1 85.9 55% cov.
$120 2.0M 78.0 — 87.9 — 97.3 (77.4 % resolved)
— 97.3 (1487.4 Elo)
97.3 (156.9 ECI)
100.0 (100.0 /100)
2 85.8 50% cov.
$30 1.0M 303 — — — 94.8 (75.8 % resolved)
— 91.1 (1466.6 Elo)
81.0 (150.9 ECI)
— 3 84.4 30% cov.
$144 400k 64.3 — 77.6 — — — 92.9 (1472.8 Elo)
100.0 (157.9 ECI)
99.8 (99.8 /100)
4 82.7 30% cov.
$144 400k 62.9 — 77.6 — — — 91.7 (1468.8 Elo)
95.4 (156.2 ECI)
99.8 (99.8 /100)
5 DeepSeek
81.6 75% cov.
$33 128k 157 86.2 73.7 94.3 (84.4 % pass@1)
— 83.7 (74.2 %)
79.4 (1427.7 Elo)
69.0 (146.5 ECI)
99.8 (99.8 /100)
6 78.0 65% cov.
$120 400k 70.1 27.7 — — 92.7 (74.4 % resolved)
100.0 (88.0 %)
72.7 (1405.1 Elo)
78.5 (150.0 ECI)
— 7 77.6 55% cov.
$120 400k 69.7 — 77.6 — 90.3 (72.8 % resolved)
— 76.5 (1417.9 Elo)
88.7 (153.7 ECI)
99.8 (99.8 /100)
8 77.0 55% cov.
$1,035 200k 6.42 — 100.0 — 94.5 (75.6 % resolved)
— 100.0 (1496.5 Elo)
93.0 (155.3 ECI)
100.0 (100.0 /100)
9 DeepSeek
76.8 40% cov.
$16 128k 285 — — — — 83.7 (74.2 %)
78.2 (1423.5 Elo)
65.1 (145.1 ECI)
— 10 76.6 30% cov.
$207 200k 29.4 — 90.8 — — — 85.5 (1448.0 Elo)
86.7 (153.0 ECI)
100.0 (100.0 /100)
11 76.3 30% cov.
$1,035 200k 6.36 — 100.0 — — — 94.3 (1477.5 Elo)
94.8 (156.0 ECI)
100.0 (100.0 /100)
12 Moonshot (Kimi)
75.7 70% cov.
$37 256k 132 — 77.6 — 87.8 (71.2 % resolved)
65.8 (59.1 %)
75.4 (1414.3 Elo)
73.6 (148.2 ECI)
99.8 (99.8 /100)
13 75.1 55% cov.
$207 200k 28.8 — 72.5 — 93.3 (74.8 % resolved)
— 81.3 (1434.0 Elo)
70.6 (147.1 ECI)
100.0 (100.0 /100)
14 OpenAI
75.1
$66 200k 73.8 47.0 — 100.0 (87.3 % pass@1)
77.8 (64.6 % resolved)
81.0 (72.0 %)
57.0 (1352.6 Elo)
69.9 (146.9 ECI)
— 15 Alibaba (Qwen)
74.3 25% cov.
$10 131k 358 — — — — — 75.2 (1413.5 Elo)
66.3 (145.6 ECI)
— 16 Alibaba (Qwen)
74.3 70% cov.
$10 131k 358 13.2 — 86.6 (80.4 % pass@1)
— 66.3 (59.6 %)
60.9 (1365.5 Elo)
50.3 (139.7 ECI)
— 17 73.3 55% cov.
$1,035 200k 6.11 — 58.0 — 100.0 (79.2 % resolved)
— 85.4 (1447.7 Elo)
78.3 (149.9 ECI)
95.1 (95.1 /100)
18 72.8 25% cov.
$120 400k 64.9 — — — — — 83.5 (1441.3 Elo)
77.6 (149.7 ECI)
— 19 71.7 80% cov.
$120 2.0M 63.8 35.7 — 94.1 (84.3 % pass@1)
61.0 (53.6 % resolved)
— 89.1 (1460.0 Elo)
69.4 (146.7 ECI)
— 20 OpenAI
71.1 70% cov.
$600 200k 8.64 20.5 — 95.1 (84.7 % pass@1)
— 92.1 (81.3 %)
73.9 (1409.1 Elo)
70.8 (147.2 ECI)
— 21 69.4 45% cov.
$345 256k 16.3 6.4 0.0 — — 90.0 (79.6 %)
74.0 (1409.6 Elo)
71.3 (147.4 ECI)
100.0 (100.0 /100)
22 68.1 50% cov.
$69 200k 72.6 — — — 80.8 (66.6 % resolved)
— 67.6 (1388.0 Elo)
59.7 (143.1 ECI)
— 23 67.8 50% cov.
$24 400k 270 — — — 70.5 (59.8 % resolved)
— 63.2 (1373.5 Elo)
66.3 (145.6 ECI)
— 24 DeepSeek
67.3
$16 128k 241 65.1 69.5 27.1 (49.6 % pass@1)
86.0 (70.0 % resolved)
78.9 (70.2 %)
78.1 (1423.3 Elo)
69.0 (146.5 ECI)
99.8 (99.8 /100)
25 xAI
64.1 70% cov.
— 1.0M — — — 82.2 (78.1 % pass@1)
— 54.1 (49.3 %)
61.1 (1366.4 Elo)
54.2 (141.1 ECI)
— 26 Zhipu AI (GLM)
63.0 30% cov.
$28 200k 124 — 100.0 — — — 81.9 (1436.0 Elo)
63.6 (144.6 ECI)
0.0 (0.0 /100)
27 Zhipu AI (GLM)
62.8 55% cov.
$28 200k 124 — 100.0 — 63.8 (55.4 % resolved)
— 83.2 (1440.4 Elo)
55.8 (141.7 ECI)
0.0 (0.0 /100)
28 61.3 85% cov.
$30 1.0M 201 52.3 42.7 76.4 (75.1 % pass@1)
23.2 (28.7 % resolved)
— 76.5 (1417.8 Elo)
60.3 (143.4 ECI)
100.0 (100.0 /100)
29 58.7
$207 200k 22.0 5.2 97.5 46.2 (59.4 % pass@1)
96.3 (76.8 % resolved)
62.6 (56.4 %)
52.5 (1337.6 Elo)
58.0 (142.5 ECI)
100.0 (100.0 /100)
30 58.6 65% cov.
$207 200k 22.0 65.9 — — 80.5 (66.4 % resolved)
72.6 (64.9 %)
41.0 (1299.0 Elo)
56.6 (142.0 ECI)
— 31 58.3
$1,035 200k 4.86 1.9 100.0 51.9 (62.4 % pass@1)
90.9 (73.2 % resolved)
79.5 (70.7 %)
76.3 (1417.3 Elo)
63.9 (144.7 ECI)
96.7 (96.7 /100)
32 56.9 30% cov.
$207 200k 21.3 6.7 — 63.8 (68.5 % pass@1)
— — — — — 33 xAI
56.9 40% cov.
$207 1.0M 21.2 8.4 — — — 58.9 (53.3 %)
78.5 (1424.6 Elo)
48.8 (139.2 ECI)
— 34 OpenAI
56.3
$66 200k 52.4 33.4 — 67.8 (70.6 % pass@1)
44.0 (42.4 % resolved)
67.3 (60.4 %)
52.2 (1336.4 Elo)
55.5 (141.6 ECI)
— 35 53.9 30% cov.
$1,035 200k 4.49 1.8 — 67.4 (70.4 % pass@1)
— — — — — 36 52.5 50% cov.
$5 400k 818 — — — 32.4 (34.8 % resolved)
— 47.2 (1319.8 Elo)
52.6 (140.6 ECI)
— 37 50.5 65% cov.
— 1.0M — — — — 39.7 (39.6 % resolved)
57.8 (52.4 %)
65.7 (1381.7 Elo)
44.5 (137.6 ECI)
— 38 OpenAI
48.7 25% cov.
$900 200k 4.01 22.2 — — — — 60.9 (1365.7 Elo)
59.1 (142.9 ECI)
— 39 45.9 25% cov.
$5 1.0M 431 32.4 — — — — 37.3 (1286.5 Elo)
25.0 (130.5 ECI)
— 40 43.7
$207 200k 15.7 47.2 — 25.5 (48.7 % pass@1)
75.9 (63.4 % resolved)
56.9 (51.6 %)
40.5 (1297.5 Elo)
35.6 (134.3 ECI)
— 41 42.4 25% cov.
$10 10.0M 175 14.1 — — — — 35.5 (1280.5 Elo)
25.4 (130.6 ECI)
— 42 42.3 25% cov.
$75 2.0M 32.6 40.8 — — — — 47.0 (1319.0 Elo)
31.4 (132.8 ECI)
— 43 OpenAI
42.1 25% cov.
$180 128k 14.9 44.6 — — — — 46.4 (1317.0 Elo)
42.0 (136.7 ECI)
— 44 39.1 50% cov.
$6 1.0M 252 25.2 — — 0.0 (13.5 % resolved)
— 57.4 (1353.8 Elo)
39.8 (135.9 ECI)
— 45 37.8 40% cov.
$14 1.0M 102 13.0 — — — 14.2 (15.6 %)
37.5 (1287.5 Elo)
32.3 (133.1 ECI)
— 46 xAI
36.2 25% cov.
$138 131k 18.0 36.0 — — — — 42.6 (1304.5 Elo)
26.0 (130.8 ECI)
— 47 Alibaba (Qwen)
35.5 25% cov.
$30 131k 31.2 3.7 — — — — 32.0 (1268.9 Elo)
22.3 (129.5 ECI)
— 48 Meta
34.8 25% cov.
$29 128k 30.8 8.5 — — — — 33.8 (1274.9 Elo)
17.0 (127.5 ECI)
— 49 Meta
31.3 25% cov.
$116 128k 8.31 0.0 — — — — 36.4 (1283.6 Elo)
18.1 (127.9 ECI)
— 50 Anthropic
31.2 40% cov.
$55 200k 31.9 25.6 — — — 28.9 (28.0 %)
27.9 (1255.2 Elo)
17.0 (127.5 ECI)
— 51 Meta
31.0 25% cov.
$29 128k 25.4 0.6 — — — — 29.6 (1260.8 Elo)
11.5 (125.5 ECI)
— 52 Mistral
30.0 25% cov.
$102 128k 13.5 1.4 — — — — 31.1 (1266.0 Elo)
20.6 (128.8 ECI)
— 53 26.6
$150 128k 9.73 13.4 — 5.4 (38.3 % pass@1)
38.5 (38.8 % resolved)
23.1 (23.1 %)
41.4 (1300.3 Elo)
22.0 (129.3 ECI)
— 54 25.6 70% cov.
$9 128k 68.2 1.9 — 0.0 (35.5 % pass@1)
— 0.0 (3.6 %)
37.2 (1286.3 Elo)
15.8 (127.1 ECI)
— 55 13.8 55% cov.
$510 128k 1.40 0.4 — 3.5 (37.3 % pass@1)
— — 32.8 (1271.6 Elo)
17.4 (127.7 ECI)
— 56 Mistral
12.0 25% cov.
$40 66k — — — — — — 0.0 (1161.9 Elo)
0.0 (121.3 ECI)
— 57 11.1 50% cov.
$1,035 200k 0.92 13.8 — — 3.5 (15.8 % resolved)
— 29.9 (1261.9 Elo)
15.6 (127.0 ECI)
— 58 10.0 0% cov.
— — — — — — — — — — — 59 10.0 0% cov.
— — — — — — — — — — — 60 10.0 0% cov.
— — — — — — — — — — — 61 10.0 0% cov.
— — — — — — — — — — — 62 10.0 0% cov.
— — — — — — — — — — — 63 10.0 0% cov.
— — — — — — — — — — — 64 10.0 0% cov.
— — — — — — — — — — — 65 10.0 0% cov.
— — — — — — — — — — — 66 10.0 0% cov.
— — — — — — — — — — — 67 7.9 0% cov.
$120 2.0M — — — — — — — — —