Archive

Verified Runs

Every accepted leaderboard submission has a permanent static page.

Rank Model Accuracy Prompt Dataset Created Run
1 gpt-6-astra 95.66% p001 lexen-v1 2026-09-25T07:35:15.607531+00:00 gpt-6-astra-xhigh-reasoning-p001-lexen-v1-20260925
2 gpt-5.5 95.60% p001 lexen-v1 2026-06-17T15:45:49.081775+00:00 gpt-5.5-xhigh-reasoning-p001-lexen-v1-20260617
3 gemini/gemini-3.8-flash 95.25% p001 lexen-v1 2026-09-25T08:00:52.962211+00:00 gemini-3.8-flash-low-reasoning-p001-lexen-v1-20260925
4 gpt-5.5 95.25% p001 lexen-v1 2026-06-14T02:57:35.564261+00:00 gpt-5.5-medium-reasoning-p001-lexen-v1-20260614
5 claude-fable-5+fallback:claude-opus-4-8 95.21% p001 lexen-v1 2026-07-01T21:52:21.405001+00:00 claude-fable-5-xhigh-reasoning-p001-lexen-v1-20260701-fallback-claude-opus-4-8
6 gpt-5.5 95.19% p001 lexen-v1 2026-06-14T10:40:02.498375+00:00 gpt-5.5-high-reasoning-p001-lexen-v1-20260614
7 gpt-5.5 95.15% p004 lexen-v1 2026-06-16T02:04:07.572024+00:00 gpt-5.5-medium-reasoning-p004-lexen-v1-20260616
8 gpt-5.5 95.15% p004 lexen-v1 2026-06-17T16:05:54.293112+00:00 gpt-5.5-xhigh-reasoning-p004-lexen-v1-20260617
9 gpt-5.5 95.10% p003 lexen-v1 2026-06-17T08:02:30.444392+00:00 gpt-5.5-high-reasoning-p003-lexen-v1-20260617
10 gemini/gemini-3.8-flash 95.04% p001 lexen-v1 2026-09-25T08:11:51.313943+00:00 gemini-3.8-flash-high-reasoning-p001-lexen-v1-20260925
11 gpt-6-sol 95.00% p001 lexen-v1 2026-09-25T07:34:19.152942+00:00 gpt-6-sol-low-reasoning-p001-lexen-v1-20260925
12 gpt-6-sol 95.00% p001 lexen-v1 2026-09-25T07:37:49.541001+00:00 gpt-6-sol-xhigh-reasoning-p001-lexen-v1-20260925
13 gpt-5.5 95.00% p003 lexen-v1 2026-06-16T02:01:57.439526+00:00 gpt-5.5-low-reasoning-p003-lexen-v1-20260616
14 gpt-5.5 95.00% p001 lexen-v1 2026-06-14T10:38:21.202553+00:00 gpt-5.5-low-reasoning-p001-lexen-v1-20260614
15 gpt-5.5 94.98% p003 lexen-v1 2026-06-16T02:02:51.976097+00:00 gpt-5.5-medium-reasoning-p003-lexen-v1-20260616
16 gpt-5.6-sol 94.94% p001 lexen-v1 2026-07-25T11:36:26.908334+00:00 gpt-5.6-sol-xhigh-reasoning-p001-lexen-v1-20260725
17 gemini/gemini-3.1-pro-preview 94.92% p001 lexen-v1 2026-06-14T13:03:44.802733+00:00 gemini-3.1-pro-high-reasoning-p001-lexen-v1-20260614
18 claude-opus-5 94.75% p001 lexen-v1 2026-07-25T11:54:56.929727+00:00 claude-opus-5-max-reasoning-p001-lexen-v1-20260725
19 openrouter/moonshotai/kimi-k3+fallback:openrouter/moonshotai/kimi-k2.7-code 94.63% p001 lexen-v1 2026-07-25T23:33:24.661391+00:00 kimi-k3-xhigh-reasoning-p001-lexen-v1-20260725-fallback-kimi-k2.7-code
20 gemini/gemini-3.1-pro-preview 94.61% p001 lexen-v1 2026-06-14T12:09:22.494330+00:00 gemini-3.1-pro-low-reasoning-p001-lexen-v1-20260614
21 claude-opus-4-8 94.57% p001 lexen-v1 2026-06-14T12:38:24.818958+00:00 claude-opus-4.8-xhigh-reasoning-p001-lexen-v1-20260614
22 gemini/gemini-3.1-pro-preview 94.53% p004 lexen-v1 2026-06-16T02:57:54.138994+00:00 gemini-3.1-pro-high-reasoning-p004-lexen-v1-20260616
23 gpt-5.6-sol 94.51% p001 lexen-v1 2026-07-25T11:06:21.543697+00:00 gpt-5.6-sol-medium-reasoning-p001-lexen-v1-20260725
24 gemini/gemini-3.1-pro-preview 94.43% p001 lexen-v1 2026-06-14T12:31:55.744716+00:00 gemini-3.1-pro-medium-reasoning-p001-lexen-v1-20260614
25 gemini/gemini-3.1-pro-preview 94.40% p003 lexen-v1 2026-06-16T02:21:16.914989+00:00 gemini-3.1-pro-low-reasoning-p003-lexen-v1-20260616
26 gpt-5.6-terra 94.22% p001 lexen-v1 2026-07-31T15:00:13.590204+00:00 gpt-5.6-terra-xhigh-reasoning-p001-lexen-v1-20260731
27 gpt-5.5 94.22% p002 lexen-v1 2026-06-14T10:42:14.146514+00:00 gpt-5.5-high-reasoning-p002-lexen-v1-20260614
28 gemini/gemini-3.5-flash 94.20% p004 lexen-v1 2026-06-16T03:05:35.303206+00:00 gemini-3.5-flash-p004-lexen-v1-20260616
29 gpt-5.6-terra 94.18% p001 lexen-v1 2026-07-31T14:59:14.624893+00:00 gpt-5.6-terra-high-reasoning-p001-lexen-v1-20260731
30 claude-opus-4-8 94.16% p001 lexen-v1 2026-06-14T12:22:29.216965+00:00 claude-opus-4.8-high-reasoning-p001-lexen-v1-20260614
31 gemini/gemini-3.5-flash 94.16% p001 lexen-v1 2026-06-14T11:40:41.558979+00:00 gemini-3.5-flash-p001-lexen-v1-20260614
32 gpt-5.5 94.03% p002 lexen-v1 2026-06-14T02:58:29.150879+00:00 gpt-5.5-medium-reasoning-p002-lexen-v1-20260614
33 gpt-5.6-terra 93.95% p003 lexen-v1 2026-07-31T15:07:13.894561+00:00 gpt-5.6-terra-xhigh-reasoning-p003-lexen-v1-20260731
34 openrouter/x-ai/grok-4.5 93.85% p001 lexen-v1 2026-07-25T18:23:25.410184+00:00 grok-4.5-xhigh-reasoning-p001-lexen-v1-20260725
35 claude-opus-4-8 93.85% p001 lexen-v1 2026-06-17T11:56:28.079841+00:00 claude-opus-4.8-p001-lexen-v1-20260617
36 claude-opus-4-8 93.81% p004 lexen-v1 2026-06-16T02:20:31.037218+00:00 claude-opus-4.8-xhigh-reasoning-p004-lexen-v1-20260616
37 google/gemma-4-31B-it 93.73% p003 lexen-v1 2026-06-16T03:47:55.278110+00:00 vllm-gemma-4-31b-fp8-h100-p003-lexen-v1-20260616-thinking
38 gpt-5.6-terra 93.68% p001 lexen-v1 2026-07-31T14:58:29.057725+00:00 gpt-5.6-terra-medium-reasoning-p001-lexen-v1-20260731
39 claude-opus-4-8 93.68% p001 lexen-v1 2026-06-14T12:02:22.453692+00:00 claude-opus-4.8-low-reasoning-p001-lexen-v1-20260614
40 claude-opus-4-8 93.62% p001 lexen-v1 2026-06-14T12:12:07.036543+00:00 claude-opus-4.8-medium-reasoning-p001-lexen-v1-20260614
41 gpt-5.6-terra 93.50% p001 lexen-v1 2026-07-31T14:57:51.175244+00:00 gpt-5.6-terra-low-reasoning-p001-lexen-v1-20260731
42 google/gemma-4-31B-it 93.44% p004 lexen-v1 2026-06-16T04:34:22.281346+00:00 vllm-gemma-4-31b-fp8-h100-p004-lexen-v1-20260616-thinking
43 google/gemma-4-31B-it 93.38% p001 lexen-v1 2026-06-15T16:44:33.637582+00:00 vllm-gemma-4-31b-fp8-h100-p001-lexen-v1-20260615-thinking
44 openrouter/z-ai/glm-5 93.38% p001 lexen-v1 2026-06-14T19:07:58.881361+00:00 glm-5-low-reasoning-p001-lexen-v1-20260614
45 gpt-6-luna 93.33% p004 lexen-v1 2026-10-09T13:28:54.379502+00:00 gpt-6-luna-max-reasoning-p004-lexen-v1-20261009
46 openrouter/moonshotai/kimi-k2.7-code 93.31% p001 lexen-v1 2026-06-17T22:30:28.396407+00:00 kimi-k2.7-code-xhigh-reasoning-p001-lexen-v1-20260617
47 gpt-6-luna 93.23% p001 lexen-v1 2026-10-09T13:28:56.244462+00:00 gpt-6-luna-max-reasoning-p001-lexen-v1-20261009
48 gpt-5.6-terra 93.23% p003 lexen-v1 2026-07-31T15:02:36.052371+00:00 gpt-5.6-terra-low-reasoning-p003-lexen-v1-20260731
49 openrouter/x-ai/grok-4.3 93.13% p001 lexen-v1 2026-06-14T21:16:55.424172+00:00 grok-4.3-medium-reasoning-p001-lexen-v1-20260614
50 claude-haiku-5-5 93.11% p003 lexen-v1 2026-10-09T13:19:35.390548+00:00 claude-haiku-5.5-max-reasoning-p003-lexen-v1-20261009-128000tokens
51 openrouter/z-ai/glm-5.2 93.11% p001 lexen-v1 2026-07-25T18:24:12.482226+00:00 glm-5.2-xhigh-reasoning-p001-lexen-v1-20260725
52 gpt-5.6-terra 93.09% p003 lexen-v1 2026-07-31T15:06:30.609336+00:00 gpt-5.6-terra-high-reasoning-p003-lexen-v1-20260731
53 openrouter/x-ai/grok-4.3 93.09% p001 lexen-v1 2026-06-14T21:09:10.548112+00:00 grok-4.3-low-reasoning-p001-lexen-v1-20260614
54 gpt-6-luna 93.05% p001 lexen-v1 2026-09-25T07:34:27.760808+00:00 gpt-6-luna-xhigh-reasoning-p001-lexen-v1-20260925
55 claude-opus-4-7 93.01% p001 lexen-v1 2026-06-14T11:43:13.094657+00:00 claude-opus-4.7-medium-reasoning-p001-lexen-v1-20260614
56 claude-haiku-5-5 92.90% p001 lexen-v1 2026-10-09T13:10:20.543118+00:00 claude-haiku-5.5-max-reasoning-p001-lexen-v1-20261009-128000tokens
57 claude-haiku-5-5 92.88% p004 lexen-v1 2026-10-09T13:09:59.275865+00:00 claude-haiku-5.5-max-reasoning-p004-lexen-v1-20261009-128000tokens
58 gpt-5.5 92.88% p003 lexen-v1 2026-06-17T11:29:06.305785+00:00 gpt-5.5-none-reasoning-p003-lexen-v1-20260617
59 openrouter/x-ai/grok-4.3 92.88% p001 lexen-v1 2026-06-14T21:25:12.643492+00:00 grok-4.3-high-reasoning-p001-lexen-v1-20260614
60 openrouter/qwen/qwen3.7-max 92.82% p002 lexen-v1 2026-06-14T21:04:35.848779+00:00 qwen3.7-max-medium-reasoning-p002-lexen-v1-20260614
61 openrouter/qwen/qwen3.7-plus 92.70% p001 lexen-v1 2026-06-14T17:27:03.417524+00:00 qwen3.7-plus-p001-lexen-v1-20260614
62 claude-opus-4-6 92.70% p001 lexen-v1 2026-06-14T11:52:50.971670+00:00 claude-opus-4.6-medium-reasoning-p001-lexen-v1-20260614
63 openrouter/moonshotai/kimi-k2.5 92.66% p001 lexen-v1 2026-06-14T16:01:24.343537+00:00 kimi-k2.5-p001-lexen-v1-20260614
64 gpt-6-luna 92.64% p001 lexen-v1 2026-10-09T13:34:30.153246+00:00 gpt-6-luna-xhigh-reasoning-p001-lexen-v1-20261009
65 gpt-6-luna 92.59% p004 lexen-v1 2026-10-09T13:34:31.990468+00:00 gpt-6-luna-xhigh-reasoning-p004-lexen-v1-20261009
66 gpt-6-luna 92.57% p004 lexen-v1 2026-10-09T13:31:40.447968+00:00 gpt-6-luna-high-reasoning-p004-lexen-v1-20261009
67 claude-haiku-5-5 92.57% p003 lexen-v1 2026-10-09T12:51:01.165778+00:00 claude-haiku-5.5-xhigh-reasoning-p003-lexen-v1-20261009
68 gemini/gemini-3-flash-preview 92.57% p002 lexen-v1 2026-06-14T11:28:13.627340+00:00 gemini-3-flash-p002-lexen-v1-20260614
69 gpt-6-luna 92.55% p001 lexen-v1 2026-10-09T13:31:34.847263+00:00 gpt-6-luna-high-reasoning-p001-lexen-v1-20261009
70 gpt-6-luna 92.53% p001 lexen-v1 2026-10-09T13:29:00.276429+00:00 gpt-6-luna-medium-reasoning-p001-lexen-v1-20261009
71 gpt-5.6-terra 92.53% p003 lexen-v1 2026-07-31T15:05:45.234588+00:00 gpt-5.6-terra-medium-reasoning-p003-lexen-v1-20260731
72 gpt-6-luna 92.47% p004 lexen-v1 2026-10-09T13:29:01.899942+00:00 gpt-6-luna-medium-reasoning-p004-lexen-v1-20261009
73 claude-haiku-5-5 92.45% p001 lexen-v1 2026-10-09T12:46:56.159729+00:00 claude-haiku-5.5-xhigh-reasoning-p001-lexen-v1-20261009
74 openrouter/deepseek/deepseek-v4-pro 92.41% p001 lexen-v1 2026-06-14T18:07:45.068845+00:00 deepseek-v4-pro-high-reasoning-p001-lexen-v1-20260614
75 google/gemma-4-31B-it 92.39% p001 lexen-v1 2026-06-14T13:05:53.315665+00:00 vllm-gemma-4-31b-fp8-h100-p001-lexen-v1-20260614
76 openrouter/moonshotai/kimi-k2.5 92.39% p002 lexen-v1 2026-06-14T16:49:12.308221+00:00 kimi-k2.5-p002-lexen-v1-20260614
77 claude-haiku-5-5 92.31% p001 lexen-v1 2026-10-09T12:44:44.605496+00:00 claude-haiku-5.5-high-reasoning-p001-lexen-v1-20261009
78 google/gemma-4-31B-it 92.29% p003 lexen-v1 2026-06-16T03:16:10.855287+00:00 vllm-gemma-4-31b-fp8-h100-p003-lexen-v1-20260616
79 claude-haiku-5-5 92.26% p001 lexen-v1 2026-10-09T12:42:46.739885+00:00 claude-haiku-5.5-medium-reasoning-p001-lexen-v1-20261009
80 claude-sonnet-5 92.22% p001 lexen-v1 2026-06-30T20:44:35.309868+00:00 claude-sonnet-5-low-reasoning-p001-lexen-v1-20260630
81 openrouter/z-ai/glm-5 92.22% p002 lexen-v1 2026-06-14T19:49:03.779025+00:00 glm-5-low-reasoning-p002-lexen-v1-20260614
82 claude-opus-4-7 92.22% p003 lexen-v1 2026-06-17T08:24:14.201902+00:00 claude-opus-4.7-medium-reasoning-p003-lexen-v1-20260617
83 gpt-6-luna 92.20% p003 lexen-v1 2026-10-09T13:28:10.547280+00:00 gpt-6-luna-max-reasoning-p003-lexen-v1-20261009
84 claude-haiku-5-5 92.20% p003 lexen-v1 2026-10-09T12:46:39.775052+00:00 claude-haiku-5.5-medium-reasoning-p003-lexen-v1-20261009
85 gpt-5.6-luna 92.20% p001 lexen-v1 2026-07-31T14:53:14.435822+00:00 gpt-5.6-luna-xhigh-reasoning-p001-lexen-v1-20260731
86 gpt-6-luna 92.10% p003 lexen-v1 2026-10-09T13:31:05.013842+00:00 gpt-6-luna-high-reasoning-p003-lexen-v1-20261009
87 gpt-6-luna 92.06% p003 lexen-v1 2026-10-09T13:28:45.026093+00:00 gpt-6-luna-medium-reasoning-p003-lexen-v1-20261009
88 gpt-6-luna 92.06% p003 lexen-v1 2026-10-09T13:34:04.401410+00:00 gpt-6-luna-xhigh-reasoning-p003-lexen-v1-20261009
89 claude-haiku-5-5 92.06% p003 lexen-v1 2026-10-09T12:48:40.494512+00:00 claude-haiku-5.5-high-reasoning-p003-lexen-v1-20261009
90 claude-haiku-5-5 92.06% p004 lexen-v1 2026-10-09T12:48:44.543270+00:00 claude-haiku-5.5-high-reasoning-p004-lexen-v1-20261009
91 claude-sonnet-5 91.96% p001 lexen-v1 2026-06-30T20:55:40.203347+00:00 claude-sonnet-5-medium-reasoning-p001-lexen-v1-20260630
92 claude-haiku-5-5 91.92% p001 lexen-v1 2026-10-09T12:40:55.058154+00:00 claude-haiku-5.5-low-reasoning-p001-lexen-v1-20261009
93 claude-sonnet-5 91.83% p001 lexen-v1 2026-06-30T21:18:33.097083+00:00 claude-sonnet-5-xhigh-reasoning-p001-lexen-v1-20260630
94 claude-opus-4-8 91.79% p002 lexen-v1 2026-06-14T12:49:29.194985+00:00 claude-opus-4.8-high-reasoning-p002-lexen-v1-20260614
95 claude-sonnet-5 91.75% p001 lexen-v1 2026-06-30T21:46:42.783013+00:00 claude-sonnet-5-high-reasoning-p001-lexen-v1-20260630
96 gpt-6-luna 91.73% p002 lexen-v1 2026-10-09T13:28:17.445832+00:00 gpt-6-luna-max-reasoning-p002-lexen-v1-20261009
97 claude-haiku-5-5 91.71% p002 lexen-v1 2026-10-09T13:26:03.321498+00:00 claude-haiku-5.5-max-reasoning-p002-lexen-v1-20261009-128000tokens
98 claude-haiku-5-5 91.67% p004 lexen-v1 2026-10-09T12:50:59.572406+00:00 claude-haiku-5.5-xhigh-reasoning-p004-lexen-v1-20261009
99 gpt-5.6-luna 91.61% p001 lexen-v1 2026-07-31T14:52:17.435208+00:00 gpt-5.6-luna-high-reasoning-p001-lexen-v1-20260731
100 openrouter/deepseek/deepseek-v4-pro 91.50% p002 lexen-v1 2026-06-14T18:31:09.158241+00:00 deepseek-v4-pro-high-reasoning-p002-lexen-v1-20260614
101 openrouter/qwen/qwen3.7-plus 91.46% p002 lexen-v1 2026-06-14T17:43:42.620560+00:00 qwen3.7-plus-p002-lexen-v1-20260614
102 gpt-6-luna 91.42% p003 lexen-v1 2026-10-09T13:26:27.869878+00:00 gpt-6-luna-low-reasoning-p003-lexen-v1-20261009
103 gpt-6-luna 91.42% p001 lexen-v1 2026-10-09T13:26:32.899162+00:00 gpt-6-luna-low-reasoning-p001-lexen-v1-20261009
104 claude-haiku-5-5 91.38% p004 lexen-v1 2026-10-09T12:46:44.272647+00:00 claude-haiku-5.5-medium-reasoning-p004-lexen-v1-20261009
105 gpt-5.6-luna 91.26% p003 lexen-v1 2026-07-31T14:56:48.192624+00:00 gpt-5.6-luna-xhigh-reasoning-p003-lexen-v1-20260731
106 gpt-6-luna 91.22% p002 lexen-v1 2026-10-09T13:28:46.899930+00:00 gpt-6-luna-medium-reasoning-p002-lexen-v1-20261009
107 gpt-5-mini 91.22% p003 lexen-v1 2026-06-17T07:47:29.768045+00:00 gpt-5-mini-high-reasoning-p003-lexen-v1-20260617
108 google/gemma-4-31B-it 91.20% p002 lexen-v1 2026-06-14T13:07:36.382312+00:00 vllm-gemma-4-31b-fp8-h100-p002-lexen-v1-20260614
109 gpt-5.6-terra 91.20% p001 lexen-v1 2026-07-31T14:57:15.323671+00:00 gpt-5.6-terra-none-reasoning-p001-lexen-v1-20260731
110 claude-haiku-5-5 91.15% p004 lexen-v1 2026-10-09T12:44:50.523802+00:00 claude-haiku-5.5-low-reasoning-p004-lexen-v1-20261009
111 gpt-6-luna 91.13% p002 lexen-v1 2026-10-09T13:33:32.656010+00:00 gpt-6-luna-xhigh-reasoning-p002-lexen-v1-20261009
112 claude-haiku-5-5 91.13% p002 lexen-v1 2026-10-09T12:51:26.658583+00:00 claude-haiku-5.5-xhigh-reasoning-p002-lexen-v1-20261009
113 gpt-5.6-luna 91.11% p003 lexen-v1 2026-07-31T14:55:49.327524+00:00 gpt-5.6-luna-high-reasoning-p003-lexen-v1-20260731
114 gpt-6-luna 91.09% p004 lexen-v1 2026-10-09T13:26:30.909293+00:00 gpt-6-luna-low-reasoning-p004-lexen-v1-20261009
115 gpt-6-luna 91.05% p002 lexen-v1 2026-10-09T13:31:07.362485+00:00 gpt-6-luna-high-reasoning-p002-lexen-v1-20261009
116 gpt-5.6-terra 91.05% p003 lexen-v1 2026-07-31T15:00:46.990581+00:00 gpt-5.6-terra-none-reasoning-p003-lexen-v1-20260731
117 gpt-5-mini 90.99% p003 lexen-v1 2026-06-17T07:45:03.292014+00:00 gpt-5-mini-medium-reasoning-p003-lexen-v1-20260617
118 claude-haiku-5-5 90.97% p002 lexen-v1 2026-10-09T12:48:50.948018+00:00 claude-haiku-5.5-high-reasoning-p002-lexen-v1-20261009
119 gpt-6-luna 90.93% p002 lexen-v1 2026-10-09T13:26:29.232898+00:00 gpt-6-luna-low-reasoning-p002-lexen-v1-20261009
120 openrouter/deepseek/deepseek-v4-flash 90.93% p001 lexen-v1 2026-06-14T10:48:09.221591+00:00 deepseek-v4-flash-high-reasoning-p001-lexen-v1-20260614
121 gpt-5.4-mini 90.89% p003 lexen-v1 2026-06-17T07:38:06.024744+00:00 gpt-5.4-mini-low-reasoning-p003-lexen-v1-20260617
122 gpt-6-luna 90.76% p001 lexen-v1 2026-09-25T07:37:21.529500+00:00 gpt-6-luna-low-reasoning-p001-lexen-v1-20260925
123 gpt-5-mini 90.72% p001 lexen-v1 2026-06-14T03:01:27.567145+00:00 gpt-5-mini-high-reasoning-p001-lexen-v1-20260614
124 claude-sonnet-4-6 90.72% p001 lexen-v1 2026-06-14T11:25:24.877127+00:00 claude-sonnet-4.6-low-reasoning-p001-lexen-v1-20260614
125 openrouter/minimax/minimax-m3 90.62% p001 lexen-v1 2026-06-14T17:01:11.417107+00:00 minimax-m3-p001-lexen-v1-20260614
126 gpt-5-mini 90.54% p001 lexen-v1 2026-06-14T02:59:58.106259+00:00 gpt-5-mini-medium-reasoning-p001-lexen-v1-20260614
127 claude-haiku-5-5 90.48% p002 lexen-v1 2026-10-09T12:46:43.217278+00:00 claude-haiku-5.5-medium-reasoning-p002-lexen-v1-20261009
128 gpt-5-mini 90.48% p003 lexen-v1 2026-06-17T07:42:53.328684+00:00 gpt-5-mini-low-reasoning-p003-lexen-v1-20260617
129 claude-haiku-4-5 90.48% p001 lexen-v1 2026-06-14T10:58:15.856929+00:00 claude-haiku-4.5-low-reasoning-p001-lexen-v1-20260614
130 gemini/gemini-3.1-flash-lite 90.41% p001 lexen-v1 2026-06-14T10:40:32.982176+00:00 gemini-3.1-flash-lite-p001-lexen-v1-20260614
131 gpt-5.6-luna 90.25% p001 lexen-v1 2026-07-31T14:51:20.032747+00:00 gpt-5.6-luna-medium-reasoning-p001-lexen-v1-20260731
132 claude-sonnet-5 90.17% p003 lexen-v1 2026-06-30T20:43:50.168514+00:00 claude-sonnet-5-low-reasoning-p003-lexen-v1-20260630
133 gpt-5.4-mini 90.10% p001 lexen-v1 2026-06-14T10:36:37.746436+00:00 gpt-5.4-mini-low-reasoning-p001-lexen-v1-20260614
134 gpt-5-mini 90.04% p002 lexen-v1 2026-06-14T03:02:45.517164+00:00 gpt-5-mini-medium-reasoning-p002-lexen-v1-20260614
135 claude-sonnet-5 90.04% p003 lexen-v1 2026-06-30T20:54:00.861583+00:00 claude-sonnet-5-medium-reasoning-p003-lexen-v1-20260630
136 gpt-5-mini 89.94% p001 lexen-v1 2026-06-14T02:59:23.338570+00:00 gpt-5-mini-low-reasoning-p001-lexen-v1-20260614
137 gpt-6-luna 89.90% p001 lexen-v1 2026-10-09T13:24:22.044480+00:00 gpt-6-luna-none-reasoning-p001-lexen-v1-20261009
138 gpt-5.6-luna 89.80% p003 lexen-v1 2026-07-31T14:55:04.963603+00:00 gpt-5.6-luna-medium-reasoning-p003-lexen-v1-20260731
139 openrouter/deepseek/deepseek-v4-flash 89.69% p002 lexen-v1 2026-06-14T11:07:29.161962+00:00 deepseek-v4-flash-high-reasoning-p002-lexen-v1-20260614
140 claude-sonnet-5 89.67% p003 lexen-v1 2026-06-30T21:45:59.721539+00:00 claude-sonnet-5-high-reasoning-p003-lexen-v1-20260630
141 gemini/gemini-2.5-flash 89.61% p002 lexen-v1 2026-06-14T11:07:54.336960+00:00 gemini-2.5-flash-p002-lexen-v1-20260614
142 Qwen/Qwen3.6-27B-FP8 89.51% p001 lexen-v1 2026-06-14T03:37:04.989093+00:00 vllm-qwen3.6-27b-fp8-h200-p001-lexen-v1-20260614
143 gpt-5.4-mini 89.49% p002 lexen-v1 2026-06-14T10:37:18.500343+00:00 gpt-5.4-mini-low-reasoning-p002-lexen-v1-20260614
144 google/gemma-4-26B-A4B-it 89.43% p001 lexen-v1 2026-06-14T13:02:48.331932+00:00 vllm-gemma-4-26b-a4b-fp8-a100-p001-lexen-v1-20260614
145 gemini/gemini-2.5-flash 89.41% p001 lexen-v1 2026-06-14T11:03:39.454582+00:00 gemini-2.5-flash-p001-lexen-v1-20260614
146 Qwen/Qwen3.6-27B-FP8 89.36% p001 lexen-v1 2026-06-14T09:20:49.931691+00:00 vllm-qwen3.6-27b-fp8-h100-p001-lexen-v1-20260614
147 google/gemma-4-26B-A4B-it 89.32% p001 lexen-v1 2026-06-14T03:43:54.686558+00:00 vllm-gemma-4-26b-a4b-fp8-h200-p001-lexen-v1-20260614
148 Qwen/Qwen3.5-397B-A17B 89.24% p001 lexen-v1 2026-06-14T17:58:20.590182+00:00 vllm-qwen3.5-397b-a17b-gptq-b300-p001-lexen-v1-20260614
149 google/gemma-4-26B-A4B-it 89.20% p001 lexen-v1 2026-06-14T12:56:57.382019+00:00 vllm-gemma-4-26b-a4b-fp8-h100-p001-lexen-v1-20260614
150 gpt-4.1 89.14% p003 lexen-v1 2026-06-17T07:33:57.499800+00:00 gpt-4.1-p003-lexen-v1-20260617
151 google/gemma-4-26B-A4B-it 89.12% p003 lexen-v1 2026-06-16T02:50:20.177857+00:00 vllm-gemma-4-26b-a4b-fp8-h100-p003-lexen-v1-20260616
152 gemini/gemini-3.1-flash-lite 89.08% p002 lexen-v1 2026-06-14T10:51:07.533822+00:00 gemini-3.1-flash-lite-p002-lexen-v1-20260614
153 Qwen/Qwen3.5-27B 89.06% p001 lexen-v1 2026-06-14T21:46:09.965074+00:00 vllm-qwen3.5-27b-bf16-a100-p001-lexen-v1-20260614
154 gpt-6-luna 88.97% p003 lexen-v1 2026-10-09T13:24:22.366801+00:00 gpt-6-luna-none-reasoning-p003-lexen-v1-20261009
155 Qwen/Qwen3.5-27B 88.97% p001 lexen-v1 2026-06-14T21:14:44.906254+00:00 vllm-qwen3.5-27b-bf16-h200-p001-lexen-v1-20260614
156 gpt-6-luna 88.97% p004 lexen-v1 2026-10-09T13:24:22.577625+00:00 gpt-6-luna-none-reasoning-p004-lexen-v1-20261009
157 claude-haiku-5-5 88.93% p003 lexen-v1 2026-10-09T12:44:49.985518+00:00 claude-haiku-5.5-low-reasoning-p003-lexen-v1-20261009
158 Qwen/Qwen3.5-27B 88.89% p001 lexen-v1 2026-06-14T18:22:27.863955+00:00 vllm-qwen3.5-27b-bf16-h100-p001-lexen-v1-20260614
159 claude-sonnet-4-6 88.89% p002 lexen-v1 2026-06-14T11:34:12.718972+00:00 claude-sonnet-4.6-low-reasoning-p002-lexen-v1-20260614
160 gpt-5.6-luna 88.83% p003 lexen-v1 2026-07-31T14:54:22.871059+00:00 gpt-5.6-luna-low-reasoning-p003-lexen-v1-20260731
161 zai-org/GLM-4.6 88.71% p001 lexen-v1 2026-06-14T14:17:06.058829+00:00 vllm-glm-4.6-awq-b300-p001-lexen-v1-20260614
162 gpt-4.1 88.69% p001 lexen-v1 2026-06-14T10:22:33.163281+00:00 gpt-4.1-p001-lexen-v1-20260614
163 gpt-6-luna 88.44% p002 lexen-v1 2026-10-09T13:24:21.916168+00:00 gpt-6-luna-none-reasoning-p002-lexen-v1-20261009
164 gpt-5.6-luna 88.34% p001 lexen-v1 2026-07-31T14:50:39.708815+00:00 gpt-5.6-luna-low-reasoning-p001-lexen-v1-20260731
165 gpt-4.1 87.86% p002 lexen-v1 2026-06-14T10:31:43.235840+00:00 gpt-4.1-p002-lexen-v1-20260614
166 gpt-5.6-luna 87.80% p003 lexen-v1 2026-07-31T14:53:46.527522+00:00 gpt-5.6-luna-none-reasoning-p003-lexen-v1-20260731
167 gpt-5.6-luna 87.72% p001 lexen-v1 2026-07-31T14:49:51.911911+00:00 gpt-5.6-luna-none-reasoning-p001-lexen-v1-20260731
168 claude-haiku-5-5 87.64% p002 lexen-v1 2026-10-09T12:44:47.540623+00:00 claude-haiku-5.5-low-reasoning-p002-lexen-v1-20261009
169 claude-haiku-4-5 87.60% p002 lexen-v1 2026-06-14T11:17:37.678627+00:00 claude-haiku-4.5-low-reasoning-p002-lexen-v1-20260614
170 meta-llama/Llama-4-Maverick-17B-128E-Instruct 87.55% p001 lexen-v1 2026-06-14T15:13:31.931784+00:00 vllm-llama-4-maverick-int4-b300-p001-lexen-v1-20260614
171 google/gemma-4-26B-A4B-it 87.25% p002 lexen-v1 2026-06-14T12:57:33.409617+00:00 vllm-gemma-4-26b-a4b-fp8-h100-p002-lexen-v1-20260614
172 google/gemma-4-26B-A4B-it 87.25% p002 lexen-v1 2026-06-14T03:44:42.664730+00:00 vllm-gemma-4-26b-a4b-fp8-h200-p002-lexen-v1-20260614
173 Qwen/Qwen3.6-27B-FP8 87.20% p002 lexen-v1 2026-06-14T09:22:18.123666+00:00 vllm-qwen3.6-27b-fp8-h100-p002-lexen-v1-20260614
174 Qwen/Qwen3.6-27B-FP8 87.18% p002 lexen-v1 2026-06-14T03:38:33.776628+00:00 vllm-qwen3.6-27b-fp8-h200-p002-lexen-v1-20260614
175 zai-org/GLM-4.6 87.12% p002 lexen-v1 2026-06-14T14:21:11.936952+00:00 vllm-glm-4.6-awq-b300-p002-lexen-v1-20260614
176 google/gemma-4-26B-A4B-it 87.10% p002 lexen-v1 2026-06-14T13:04:18.320439+00:00 vllm-gemma-4-26b-a4b-fp8-a100-p002-lexen-v1-20260614
177 Qwen/Qwen3.5-122B-A10B 87.06% p001 lexen-v1 2026-06-14T20:59:20.246395+00:00 vllm-qwen3.5-122b-a10b-fp8-h200-p001-lexen-v1-20260614
178 Qwen/Qwen3.5-122B-A10B 87.02% p001 lexen-v1 2026-06-14T17:26:39.154524+00:00 vllm-qwen3.5-122b-a10b-fp8-b300-p001-lexen-v1-20260614
179 Qwen/Qwen3.5-397B-A17B 86.69% p002 lexen-v1 2026-06-14T18:01:16.443151+00:00 vllm-qwen3.5-397b-a17b-gptq-b300-p002-lexen-v1-20260614
180 gpt-5.4-nano 86.63% p003 lexen-v1 2026-06-17T07:39:04.268726+00:00 gpt-5.4-nano-low-reasoning-p003-lexen-v1-20260617
181 Qwen/Qwen3-235B-A22B-Instruct-2507 86.59% p001 lexen-v1 2026-06-14T20:01:55.579872+00:00 vllm-qwen3-235b-2507-awq-h200-p001-lexen-v1-20260614
182 Qwen/Qwen3.5-27B 86.55% p002 lexen-v1 2026-06-14T18:24:27.165748+00:00 vllm-qwen3.5-27b-bf16-h100-p002-lexen-v1-20260614
183 Qwen/Qwen3.5-27B 86.55% p002 lexen-v1 2026-06-14T21:16:43.650053+00:00 vllm-qwen3.5-27b-bf16-h200-p002-lexen-v1-20260614
184 gpt-5-nano 86.48% p003 lexen-v1 2026-06-17T07:52:26.335235+00:00 gpt-5-nano-medium-reasoning-p003-lexen-v1-20260617
185 Qwen/Qwen3.5-27B 86.46% p002 lexen-v1 2026-06-14T21:51:15.471462+00:00 vllm-qwen3.5-27b-bf16-a100-p002-lexen-v1-20260614
186 gpt-5.4-nano 86.26% p001 lexen-v1 2026-06-14T10:26:49.278471+00:00 gpt-5.4-nano-low-reasoning-p001-lexen-v1-20260614
187 google/gemma-4-E4B-it 85.58% p003 lexen-v1 2026-06-16T12:12:21.657535+00:00 vllm-gemma-4-e4b-fp8-h100-p003-lexen-v1-20260616-thinking
188 Qwen/Qwen3.6-35B-A3B-FP8 85.56% p001 lexen-v1 2026-06-14T19:07:57.673409+00:00 vllm-qwen3.6-35b-a3b-fp8-h100-p001-lexen-v1-20260614
189 Qwen/Qwen3.6-35B-A3B-FP8 85.50% p001 lexen-v1 2026-06-14T03:54:43.714581+00:00 vllm-qwen3.6-35b-a3b-fp8-h200-p001-lexen-v1-20260614
190 gpt-5-nano 85.50% p002 lexen-v1 2026-06-14T03:09:12.248467+00:00 gpt-5-nano-medium-reasoning-p002-lexen-v1-20260614
191 Qwen/Qwen3.5-122B-A10B 85.48% p002 lexen-v1 2026-06-14T21:01:03.796592+00:00 vllm-qwen3.5-122b-a10b-fp8-h200-p002-lexen-v1-20260614
192 Qwen/Qwen3.5-122B-A10B 85.29% p002 lexen-v1 2026-06-14T17:28:29.170586+00:00 vllm-qwen3.5-122b-a10b-fp8-b300-p002-lexen-v1-20260614
193 Qwen/Qwen3-235B-A22B 85.27% p001 lexen-v1 2026-06-14T17:02:46.131355+00:00 vllm-qwen3-235b-a22b-fp8-b300-p001-lexen-v1-20260614
194 CohereLabs/c4ai-command-a-03-2025 85.23% p001 lexen-v1 2026-06-14T12:51:16.703271+00:00 vllm-command-a-fp8-h200-p001-lexen-v1-20260614
195 google/gemma-4-E4B-it 85.19% p001 lexen-v1 2026-06-15T16:54:34.206811+00:00 vllm-gemma-4-e4b-fp8-h100-p001-lexen-v1-20260615-thinking
196 gpt-5-mini 85.00% p001 lexen-v1 2026-06-14T02:58:57.465838+00:00 gpt-5-mini-minimal-reasoning-p001-lexen-v1-20260614
197 Qwen/Qwen2.5-72B-Instruct 84.84% p002 lexen-v1 2026-06-14T21:23:56.668649+00:00 vllm-qwen2.5-72b-awq-a100-p002-lexen-v1-20260614
198 Qwen/Qwen2.5-72B-Instruct 84.82% p002 lexen-v1 2026-06-14T18:10:51.795477+00:00 vllm-qwen2.5-72b-awq-h100-p002-lexen-v1-20260614
199 Qwen/Qwen2.5-72B-Instruct 84.82% p002 lexen-v1 2026-06-14T19:36:35.051728+00:00 vllm-qwen2.5-72b-awq-h200-p002-lexen-v1-20260614
200 Qwen/Qwen3-235B-A22B-Instruct-2507 84.74% p002 lexen-v1 2026-06-14T20:04:54.740808+00:00 vllm-qwen3-235b-2507-awq-h200-p002-lexen-v1-20260614
201 Qwen/Qwen3.5-35B-A3B 84.45% p001 lexen-v1 2026-06-14T21:29:51.511649+00:00 vllm-qwen3.5-35b-a3b-bf16-h200-p001-lexen-v1-20260614
202 gpt-5-nano 84.32% p001 lexen-v1 2026-06-14T03:08:14.245995+00:00 gpt-5-nano-high-reasoning-p001-lexen-v1-20260614
203 Qwen/Qwen3-235B-A22B 84.08% p001 lexen-v1 2026-06-14T20:30:58.208934+00:00 vllm-qwen3-235b-a22b-awq-h200-p001-lexen-v1-20260614
204 nvidia/NVIDIA-Nemotron-3-Super-120B-A12B 83.93% p003 lexen-v1 2026-06-17T08:49:01.056118+00:00 vllm-nemotron-3-super-120b-fp8-h200-p003-lexen-v1-20260617
205 gpt-5.4-nano 83.93% p002 lexen-v1 2026-06-14T10:27:23.808460+00:00 gpt-5.4-nano-low-reasoning-p002-lexen-v1-20260614
206 claude-haiku-5-5 83.79% p001 lexen-v1 2026-10-09T12:40:15.003520+00:00 claude-haiku-5.5-none-reasoning-p001-lexen-v1-20261009
207 gpt-5-mini 83.77% p003 lexen-v1 2026-06-17T07:40:43.737804+00:00 gpt-5-mini-minimal-reasoning-p003-lexen-v1-20260617
208 claude-haiku-5-5 83.75% p004 lexen-v1 2026-10-09T12:42:38.421130+00:00 claude-haiku-5.5-none-reasoning-p004-lexen-v1-20261009
209 gpt-4.1-mini 83.69% p001 lexen-v1 2026-06-14T03:10:31.779383+00:00 gpt-4.1-mini-p001-lexen-v1-20260614
210 gpt-5-nano 83.56% p003 lexen-v1 2026-06-17T07:49:45.901920+00:00 gpt-5-nano-low-reasoning-p003-lexen-v1-20260617
211 gpt-5-nano 83.56% p001 lexen-v1 2026-06-14T03:04:55.641744+00:00 gpt-5-nano-medium-reasoning-p001-lexen-v1-20260614
212 google/gemma-4-E4B-it 83.44% p001 lexen-v1 2026-06-14T03:25:03.326707+00:00 vllm-gemma-4-e4b-fp8-h200-p001-lexen-v1-20260614
213 Qwen/Qwen2.5-72B-Instruct 83.44% p001 lexen-v1 2026-06-14T21:09:10.349327+00:00 vllm-qwen2.5-72b-awq-a100-p001-lexen-v1-20260614
214 Qwen/Qwen2.5-72B-Instruct 83.42% p001 lexen-v1 2026-06-14T19:32:09.858826+00:00 vllm-qwen2.5-72b-awq-h200-p001-lexen-v1-20260614
215 Qwen/Qwen2.5-72B-Instruct 83.40% p001 lexen-v1 2026-06-14T18:06:23.582043+00:00 vllm-qwen2.5-72b-awq-h100-p001-lexen-v1-20260614
216 google/gemma-4-E4B-it 83.30% p002 lexen-v1 2026-06-16T12:07:56.371195+00:00 vllm-gemma-4-e4b-fp8-h100-p002-lexen-v1-20260616-thinking
217 gpt-4o-mini 82.90% p002 lexen-v1 2026-06-14T03:13:09.202699+00:00 gpt-4o-mini-p002-lexen-v1-20260614
218 Qwen/Qwen3.6-35B-A3B-FP8 82.72% p002 lexen-v1 2026-06-14T19:08:36.001596+00:00 vllm-qwen3.6-35b-a3b-fp8-h100-p002-lexen-v1-20260614
219 Qwen/Qwen3.6-35B-A3B-FP8 82.70% p002 lexen-v1 2026-06-14T03:55:37.865365+00:00 vllm-qwen3.6-35b-a3b-fp8-h200-p002-lexen-v1-20260614
220 gpt-4o-mini 82.70% p001 lexen-v1 2026-06-14T03:11:36.212233+00:00 gpt-4o-mini-p001-lexen-v1-20260614
221 nvidia/NVIDIA-Nemotron-3-Super-120B-A12B 82.35% p002 lexen-v1 2026-06-14T19:12:56.557834+00:00 vllm-nemotron-3-super-120b-fp8-h200-p002-lexen-v1-20260614
222 claude-haiku-5-5 82.31% p002 lexen-v1 2026-10-09T12:42:24.087817+00:00 claude-haiku-5.5-none-reasoning-p002-lexen-v1-20261009
223 Qwen/Qwen3-235B-A22B 82.27% p002 lexen-v1 2026-06-14T17:04:02.610404+00:00 vllm-qwen3-235b-a22b-fp8-b300-p002-lexen-v1-20260614
224 claude-haiku-5-5 82.14% p003 lexen-v1 2026-10-09T12:42:27.607515+00:00 claude-haiku-5.5-none-reasoning-p003-lexen-v1-20261009
225 Qwen/Qwen3.5-35B-A3B 82.10% p002 lexen-v1 2026-06-14T21:30:47.805630+00:00 vllm-qwen3.5-35b-a3b-bf16-h200-p002-lexen-v1-20260614
226 nvidia/NVIDIA-Nemotron-3-Super-120B-A12B 81.86% p001 lexen-v1 2026-06-14T19:11:26.351859+00:00 vllm-nemotron-3-super-120b-fp8-h200-p001-lexen-v1-20260614
227 meta-llama/Llama-4-Maverick-17B-128E-Instruct 81.53% p002 lexen-v1 2026-06-14T15:17:21.457755+00:00 vllm-llama-4-maverick-int4-b300-p002-lexen-v1-20260614
228 google/gemma-4-E4B-it 81.44% p003 lexen-v1 2026-06-16T02:47:50.795294+00:00 vllm-gemma-4-e4b-fp8-h100-p003-lexen-v1-20260616
229 Qwen/Qwen3-235B-A22B 81.03% p002 lexen-v1 2026-06-14T20:34:00.314833+00:00 vllm-qwen3-235b-a22b-awq-h200-p002-lexen-v1-20260614
230 Qwen/Qwen3.5-9B 80.91% p001 lexen-v1 2026-06-14T22:26:23.261470+00:00 vllm-qwen3.5-9b-bf16-a100-p001-lexen-v1-20260614
231 Qwen/Qwen3.5-9B 80.89% p001 lexen-v1 2026-06-14T21:37:26.714544+00:00 vllm-qwen3.5-9b-bf16-h200-p001-lexen-v1-20260614
232 Qwen/Qwen3.5-9B 80.79% p001 lexen-v1 2026-06-14T18:55:28.122562+00:00 vllm-qwen3.5-9b-bf16-h100-p001-lexen-v1-20260614
233 gpt-4.1-mini 80.54% p002 lexen-v1 2026-06-14T03:10:47.348916+00:00 gpt-4.1-mini-p002-lexen-v1-20260614
234 zai-org/GLM-4-9B-0414 80.46% p002 lexen-v1 2026-06-14T13:13:51.676910+00:00 vllm-glm-4-9b-bf16-a100-p002-lexen-v1-20260614
235 zai-org/GLM-4-9B-0414 79.78% p001 lexen-v1 2026-06-14T13:12:11.870521+00:00 vllm-glm-4-9b-bf16-a100-p001-lexen-v1-20260614
236 mistralai/Mistral-Small-3.2-24B-Instruct-2506 79.39% p002 lexen-v1 2026-06-14T04:09:21.457204+00:00 vllm-mistral-small-3.2-fp8-h200-p002-lexen-v1-20260614
237 mistralai/Mistral-Small-3.2-24B-Instruct-2506 79.28% p002 lexen-v1 2026-06-14T17:01:31.952947+00:00 vllm-mistral-small-3.2-fp8-h100-p002-lexen-v1-20260614
238 mistralai/Mistral-Small-3.2-24B-Instruct-2506 79.00% p002 lexen-v1 2026-06-14T19:43:05.518865+00:00 vllm-mistral-small-3.2-fp8-a100-p002-lexen-v1-20260614
239 google/gemma-4-E4B-it 78.89% p002 lexen-v1 2026-06-14T03:25:43.646502+00:00 vllm-gemma-4-e4b-fp8-h200-p002-lexen-v1-20260614
240 google/gemma-4-E2B-it 78.89% p003 lexen-v1 2026-06-16T11:55:39.619700+00:00 vllm-gemma-4-e2b-fp8-h100-p003-lexen-v1-20260616-thinking
241 google/gemma-4-E4B-it 78.87% p002 lexen-v1 2026-06-14T09:10:08.959121+00:00 vllm-gemma-4-e4b-fp8-h100-p002-lexen-v1-20260614
242 tencent/Hunyuan-A13B-Instruct 78.73% p001 lexen-v1 2026-06-14T13:56:24.339501+00:00 vllm-hunyuan-a13b-int4-a100-p001-lexen-v1-20260614
243 zai-org/GLM-4.7-Flash 77.60% p001 lexen-v1 2026-06-14T13:25:17.068123+00:00 vllm-glm-4.7-flash-bf16-a100-p001-lexen-v1-20260614
244 mistralai/Mistral-Small-3.2-24B-Instruct-2506 77.17% p001 lexen-v1 2026-06-14T19:37:17.468158+00:00 vllm-mistral-small-3.2-fp8-a100-p001-lexen-v1-20260614
245 google/gemma-4-E2B-it 77.12% p002 lexen-v1 2026-06-16T11:51:52.132443+00:00 vllm-gemma-4-e2b-fp8-h100-p002-lexen-v1-20260616-thinking
246 gpt-5-nano 76.98% p001 lexen-v1 2026-06-14T03:03:34.449002+00:00 gpt-5-nano-low-reasoning-p001-lexen-v1-20260614
247 mistralai/Mistral-Small-3.2-24B-Instruct-2506 76.75% p001 lexen-v1 2026-06-14T17:00:10.756548+00:00 vllm-mistral-small-3.2-fp8-h100-p001-lexen-v1-20260614
248 mistralai/Mistral-Small-3.2-24B-Instruct-2506 76.61% p001 lexen-v1 2026-06-14T04:08:01.202862+00:00 vllm-mistral-small-3.2-fp8-h200-p001-lexen-v1-20260614
249 Qwen/Qwen3.5-9B 76.34% p002 lexen-v1 2026-06-14T18:56:17.224420+00:00 vllm-qwen3.5-9b-bf16-h100-p002-lexen-v1-20260614
250 Qwen/Qwen3.5-9B 76.28% p002 lexen-v1 2026-06-14T21:38:16.517970+00:00 vllm-qwen3.5-9b-bf16-h200-p002-lexen-v1-20260614
251 zai-org/GLM-4.7-Flash 75.70% p002 lexen-v1 2026-06-14T13:26:48.163045+00:00 vllm-glm-4.7-flash-bf16-a100-p002-lexen-v1-20260614
252 allenai/Olmo-3.1-32B-Instruct 73.98% p001 lexen-v1 2026-06-14T17:48:27.265217+00:00 vllm-olmo-3.1-32b-fp8-h100-p001-lexen-v1-20260614
253 allenai/Olmo-3.1-32B-Instruct 73.32% p002 lexen-v1 2026-06-14T17:49:57.208847+00:00 vllm-olmo-3.1-32b-fp8-h100-p002-lexen-v1-20260614
254 gpt-4.1-nano 73.28% p002 lexen-v1 2026-06-14T03:11:19.453636+00:00 gpt-4.1-nano-p002-lexen-v1-20260614
255 ibm-granite/granite-4.1-8b-fp8 70.17% p001 lexen-v1 2026-06-14T03:08:55.286627+00:00 vllm-granite-4.1-8b-fp8-h200-p001-lexen-v1-20260614
256 google/gemma-4-E2B-it 70.13% p001 lexen-v1 2026-06-14T03:19:39.961246+00:00 vllm-gemma-4-e2b-fp8-h200-p001-lexen-v1-20260614
257 gpt-4.1-nano 70.07% p001 lexen-v1 2026-06-14T03:10:59.879737+00:00 gpt-4.1-nano-p001-lexen-v1-20260614
258 ibm-granite/granite-4.1-8b-fp8 69.92% p001 lexen-v1 2026-06-14T08:55:32.038625+00:00 vllm-granite-4.1-8b-fp8-h100-p001-lexen-v1-20260614
259 nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B 69.22% p002 lexen-v1 2026-06-14T17:08:45.708843+00:00 vllm-nemotron-3-nano-30b-fp8-h100-p002-lexen-v1-20260614
260 ibm-granite/granite-4.1-8b 69.02% p001 lexen-v1 2026-06-14T13:38:08.800623+00:00 vllm-granite-4.1-8b-bf16-a100-p001-lexen-v1-20260614
261 nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B 65.34% p003 lexen-v1 2026-06-17T08:25:49.592029+00:00 vllm-nemotron-3-nano-30b-fp8-h100-p003-lexen-v1-20260617
262 google/gemma-4-E2B-it 65.07% p003 lexen-v1 2026-06-16T02:48:05.643909+00:00 vllm-gemma-4-e2b-fp8-h100-p003-lexen-v1-20260616
263 microsoft/Phi-4-mini-instruct 63.98% p001 lexen-v1 2026-06-14T20:23:39.820467+00:00 vllm-phi-4-mini-bf16-a100-p001-lexen-v1-20260614
264 nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B 63.55% p001 lexen-v1 2026-06-14T17:08:07.789507+00:00 vllm-nemotron-3-nano-30b-fp8-h100-p001-lexen-v1-20260614
265 google/gemma-4-E2B-it 61.65% p002 lexen-v1 2026-06-14T09:05:03.172757+00:00 vllm-gemma-4-e2b-fp8-h100-p002-lexen-v1-20260614
266 google/gemma-4-E2B-it 61.63% p002 lexen-v1 2026-06-14T03:20:22.722243+00:00 vllm-gemma-4-e2b-fp8-h200-p002-lexen-v1-20260614
267 gpt-5-nano 59.06% p001 lexen-v1 2026-06-14T03:03:01.790422+00:00 gpt-5-nano-minimal-reasoning-p001-lexen-v1-20260614
268 meta-llama/Llama-3.1-8B-Instruct 58.82% p001 lexen-v1 2026-06-14T14:08:58.621756+00:00 vllm-llama-3.1-8b-bf16-a100-p001-lexen-v1-20260614
269 meta-llama/Llama-3.1-8B-Instruct 58.05% p001 lexen-v1 2026-06-14T03:14:37.607430+00:00 vllm-llama-3.1-8b-fp8-h200-p001-lexen-v1-20260614
270 meta-llama/Llama-3.1-8B-Instruct 57.99% p001 lexen-v1 2026-06-14T08:59:47.839377+00:00 vllm-llama-3.1-8b-fp8-h100-p001-lexen-v1-20260614
271 meta-llama/Llama-3.1-8B-Instruct 44.31% p002 lexen-v1 2026-06-14T09:00:22.409515+00:00 vllm-llama-3.1-8b-fp8-h100-p002-lexen-v1-20260614
272 meta-llama/Llama-3.1-8B-Instruct 44.21% p002 lexen-v1 2026-06-14T03:15:18.793310+00:00 vllm-llama-3.1-8b-fp8-h200-p002-lexen-v1-20260614
273 meta-llama/Llama-3.1-8B-Instruct 39.85% p002 lexen-v1 2026-06-14T14:10:27.680965+00:00 vllm-llama-3.1-8b-bf16-a100-p002-lexen-v1-20260614