BenchLeader

All models

1054 models with at least one independent benchmark result. Another 157 appear in price lists only and are left out here; they still have model pages you can search for.

673 of 673
#
1GPT-6 AstramaxOpenAI70.6±4$22.0054329 s1.1M2026-09-032026-09-08
2Claude Fable 5Anthropic70.4±3$20.006392 s1M2026-06-092026-09-08
3Claude Fable 5.1xhighAnthropic70.3±7$20.0058132 s1M2026-09-012026-09-01
4Claude Opus 5Anthropic70.0±4$10.005282 s1M2026-07-242026-09-05
5GPT-5.6 SolhighOpenAI68.0±6$8.005931 s1M2026-07-092026-07-09
6GPT-5.5OpenAI66.6±4$11.258862 s1.1M2026-04-232026-09-08
7Kimi K3Moonshot AIopen ↗66.5±3$6.003758 s1.0M2026-07-162026-09-05
8Claude Opus 4.7Anthropic65.5±3$10.004621 s1M2026-04-162026-09-08
9Muse SparkMeta65.4±3262k2026-04-082026-09-02
10Muse Spark 1.1Meta64.9±4$2.001942.03 s1.0M2026-07-092026-09-08
11Claude Opus 4.8Anthropic64.7±3$10.005829 s1M2026-05-282026-09-08
12Gemini 3.7 FlashmediumGoogle64.4±4$1.502825.27 s1M2026-08-132026-08-13
13GPT-5.6 TerraxhighOpenAI64.2±4$4.509333 s1M2026-07-092026-09-08
14GPT-5.4 ProOpenAI64.2±4$67.5016.70 s1.1M2026-03-052026-03-23
15Gemini 3.1 ProGoogle63.9±4$4.5011030 s1.0M2026-02-192026-09-08
16Qwen3 8maxAlibaba63.9±3$2.673953 s1M2026-08-022026-09-08
17Gemini 3.5 FlashmediumGoogle63.9±3$3.3820917 s1M2026-05-192026-09-08
18Muse Spark 1.3xhighMeta63.9±5$2.0019340 s1M2026-09-022026-09-08
19Grok 4.6mediumxAI63.8±7$3.005537 s500k2026-08-122026-08-12
20Gemini 3.8 FlashmediumGoogle63.5±5$1.5027314 s1M2026-09-022026-09-02
21GPT-5.4OpenAI63.4±6$5.63130126 s1.1M2026-03-052026-09-08
22Grok 4.5xAI63.4±4$3.005613 s500k2026-07-082026-09-08
23Claude Opus 4.6Anthropic63.1±4$10.00382.05 s1M2026-02-052026-09-08
24Muse Spark 1.2Meta62.6±7$2.0021924 s1.0M2026-08-052026-08-09
25GPT-5.3 CodexOpenAI62.4±9$4.8112665 s400k2026-02-052026-09-08
26Qwen3 6maxAlibaba62.0±3$2.925838 s256k2026-04-20
27Gemini 3 ProGoogle61.6±3$4.501.0M2025-11-182026-09-08
28GPT-5.2OpenAI61.5±4$4.8172138 s400k2025-12-112026-09-08
29Gemini 3 FlashthinkingGoogle61.5±3$1.132006.12 s1M2025-12-17
30Claude Sonnet 5Anthropic61.2±3$4.0079193 s1M2026-06-302026-09-05
31GLM-5.3-FlashZhipu AIopen ↗61.0±6$0.1197230 s1M2026-08-202026-09-08
32GPT-5.2 CodexOpenAI60.7±5$4.81256.74 s400k2025-12-182026-09-08
33Gemini 3.6 FlashGoogle60.7±6$1.5019016 s1.0M2026-07-212026-07-21
34GPT-5 ProOpenAI60.7±6$41.25400k2025-08-072025-11-13 · stale
35Grok 4.3mediumxAI60.7±6$1.5611312 s1M2026-04-17
36Kimi K2.6Moonshot AIopen ↗60.6±4$1.715289 s262k2026-04-202026-09-08
37Claude Opus 4.5thinkingAnthropic60.6±3$10.004618 s200k2025-11-242026-09-01
38Mimo v2 ProXiaomi60.5±4$3.001.0M2026-03-182026-09-08
39GPT-5.5 InstantOpenAI60.4±6$11.2513516 s400k2026-05-052026-09-02
40Claude Sonnet 4.6Anthropic60.3±3$6.00432.12 s1M2026-02-172026-09-08
41o3OpenAI60.3±3$3.501396.03 s200k2025-04-162026-09-02
42Deepseek v4 ProhighDeepSeek60.3±52026-04-242026-09-08
43GLM-5.1Zhipu AIopen ↗60.1±3$2.156066 s200k2026-04-072026-09-08
44DeepSeek V4 ProhighDeepSeekopen ↗60.0±3$0.5486632 s1M2026-04-242026-09-08
45GLM-5.3maxZhipu AIopen ↗59.9±3$2.156036 s1M2026-08-142026-09-08
46Qwen3.7 PlusAlibaba59.7±7$1.135638 s1M2026-06-022026-09-08
47GPT-5OpenAI59.5±4$3.447674 s400k2025-08-072026-09-02
48GPT-5.1OpenAI59.4±5$3.4410554 s400k2025-11-122026-09-08
49GPT-5.6 LunaxhighOpenAI59.3±4$0.45010660 s1M2026-07-092026-09-08
50DeepSeek V4 FlashhighDeepSeekopen ↗59.3±3$0.16811818 s1M2026-07-312026-09-08
51Qwen3.8-Flash-NextAlibabaopen ↗59.3±7$0.2306434 s256k2026-08-262026-09-08
52Mimo v2 OmniXiaomi59.1±2256k2026-09-02
53Qwen3.6 PlusAlibabaopen59.0±4$1.1356101 s1M2026-03-312026-09-08
54GLM-5Zhipu AIopen ↗59.0±4$1.556648 s205k2026-02-112026-09-08
55MiMo-V2.5-ProXiaomiopen ↗59.0±5$0.6533560 s1.0M2026-04-232026-09-08
56Qwen3 7maxAlibaba58.9±4$3.7519914 s1M2026-05-192026-09-08
57Qwen3.5 397B-A17BAlibabaopen ↗58.6±4$0.3878141 s262k2026-02-132026-09-08
58Nemotron 3 Ultra 550B A55BNVIDIAopen ↗58.3±7$1.0015617 s1M2026-06-042026-09-05
59MiMo-V2.5Xiaomiopen ↗58.3±3$0.1755445 s1M2026-04-22
60Claude Opus 4.1thinkingAnthropic58.1±3$30.00102.68 s200k2025-08-052026-09-02
61GPT-5-CodexOpenAI58.1±4$3.44400k2025-09-152025-09-15 · stale
62GLM-5-TurboZhipu AI58.1±4$1.90136.58 s200k2026-03-16
63KAT-Coder-Pro V2KwaiKAT58.1±7$0.525262k
64Grok 4.20xAI57.9±8$1.5610419 s1M2026-02-172026-04-16
65Claude Sonnet 4.5highAnthropic57.8±7$6.00401.38 s200k2025-09-292026-09-08
66GLM-5.2maxZhipu AIopen ↗57.6±4$1.796335 s1M2026-06-162026-09-08
67Deepseek v4 Flash VisionDeepSeek57.4±6$0.17511918 s1M2026-08-212026-06-25
68Grok 4xAI57.2±3$1.56256k2025-07-092026-09-02
69GLM-5V-TurboZhipu AI57.2±3$9.251711 s200k2026-04-012026-09-08
70Qwen3.5 PlusthinkingAlibaba57.2±1$1.29481.07 s1M2026-02-162026-09-01
71Qwen 3.8 27BAlibabaopen ↗57.1±5$1.134647 s262k2026-08-142026-09-08
72GPT-5.1-CodexOpenAI57.1±5$3.44485.18 s400k2025-11-142026-09-08
73MiniMax-M3MiniMaxopen ↗56.9±5$0.52510022 s1.0M2026-06-012026-09-08
74MiniMax-M2.7MiniMaxopen ↗56.5±5$0.5256241 s205k2026-03-182026-09-08
75Kimi K2.7 CodeMoonshot AIopen ↗56.2±4$1.716338 s262k2026-06-122026-09-08
76Kimi K2.5Moonshot AIopen ↗56.1±3$1.20371.64 s262k2026-01-272026-02-13 · stale
77Grok Build 0.1xAI56.1±10$1.256233 s256k2026-05-292026-06-25
78Qwen3.5 122B-A10BAlibabaopen ↗56.0±5$1.1012918 s262k2026-02-242026-09-08
79Solar Pro 4Upstage56.0±5$0.5256832 s524k2026-08-062026-09-08
80Grok 4.1thinkingxAI55.9±4$1.562M2025-06-272026-09-08
81DeepSeek V3.2thinkingDeepSeekopen ↗55.9±4$0.315301.78 s128k2025-01-012026-09-08
82Kimi K2 5 InstantMoonshot AI55.9±62026-09-08
83GPT-5 miniOpenAI55.8±5$0.68810374 s400k2025-08-072026-02-17 · stale
84Gemma-4-31B-ITNVIDIAopen ↗55.4±6$0.2053551 s256k2026-04-022026-09-08
85Qwen3.5 27BAlibabaopen ↗55.4±5$0.8257632 s262k2026-02-242026-09-08
86MiniMax-M2MiniMaxopen ↗55.1±3$0.5258825 s205k2025-10-272026-09-08
87Muse Glimmer (high)Metaopen55.1±6$0.63810420 s131k2026-08-102026-09-08
88Inkling-SmallThinking Machinesopen ↗55.0±4$0.63815015 s1M2026-07-152026-09-08
89Kimi K2thinkingMoonshot AI55.0±7$2.86262k2025-11-062026-09-08
90Qwen3 MaxthinkingAlibaba55.0±7$2.405838 s262k2025-09-05
91GLM-4.7Zhipu AIopen ↗54.9±4$1.009423 s205k2025-12-222026-09-08
92o4-miniOpenAI54.9±4$1.9314823 s200k2025-04-162026-09-02
93Step 3.5 FlashStepFunopen ↗54.9±4$0.15021610 s256k2026-02-112026-09-02
94DeepSeek V3.1thinkingDeepSeekopen ↗54.8±4$1.92291.81 s128k2025-08-212026-09-02
95GPT-5.4 miniOpenAI54.8±8$1.69218139 s400k2026-03-172026-03-17
96Step 3.7 FlashStepFunopen ↗54.6±5$0.4168626 s256k2026-05-292026-05-29
97Claude Opus 4thinkingAnthropic54.4±4$30.00203.02 s200k2025-05-222026-09-02
98o3-prohighOpenAI54.4±8$35.00200k2025-06-102025-06-26 · stale
99Gemini 3.1 Flash LiteGoogle54.3±4$0.5633035.78 s1.0M2026-03-032026-09-08
100Gemini 2.5 ProGoogle54.1±3$3.4412323 s1.0M2025-03-252026-09-08