / 92	46	0 / 1	Repaired · 2026-07-02
E-3311575b341ee4a8	GPT-5.4 Nano	None	Rated	19.6	1262	—	21 / 0 / 67	88 / 88	44	0 / 1	Repaired · 2026-07-09
E-6c37eeef15b82287	GPT-5.4 Nano	None	Rated	15.0	1212	—	21 / 0 / 69	90 / 90	45	0 / 1	Repaired · 2026-07-02
E-8e40431df091d53f	GPT-5.4 Nano	Medium	Rated	71.0	1805	—	75 / 0 / 17	92 / 92	46	0 / 1	First try · 2026-07-02
E-a0d8c8fd6b01598c	GPT-5.4 Nano	Medium	Rated	23.0	1292	—	37 / 0 / 77	114 / 114	57	0 / 1	First try · 2026-07-09
E-6f42dbbf02274b56	GPT-5.5	None	Rated	47.2	1553	—	52 / 0 / 38	90 / 90	45	0 / 1	First try · 2026-07-02
E-762e9d80a60b41ed	GPT-5.5	XHigh	Rated	81.4	1914	—	76 / 0 / 20	96 / 96	45	0 / 1	First try · 2026-07-02
E-ffa82d1e96e897ab	GPT-5.5	Medium	Rated	64.4	1734	—	66 / 0 / 30	96 / 96	48	0 / 1	First try · 2026-07-02
E-25a83ddaeb1268a4	GPT-5.6 Luna	XHigh	Rated	53.7	1618	—	50 / 0 / 56	106 / 106	52	0 / 1	First try · 2026-07-10
E-59156a669808a24f	GPT-5.6 Luna	None	Rated	0.5	1060	—	7 / 0 / 79	86 / 88	43	2 / 1	Repaired · 2026-07-10
E-e917387a1c57aa23	GPT-5.6 Luna	Medium	Rated	52.0	1599	—	57 / 0 / 59	116 / 116	58	0 / 1	First try · 2026-07-10
E-471e9297eea18ffd	GPT-5.6 Sol	None	Rated	57.7	1663	—	59 / 0 / 39	98 / 98	49	0 / 1	First try · 2026-07-10
E-af9c2c2998294ad0	GPT-5.6 Sol	XHigh	Rated	63.9	1729	—	59 / 0 / 33	92 / 92	44	0 / 1	First try · 2026-07-10
E-d61f8454991c5422	GPT-5.6 Sol	Medium	Rated	58.6	1672	—	61 / 0 / 37	98 / 98	49	0 / 1	First try · 2026-07-10
E-012ecb9ce0709c05	GPT-5.6 Terra	XHigh	Rated	56.4	1650	—	52 / 0 / 42	94 / 94	45	0 / 1	Repaired · 2026-07-10
E-1f00b423eab1c19d	GPT-5.6 Terra	None	Rated	49.5	1578	—	53 / 0 / 35	88 / 88	44	0 / 1	First try · 2026-07-10
E-9664e98d37ece097	GPT-5.6 Terra	Medium	Rated	52.4	1604	—	64 / 0 / 44	108 / 108	54	0 / 1	First try · 2026-07-10
E-067ab716d64e3e9a	LongCat 2.0	None	Rated	11.1	1171	—	21 / 0 / 69	90 / 92	45	2 / 1	Repaired · 2026-07-24
E-73a7ad076eeaa6ae	LongCat 2.0	Enabled	Rated	42.5	1517	—	30 / 0 / 22	52 / 52	26	0 / 1	First try · 2026-07-24
E-8b7eb63d4f53d846	LongCat 2.0	Enabled	Rated	20.3	1281	—	13 / 0 / 39	52 / 52	26	0 / 1	First try · 2026-07-24
E-8cc657b7db4428cb	LongCat 2.0	None	Rated	16.1	1225	—	27 / 0 / 57	84 / 86	42	2 / 1	First try · 2026-07-24
E-33797d7b77c7800c	Minimax M3	Reasoning disabled	Rated	39.7	1469	—	54 / 0 / 58	112 / 112	56	0 / 1	Repaired · 2026-07-02
E-fb8ac45946e32e22	Minimax M3	Reasoning enabled	Rated	4.6	1108	—	2 / 0 / 66	68 / 68	34	0 / 1	Repaired · 2026-07-02
E-1954b83d439b455c	Mistral Medium 3.5	High	Rated	17.4	1253	—	8 / 0 / 40	48 / 48	24	0 / 1	Repaired · 2026-07-02
E-4a7d37b86196302f	Mistral Medium 3.5	None	Rated	32.0	1391	—	44 / 0 / 52	96 / 96	48	0 / 1	First try · 2026-07-02
E-952fba19b28982d5	Kimi K2.7 Code	Reasoning enabled	Rated	57.5	1670	—	40 / 0 / 24	64 / 64	32	0 / 1	Repaired · 2026-07-02
E-4419230379dcd41e	Kimi K3	Low	Rated	61.0	1712	—	40 / 0 / 12	52 / 52	26	0 / 1	First try · 2026-07-24
E-895556dde47644ae	Kimi K3	High	Rated	48.8	1581	—	35 / 0 / 21	56 / 56	28	0 / 1	First try · 2026-07-24
E-5f76f577111bee8d	Nex N2 Pro	Reasoning enabled	Rated	11.1	1178	—	10 / 0 / 56	66 / 66	33	0 / 1	Repaired · 2026-07-02
E-962a9da8812a74d4	Nex N2 Pro	Reasoning disabled	Rated	42.5	1501	—	52 / 0 / 52	104 / 104	52	0 / 1	Repaired · 2026-07-11
E-4477e0de2e04aad4	Nemotron 3 Ultra 550B A55B	Reasoning disabled	Rated	51.3	1598	—	53 / 0 / 33	86 / 86	43	0 / 1	First try · 2026-07-02
E-48ed5c5e00ef38fb	Nemotron 3 Ultra 550B A55B	High	Rated	28.1	1365	—	14 / 0 / 36	50 / 50	25	0 / 1	First try · 2026-07-02
E-da3b98638ff53ea9	Nemotron 3 Ultra 550B A55B	High	Rated	32.4	1410	—	19 / 0 / 31	50 / 50	25	0 / 1	Repaired · 2026-07-11
E-343b92f3dda3dcb5	O3	Medium	Rated	47.0	1547	—	64 / 0 / 48	112 / 112	56	0 / 1	First try · 2026-07-02
E-4724b57e861c4ecf	O3	High	Rated	39.5	1481	—	30 / 0 / 28	58 / 58	29	0 / 1	First try · 2026-07-02
E-61d05a26a332d2e5	O3	High	Rated	38.9	1477	—	23 / 0 / 31	54 / 54	27	0 / 1	First try · 2026-07-03
E-9bfe5e29476019eb	O3	High	Limited data	33.9	1440	—	15 / 0 / 17	32 / 32	16	0 / 1	First try · 2026-07-03
E-ffb183b7ecfe85e0	O3	High	Limited data	34.8	1448	—	17 / 0 / 17	34 / 34	17	0 / 1	First try · 2026-07-03
E-172336d3fd38632a	GPT-OSS 120B	Low	Rated	31.9	1402	—	21 / 0 / 35	56 / 56	28	0 / 1	Repaired · 2026-07-21
E-5ef540286ecbb63d	GPT-OSS 120B	Medium	Rated	38.4	1455	—	47 / 0 / 67	114 / 114	57	0 / 1	Repaired · 2026-07-02
E-1ca53619662c7f6f	Laguna S 2.1	None	Rated	71.7	1811	—	76 / 0 / 24	100 / 100	50	0 / 1	First try · 2026-07-24
E-21623e96b2b104e9	Laguna S 2.1	None	Rated	33.5	1407	—	46 / 0 / 46	92 / 92	46	0 / 1	Repaired · 2026-07-24
E-53ce0020411c86d4	Laguna S 2.1	Enabled	Rated	18.9	1267	—	10 / 0 / 40	50 / 50	25	0 / 1	First try · 2026-07-24
E-62e15a037ee860c1	Laguna S 2.1	Enabled	Rated	31.2	1394	—	22 / 0 / 36	58 / 58	29	0 / 1	Repaired · 2026-07-24
E-435ec29661cdc285	Qwen3.7 Max	Reasoning enabled	Rated	48.5	1569	—	41 / 0 / 41	82 / 82	41	0 / 1	Repaired · 2026-07-02
E-c577c41440c17864	Qwen3.7 Max	Reasoning disabled	Rated	44.9	1525	—	52 / 0 / 52	104 / 104	52	0 / 1	First try · 2026-07-02
E-6cc7454f585005c4	Qwen3.7 Plus	Reasoning enabled	Rated	47.4	1558	—	37 / 0 / 43	80 / 80	40	0 / 1	Repaired · 2026-07-02
E-94daaf1196d89c6c	Qwen3.7 Plus	Reasoning disabled	Rated	42.8	1505	—	48 / 0 / 52	100 / 100	50	0 / 1	First try · 2026-07-02
E-358338a9fbdbcb6a	Step 3.7 Flash	High	Rated	39.3	1483	—	23 / 0 / 27	50 / 50	25	0 / 1	Repaired · 2026-07-02
E-50f22f1c15a8fd4a	Step 3.7 Flash	Low	Limited data	32.8	1436	—	11 / 0 / 15	26 / 30	13	0 / 1	First try · 2026-07-21
E-7b9b33921ba865f5	Step 3.7 Flash	Medium	Rated	41.8	1491	—	52 / 0 / 64	116 / 116	58	0 / 1	Repaired · 2026-07-02
E-1bb81f8a4ae78954	Hy3 Preview	None	Rated	31.0	1379	—	39 / 0 / 63	102 / 102	51	0 / 1	First try · 2026-07-02
E-92dc0ac61d798488	Hy3 Preview	High	Rated	38.1	1472	—	23 / 0 / 25	48 / 48	24	0 / 1	Repaired · 2026-07-03
E-0f05573125dedc2b	Inkling	None	Rated	28.3	1351	—	34 / 0 / 68	102 / 102	51	0 / 1	Repaired · 2026-07-24
E-2c483dc32fc18ba8	Inkling	Max	Limited data	10.5	1190	—	4 / 0 / 30	34 / 34	17	0 / 1	First try · 2026-07-24
E-ae60ed096a69eeff	Inkling	Medium	Rated	26.9	1332	—	44 / 0 / 78	122 / 122	61	0 / 1	Repaired · 2026-07-24
E-e9202aa1565d1c4e	Inkling	Max	Limited data	20.2	1291	—	9 / 0 / 27	36 / 36	18	0 / 1	Repaired · 2026-07-24
E-f7a1d86c7e241f8d	Inkling	None	Rated	29.1	1358	—	37 / 0 / 71	108 / 108	54	0 / 1	First try · 2026-07-24
E-3c5879def34f7d38	Grok 4.5	Low	Rated	51.3	1611	—	30 / 0 / 18	48 / 48	24	0 / 1	First try · 2026-07-24
E-824ec3caceabd338	Grok 4.5	Medium	Rated	58.0	1663	—	70 / 0 / 46	116 / 116	58	0 / 1	First try · 2026-07-24
E-8e6cb252293b2af9	Grok 4.5	High	Limited data	47.1	1578	—	16 / 0 / 18	34 / 34	17	0 / 1	First try · 2026-07-24
E-4aac1b6621aeae38	Grok Build 0.1	Reasoning enabled	Rated	49.6	1583	—	44 / 0 / 30	74 / 74	37	0 / 1	Repaired · 2026-07-02
E-09d406abc15f7c9a	MiMo-V2.5	Reasoning disabled	Rated	55.7	1644	—	52 / 0 / 34	86 / 86	43	0 / 1	First try · 2026-07-02
E-9490f08c56c27d13	MiMo-V2.5	Reasoning disabled	Rated	27.4	1344	—	32 / 0 / 54	86 / 86	43	0 / 1	Repaired · 2026-07-01
E-ad48cf51fe7da3cc	MiMo-V2.5	Reasoning enabled	Rated	23.7	1309	—	22 / 0 / 48	70 / 70	35	0 / 1	Repaired · 2026-07-02
E-be8fc9653466bbe1	MiMo-V2.5	Reasoning disabled	Rated	35.0	1426	—	39 / 0 / 43	82 / 82	41	0 / 1	First try · 2026-07-02
E-faaa866ee28d6401	MiMo-V2.5	Reasoning enabled	Rated	17.8	1252	—	10 / 0 / 48	58 / 58	29	0 / 1	Repaired · 2026-07-02
E-9c228ad72a159b33	MiMo-V2.5-Pro	Reasoning enabled	Rated	26.6	1341	—	18 / 0 / 52	70 / 70	35	0 / 1	Repaired · 2026-07-02
E-af55f57b03605914	MiMo-V2.5-Pro	Reasoning disabled	Rated	37.6	1450	—	50 / 0 / 46	96 / 96	48	0 / 1	First try · 2026-07-02
E-38e323f4ce233fa1	GLM-5.2	Reasoning disabled	Rated	35.5	1431	—	42 / 0 / 40	82 / 82	41	0 / 1	First try · 2026-07-11
E-3916ba303b2ff700	GLM-5.2	High	Rated	49.1	1575	—	42 / 0 / 40	82 / 82	41	0 / 1	Repaired · 2026-07-11
E-d8655d29a4806df8	GLM-5.2	Reasoning disabled	Rated	53.7	1625	—	38 / 0 / 42	80 / 80	40	0 / 1	Repaired · 2026-07-02