BenchLeader
Menu
Best LLMsChoose a modelLeaderboardsModelsBenchmarksProvidersReleases16

All models

1233 models with at least one independent benchmark result, plus this week’s new arrivals. Another 369 appear in price lists only and are left out here; they still have model pages you can search for.

Looking at two of them? Put any models side by side.

754 of 754
#
1Claude Opus 5.5max72.7±6$8.0095609 s1M2026-09-222026-10-19
2Gemini 4 Argonhigh71.0±3$4.008349 s1.0M2026-09-302026-10-19
3Muse Wonder Fullmax70.7±9–––1M2026-10-122026-10-19
4GPT-6 Astramax70.6±4$20.0064328 s1.1M2026-09-022026-10-19
5Claude Fable 5.1max70.6±5$20.0069221 s1M2026-09-012026-10-19
6GPT-6.1 Solmax70.0±3$4.0055248 s1.1M2026-09-292026-10-19
7Claude Sonnet 5.5max69.5±5$4.00137428 s1M2026-09-282026-10-19
8Claude Fable 5max69.4±4$20.006775 s1M2026-06-092026-06-09
9Claude Opus 5max68.9±3$10.005469 s1M2026-07-242026-10-19
10GPT-5.6 Solmax68.0±4$8.008493 s1.1M2026-07-092026-10-14
11Muse Wondermax67.5±5$8.0016145 s1.0M2026-10-122026-10-19
12Muse Spark 1.3max67.2±4$2.0012880 s1.0M2026-09-022026-10-19
13GPT-6 Solmax66.6±4$4.0011890 s1.1M2026-09-222026-10-19
14GPT-5.5xhigh66.1±4$11.259252 s1.1M2026-04-232026-10-19
15GPT-5.5 Proxhigh65.3±8$67.50234.35 s1.1M2026-04-232026-04-23 · stale
16Kimi K3max64.9±3$6.004252 s1.0M2026-07-162026-10-19
17GPT-5.4xhigh64.8±3$5.63112134 s1.1M2026-03-052026-10-13
18Gemini 3.8 Flashhigh64.5±4$1.5014426 s1.0M2026-09-022026-10-19
19Muse Spark(Apr 2026)64.4±3–––262k2026-04-082026-10-19
20GPT-5.6 Terramax64.4±5$4.50133128 s1.1M2026-07-092026-10-14
21MiMo-V2.6-Pro64.2±4$0.5485043 s1.0M2026-09-212026-10-19
22Grok 4.6medium64.2±4$3.006831 s500k2026-08-112026-08-12
23Grok 4.7high64.0±7$3.008733 s500k2026-09-212026-09-21
24GPT-5.3-Codexxhigh63.8±5$4.8112058 s400k2026-02-052026-10-14
25GLM 5.3max63.6±3$2.158426 s1M2026-08-182026-10-19
26Gemini 3.7 Flashhigh63.5±4$0.755802.48 s1.0M2026-08-132026-10-19
27GPT-5.4 Pro63.5±3$67.50106.11 s1.1M2026-03-042026-10-07
28Claude Opus 4.763.4±3$10.00601.23 s1M2026-04-162026-10-19
29Claude Opus 4.8max63.4±5$10.006345 s1M2026-05-282026-06-01
30Qwen3.8 Maxmax63.3±4$3.004053 s1M2026-08-032026-10-19
31Gemini 3.5 Flashhigh63.2±3$3.3820815 s1.0M2026-05-192026-10-19
32Muse Spark 1.2xhigh63.2±5$2.0031522 s1.0M2026-08-052026-10-19
33Qwen3.8 2.4T A95B63.2±5$3.004251 s1M2026-08-122026-08-12
34NewDeepSeek V4.1 Flash 1017max63.1±7$0.52520911 s1.0M2026-10-172026-10-17
35Muse Spark 1.162.9±6$2.002361.68 s1.0M2026-07-092026-10-19
36Claude Opus 4.6high62.9±2$10.00401.21 s1M2026-02-052026-10-19
37GLM 5.3 Flash62.8±4$0.2387729 s1M2026-08-202026-10-19
38DeepSeek V4 Promax62.7±3$1.9810347 s1.0M2026-08-132026-10-14
39GLM 5.2max62.4±4$2.158826 s1M2026-06-162026-10-19
40Qwen3.6 Maxmax62.4±3$2.96––246k2026-04-202026-10-19
41Gemini 3.6 Flashhigh62.1±3$1.5021416 s1.0M2026-07-212026-10-19
42DeepSeek V4.1 Flashmax62.0±4$0.5252409.25 s1.0M2026-09-102026-10-19
43NewMiniMax-M3.1-Flash61.9±6$0.26210520 s1M2026-10-192026-10-19
44Claude Haiku 5.5xhigh61.5±5$0.20019260 s1M2026-10-072026-10-07
45NewMuse Spark Openxhigh61.2±4$2.0014115 s1.0M2026-10-152026-10-15
46DeepSeek V4 Flashmax61.1±4$0.175145121 s1.0M2026-07-312026-07-31
47Gemini 3.1 Pro60.7±4$4.5013121 s1.0M2026-02-192026-10-19
48Qwen3 7max60.7±4$3.7520114 s1M2026-05-192026-10-19
49GPT-5.2xhigh60.7±4$4.8183104 s400k2025-12-112026-10-13
50Step 5 Preview60.6±5$1.439224 s1M2026-09-182026-10-19
51Gemini 3 Pro60.5±3––––2025-11-182026-10-19
52Claude Sonnet 5high60.3±2$4.007111 s1M2026-06-302026-10-19
53Qwen3.8-Flash-Next60.3±7$0.2305240 s256k2026-08-262026-10-19
54GPT-6 Lunamax60.1±3$0.20012490 s1.1M2026-09-222026-10-19
55Claude Opus 4.5thinking60.0±3$10.005717 s200k2025-11-242026-10-13
56GPT-5.6 Lunamax59.9±4$0.45013497 s1.1M2026-07-092026-10-14
57MiMo-V2.6-Flash59.8±3$0.1755343 s1.0M2026-09-212026-10-19
58GPT-5 Pro59.8±6$41.25––400k2025-08-072025-11-13 · stale
59o359.5±4$3.501496.53 s200k2025-04-162026-10-19
60Kimi K2.6thinking59.4±4$1.717264 s262k2026-04-202026-04-20 · stale
61GPT-5.2-Codexxhigh59.4±5$4.8112476 s400k2025-12-182025-12-11 · stale
62Grok 4.5high59.3±5$3.006412 s500k2026-07-082026-10-14
63Gemini 3 Flashthinking59.2±5$1.132146.09 s1.0M2025-12-172025-12-17 · stale
64Agnes 2.5 Pro Beta59.1±4$0.15011419 s1M2026-08-262026-08-26
65Deepseek v4 Pro Highhigh59.0±5––––2026-04-242026-10-15
66GLM-5thinking58.9±4$1.557543 s205k2026-02-112026-10-13
67Qwen3.6 Plus58.8±4$1.1356101 s1M2026-03-312026-10-19
68Grok 4.20thinking58.7±4$1.5610518 s2M2026-02-172026-10-19
69Mimo v2 Pro58.7±5–––1M2026-03-182026-10-19
70Grok 4.3medium58.7±7$1.567220 s1M2026-04-172026-04-30
71Dola Seed 2.0 Pro58.7±1–––––2026-10-19
72Grok 4.20 Multi-Agent58.7±2$1.563565.47 s2M2026-03-092026-10-19
73Qwen3.7 Plus58.6±6$0.7005737 s1M2026-06-022026-10-19
74NewMuse Spark Open 816B A42Bxhigh58.6±6$2.00––1.0M2026-10-152026-10-15
75Claude Sonnet 4.5high58.3±7$6.00381.12 s200k2025-09-292026-10-19
76Deepseek v4 Flash Visionmax58.3±5$0.66020211 s1.0M2026-08-212026-08-21
77GPT-5.5 Instant58.1±5$11.2515614 s400k2026-05-052026-10-19
78GPT-5high58.0±3$3.4410963 s400k2025-08-072026-10-19
79Grok 458.0±3$6.00839.15 s256k2025-07-092026-10-19
80GPT-5.1high57.8±4$3.4411635 s400k2025-11-122026-10-19
81Motif 357.8±5–––262k2026-08-122026-08-12
82Kimi K2.5thinking57.7±4$1.206647 s262k2026-01-272026-10-19
83Mimo v2 Omni57.7±4–––256k2026-03-272026-10-19
84GPT-5-Codexhigh57.5±4$3.4419010 s400k2025-09-152026-09-01
85Grok 4.157.4±3––––2025-11-172026-10-15
86Qwen3.5 Plus 2026-04-20thinking57.3±1$0.258441.15 s1M2026-02-162026-10-13
87Claude Sonnet 4.657.1±3$6.00430.78 s1M2026-02-172026-10-19
88o4-mini57.0±6$1.931253.72 s200k2025-04-162026-10-19
89MiMo-V2.5-Prothinking57.0±9$0.5484250 s1.0M2026-04-232026-04-22 · stale
90Mistral Large 456.8±6$2.066831 s1.0M2026-10-062026-10-19
91DeepSeek V3.256.7±6$0.315162.17 s131k2025-12-012026-10-19
92GLM 5.1thinking56.6±8$1.996858 s200k2026-04-072026-04-07 · stale
93MiniMax M356.5±5$0.5259223 s1M2026-06-012026-10-19
94Claude Opus 4.1thinking56.5±3$30.00113.92 s200k2025-08-052026-10-15
95GPT-5 mini56.5±8$0.688863.42 s400k2025-08-072026-02-17 · stale
96GPT-5.4 Minixhigh56.4±5$1.6927688 s400k2026-03-172026-09-01
97Gemma 4 26B A4B56.4±8$0.198500.50 s262k2026-04-022026-10-19
98Qwen3.8 27Bxhigh56.3±6$1.134449 s262k2026-08-142026-10-14
99GPT-5.1-Codexhigh56.3±4$3.4412516 s400k2025-11-122025-11-13 · stale
100K2 Horizon 375B A23B56.3±5–11154.38 s524k2026-09-032026-09-03