| 1 | New | OGPT-5 (high)ClosedOpenAI · 3 more variants | 69.0 | $3.4 | — | — |
| 2 | ▼ 1 | XGrok 4ClosedxAI | 67.5 | $6.0 | — | — |
| 3 | ▼ 1 | Oo3-proClosedOpenAI | 67.5 | $35 | — | — |
| 4 | — | Oo3ClosedOpenAI | 67.1 | $3.5 | — | — |
| 5 | — | Oo4-mini (high)ClosedOpenAI | 65.1 | $1.9 | — | — |
| 6 | ▼ 3 | GGemini 2.5 ProClosedGoogle | 64.6 | $3.4 | — | — |
| 7 | New | OGPT-5 miniClosedOpenAI | 63.7 | $0.69 | — | — |
| 8 | ▼ 2 | AQwen3 235B A22B 2507 (Reasoning)OpenAlibaba · 3 more variants | 63.6 | $2.6 | — | — |
| 9 | New | AClaude 4.1 Opus (Extended Thinking)ClosedAnthropic · 1 more variant | 61.0 | $30 | — | — |
| 10 | New | Ogpt-oss-120BOpenOpenAI | 60.7 | $0.26 | — | — |
| 11 | ▼ 4 | GGemini 2.5 Pro Preview (Mar' 25)ClosedGoogle · 1 more variant | 59.0 | $3.4 | — | — |
| 12 | ▲ 3 | AClaude 4 Sonnet (Extended Thinking)ClosedAnthropic · 1 more variant | 58.8 | $6.0 | — | — |
| 13 | ▼ 5 | DDeepSeek R1 0528 (May '25)OpenDeepSeek · 1 more variant | 58.7 | $0.96 | — | — |
| 14 | ▼ 2 | GGemini 2.5 Flash (Reasoning)ClosedGoogle · 1 more variant | 58.4 | $0.85 | — | — |
| 15 | ▼ 6 | XGrok 3 mini Reasoning (high)ClosedxAI | 58.0 | $0.35 | — | — |
| 16 | ▼ 6 | ZGLM-4.5OpenZ AI | 56.1 | $0.96 | — | — |
| 17 | ▼ 6 | Oo3-mini (high)ClosedOpenAI · 1 more variant | 55.5 | $1.9 | — | — |
| 18 | ▼ 5 | AClaude 4 Opus (Extended Thinking)ClosedAnthropic · 1 more variant | 55.3 | $30 | — | — |
| 19 | New | OGPT-5 nanoClosedOpenAI | 53.8 | $0.14 | — | — |
| 20 | ▼ 3 | AQwen3 30B A3B 2507 (Reasoning)OpenAlibaba · 3 more variants | 53.2 | $0.75 | — | — |
| 21 | ▼ 3 | MMiniMax M1 80kOpenMiniMax | 53.2 | $0.83 | — | — |
| 22 | ▼ 6 | NLlama Nemotron Super 49B v1.5 (Reasoning)OpenNVIDIA · 1 more variant | 52.4 | $0.000 | — | — |
| 23 | ▼ 4 | Oo1ClosedOpenAI · 1 more variant | 51.7 | $26 | — | — |
| 24 | ▼ 4 | MMiniMax M1 40kOpenMiniMax | 51.1 | $0.83 | — | — |
| 25 | ▼ 4 | PSonar Reasoning ProClosedPerplexity | 50.7 | $0.000 | — | — |
| 26 | ▼ 12 | LEXAONE 4.0 32B (Reasoning)OpenLG AI Research · 1 more variant | 50.7 | $0.70 | — | — |
| 27 | ▼ 4 | GGemini 2.5 Flash Preview (Reasoning)ClosedGoogle · 1 more variant | 50.2 | $0.99 | — | — |
| 28 | ▼ 4 | ZGLM-4.5-AirOpenZ AI | 49.5 | $0.43 | — | — |
| 29 | New | Ogpt-oss-20BOpenOpenAI | 49.0 | $0.088 | — | — |
| 30 | ▼ 2 | MKimi K2OpenMoonshot AI | 48.6 | $1.1 | — | — |
| 31 | ▼ 4 | AQwQ 32BOpenAlibaba | 47.7 | $0.47 | — | — |
| 32 | ▼ 3 | AClaude 3.7 Sonnet (Extended Thinking)ClosedAnthropic · 1 more variant | 47.0 | $6.0 | — | — |
| 33 | ▲ 10 | OGPT-4.1ClosedOpenAI | 46.8 | $3.5 | — | — |
| 34 | ▼ 12 | NLlama 3.1 Nemotron Ultra 253B v1 (Reasoning)OpenNVIDIA | 46.4 | $0.90 | — | — |
| 35 | ▼ 5 | XGrok 3 Reasoning BetaClosedxAI | 45.6 | $0.000 | — | — |
| 35 | ▼ 5 | Oo1-proClosedOpenAI | 45.6 | $263 | — | — |
| 37 | ▼ 4 | AQwen3 14B (Reasoning)OpenAlibaba · 1 more variant | 45.2 | $1.3 | — | — |
| 38 | ▼ 1 | AQwen3 Coder 480B A35BOpenAlibaba | 45.2 | $3.0 | — | — |
| 39 | ▼ 5 | GGemini 2.5 Flash-Lite (Reasoning)ClosedGoogle · 1 more variant | 44.3 | $0.18 | — | — |
| 40 | ▼ 15 | AQwen3 32B (Reasoning)OpenAlibaba · 1 more variant | 44.3 | $2.6 | — | — |
| 41 | ▼ 1 | DDeepSeek V3 0324 (Mar '25)OpenDeepSeek · 1 more variant | 44.0 | $0.48 | — | — |
| 42 | ▼ 16 | USolar Pro 2 (Reasoning)ClosedUpstage · 3 more variants | 43.3 | $0.50 | — | — |
| 43 | ▼ 7 | Oo1-miniClosedOpenAI | 43.3 | $1.9 | — | — |
| 44 | ▼ 3 | OGPT-4.5 (Preview)ClosedOpenAI | 42.4 | $0.000 | — | — |
| 45 | ▼ 3 | OGPT-4.1 miniClosedOpenAI | 42.2 | $0.70 | — | — |
| 46 | ▲ 4 | MLlama 4 MaverickOpenMeta | 41.7 | $0.39 | — | — |
| 47 | ▼ 3 | GGemini 2.0 Flash Thinking Experimental (Jan '25)ClosedGoogle · 1 more variant | 41.7 | $0.000 | — | — |
| 48 | ▼ 3 | DDeepSeek R1 0528 Qwen3 8BOpenDeepSeek | 41.5 | $0.065 | — | — |
| 49 | ▼ 3 | DDeepSeek R1 Distill Qwen 32BOpenDeepSeek | 41.2 | $0.30 | — | — |
| 50 | ▼ 3 | AQwen3 8B (Reasoning)OpenAlibaba · 1 more variant | 40.8 | $0.66 | — | — |
| 51 | ▼ 3 | NLlama 3.3 Nemotron Super 49B v1 (Reasoning)OpenNVIDIA · 1 more variant | 40.5 | $0.000 | — | — |
| 52 | ▼ 3 | XGrok 3ClosedxAI | 39.9 | $6.0 | — | — |
| 53 | ▼ 2 | OGPT-4o (March 2025, chatgpt-4o-latest)ClosedOpenAI · 4 more variants | 39.5 | $7.5 | — | — |
| 54 | — | MMistral Medium 3ClosedMistral | 38.6 | $0.80 | — | — |
| 55 | ▼ 3 | GGemini 2.0 Pro Experimental (Feb '25)ClosedGoogle | 38.4 | $0.000 | — | — |
| 56 | ▼ 3 | DDeepSeek R1 Distill Qwen 14BOpenDeepSeek | 38.2 | $0.20 | — | — |
| 57 | ▼ 18 | PSonar ReasoningClosedPerplexity | 38.0 | $2.0 | — | — |
| 58 | ▼ 3 | GGemini 2.0 Flash (Feb '25)ClosedGoogle · 1 more variant | 37.8 | $0.18 | — | — |
| 59 | ▼ 27 | MMagistral MediumClosedMistral | 37.6 | $2.8 | — | — |
| 60 | ▼ 4 | DDeepSeek R1 Distill Llama 70BOpenDeepSeek | 37.4 | $0.72 | — | — |
| 61 | ▼ 4 | AQwen3 4B (Reasoning)OpenAlibaba · 1 more variant | 36.4 | $0.40 | — | — |
| 62 | ▼ 4 | RReka Flash 3OpenReka AI | 36.3 | $0.35 | — | — |
| 63 | ▼ 28 | MMagistral SmallOpenMistral | 36.0 | $0.75 | — | — |
| 64 | ▲ 3 | ANova PremierClosedAmazon | 34.8 | $5.0 | — | — |
| 65 | ▼ 6 | AQwen2.5 MaxClosedAlibaba | 34.3 | $2.8 | — | — |
| 66 | ▼ 6 | NLlama 3.1 Nemotron Nano 4B v1.1 (Reasoning)OpenNVIDIA | 34.1 | $0.000 | — | — |
| 67 | ▼ 6 | GGemini 1.5 Pro (Sep '24)ClosedGoogle · 1 more variant | 33.6 | $0.000 | — | — |
| 68 | ▼ 6 | AClaude 3.5 Sonnet (Oct '24)ClosedAnthropic · 1 more variant | 33.5 | $6.0 | — | — |
| 69 | New | AQwen3 Coder 30B A3BOpenAlibaba | 33.4 | $0.90 | — | — |
| 70 | ▼ 6 | MLlama 4 ScoutOpenMeta | 33.1 | $0.21 | — | — |
| 71 | ▼ 8 | PSonarClosedPerplexity | 32.4 | $1.0 | — | — |
| 72 | ▼ 4 | MMistral Small 3.2OpenMistral | 31.8 | $0.15 | — | — |
| 73 | ▼ 8 | PSonar ProClosedPerplexity | 31.7 | $6.0 | — | — |
| 74 | ▲ 2 | CCommand AOpenCohere | 31.6 | $4.4 | — | — |
| 75 | ▼ 9 | AQwQ 32B-PreviewOpenAlibaba | 31.5 | $0.67 | — | — |
| 76 | ▲ 6 | MDevstral MediumClosedMistral | 31.3 | $0.80 | — | — |
| 77 | ▼ 7 | MLlama 3.3 Instruct 70BOpenMeta | 31.2 | $0.60 | — | — |
| 78 | ▼ 9 | GGemini 2.0 Flash-Lite (Feb '25)ClosedGoogle · 1 more variant | 30.3 | $0.13 | — | — |
| 79 | ▼ 8 | OGPT-4.1 nanoClosedOpenAI | 29.9 | $0.18 | — | — |
| 80 | ▼ 8 | MLlama 3.1 Instruct 405BOpenMeta | 29.3 | $3.3 | — | — |
| 81 | ▼ 8 | AQwen2.5 Instruct 72BOpenAlibaba | 29.2 | $0.000 | — | — |
| 82 | ▼ 8 | MMiniMax-Text-01OpenMiniMax | 29.1 | $0.43 | — | — |
| 83 | ▲ 6 | ANova ProClosedAmazon | 28.8 | $1.4 | — | — |
| 84 | ▼ 7 | ALlama 3.1 Tulu3 405BOpenAllen Institute for AI | 28.7 | $0.000 | — | — |
| 85 | ▼ 7 | XGrok 2 (Dec '24)ClosedxAI | 28.0 | $0.000 | — | — |
| 86 | ▼ 11 | MPhi-4OpenMicrosoft Azure | 28.0 | $0.22 | — | — |
| 87 | ▼ 8 | GGemini 1.5 Flash (Sep '24)ClosedGoogle · 1 more variant | 27.7 | $0.000 | — | — |
| 88 | ▼ 8 | OGPT-4 TurboClosedOpenAI | 27.5 | $15 | — | — |
| 89 | ▼ 8 | MMistral Large 2 (Nov '24)OpenMistral · 1 more variant | 27.0 | $3.0 | — | — |
| 90 | ▼ 7 | AQwen3 1.7B (Reasoning)OpenAlibaba · 1 more variant | 26.9 | $0.40 | — | — |
| 91 | ▲ 4 | MMistral Small 3.1OpenMistral | 26.4 | $0.15 | — | — |
| 92 | ▼ 7 | XGrok BetaClosedxAI | 26.3 | $0.000 | — | — |
| 93 | ▼ 7 | MPixtral LargeOpenMistral | 26.1 | $3.0 | — | — |
| 94 | ▼ 7 | AQwen2.5 Instruct 32BOpenAlibaba | 26.1 | $0.15 | — | — |
| 95 | ▼ 7 | NLlama 3.1 Nemotron Instruct 70BOpenNVIDIA | 26.0 | $0.16 | — | — |
| 96 | ▼ 12 | GGemma 3 27B InstructOpenGoogle | 25.2 | $0.000 | — | — |
| 97 | ▼ 7 | AQwen2.5 Coder Instruct 32BOpenAlibaba | 25.0 | $0.15 | — | — |
| 98 | ▼ 7 | OGPT-4ClosedOpenAI | 24.6 | $38 | — | — |
| 99 | ▲ 8 | ANova LiteClosedAmazon | 24.5 | $0.11 | — | — |
| 100 | ▼ 7 | OGPT-4o miniClosedOpenAI | 24.3 | $0.26 | — | — |
| 101 | ▼ 7 | MLlama 3.1 Instruct 70BOpenMeta | 24.0 | $0.76 | — | — |
| 102 | — | GGemma 3 12B InstructOpenGoogle | 24.0 | $0.063 | — | — |
| 103 | ▼ 7 | MMistral Small 3OpenMistral | 23.9 | $0.15 | — | — |
| 104 | ▼ 12 | DDeepSeek-V2.5 (Dec '24)OpenDeepSeek · 1 more variant | 23.9 | $0.18 | — | — |
| 105 | ▼ 8 | AClaude 3 OpusClosedAnthropic | 23.7 | $30 | — | — |
| 106 | ▼ 8 | AClaude 3.5 HaikuClosedAnthropic | 23.3 | $1.6 | — | — |
| 107 | ▼ 8 | MDevstral Small (May '25)OpenMistral · 1 more variant | 22.7 | $0.15 | — | — |
| 108 | ▼ 7 | MMistral SabaClosedMistral | 22.6 | $0.30 | — | — |
| 109 | ▼ 9 | DDeepSeek R1 Distill Llama 8BOpenDeepSeek | 22.6 | $0.040 | — | — |
| 110 | ▲ 19 | RReka CoreClosedReka AI | 22.4 | $2.0 | — | — |
| 111 | ▼ 73 | PR1 1776OpenPerplexity | 22.2 | $3.5 | — | — |
| 112 | ▼ 9 | AQwen2.5 TurboClosedAlibaba | 22.1 | $0.088 | — | — |
| 113 | ▲ 19 | RReka Flash (Sep '24)ClosedReka AI · 1 more variant | 22.1 | $0.35 | — | — |
| 114 | ▼ 10 | MLlama 3.2 Instruct 90B (Vision)OpenMeta | 21.9 | $0.54 | — | — |
| 114 | ▲ 44 | USolar MiniOpenUpstage | 21.9 | $0.15 | — | — |
| 116 | ▲ 56 | RReka EdgeClosedReka AI | 21.5 | $0.10 | — | — |
| 117 | ▼ 12 | XGrok-1OpenxAI | 21.2 | $0.000 | — | — |
| 118 | ▼ 12 | AQwen2 Instruct 72BOpenAlibaba | 21.1 | $0.000 | — | — |
| 119 | ▼ 3 | ANova MicroClosedAmazon | 20.2 | $0.061 | — | — |
| 120 | ▼ 12 | GGemma 2 27BOpenGoogle | 20.1 | $0.80 | — | — |
| 121 | ▼ 12 | GGemini 1.5 Flash-8BClosedGoogle | 19.2 | $0.000 | — | — |
| 122 | ▲ 17 | MLlama 3.1 Instruct 8BOpenMeta | 19.0 | $0.10 | — | — |
| 123 | ▼ 6 | GGemma 3n E4B InstructOpenGoogle | 18.5 | $0.025 | — | — |
| 124 | ▼ 14 | NDeepHermes 3 - Mistral 24B PreviewOpenNous Research | 18.4 | $0.000 | — | — |
| 125 | ▼ 14 | AJamba 1.7 LargeOpenAI21 Labs | 17.9 | $3.5 | — | — |
| 126 | ▼ 14 | AJamba 1.5 LargeOpenAI21 Labs | 17.7 | $3.5 | — | — |
| 127 | ▲ 4 | IGranite 3.3 Instruct 8BOpenIBM | 17.6 | $0.085 | — | — |
| 128 | ▼ 15 | NHermes 3 - Llama-3.1 70BOpenNous Research | 17.5 | $0.15 | — | — |
| 129 | ▼ 15 | DDeepSeek-Coder-V2OpenDeepSeek | 17.3 | $0.18 | — | — |
| 130 | ▼ 15 | AJamba 1.6 LargeOpenAI21 Labs | 17.1 | $3.5 | — | — |
| 131 | ▼ 13 | 0Yi-LargeClosed01.AI | 16.2 | $0.000 | — | — |
| 132 | ▼ 13 | AClaude 3 SonnetClosedAnthropic | 16.0 | $6.0 | — | — |
| 133 | ▼ 13 | MCodestral (Jan '25)ClosedMistral · 1 more variant | 15.9 | $0.45 | — | — |
| 134 | ▼ 13 | MLlama 3 Instruct 70BOpenMeta | 15.7 | $0.75 | — | — |
| 135 | ▼ 13 | MMistral Small (Sep '24)OpenMistral · 1 more variant | 15.7 | $0.30 | — | — |
| 136 | ▼ 13 | GGemini 1.0 UltraClosedGoogle | 15.6 | $0.000 | — | — |
| 137 | ▼ 13 | GGemma 3n E4B Instruct Preview (May '25)OpenGoogle | 15.2 | $0.000 | — | — |
| 138 | ▼ 13 | MPhi-4 Multimodal InstructOpenMicrosoft Azure | 15.1 | $0.000 | — | — |
| 139 | ▼ 13 | AQwen2.5 Coder Instruct 7BOpenAlibaba | 14.9 | $0.000 | — | — |
| 140 | ▼ 13 | MMistral Large (Feb '24)ClosedMistral | 14.6 | $6.0 | — | — |
| 141 | ▲ 33 | AJamba InstructClosedAI21 Labs | 14.5 | $0.000 | — | — |
| 142 | ▼ 14 | MMixtral 8x22B InstructOpenMistral | 14.4 | $3.0 | — | — |
| 143 | ▼ 13 | MPhi-4 Mini InstructOpenMicrosoft Azure | 14.2 | $0.000 | — | — |
| 144 | ▲ 40 | MLlama 2 Chat 7BOpenMeta | 13.9 | $0.10 | — | — |
| 145 | ▼ 12 | GGemma 3 4B InstructOpenGoogle | 13.5 | $0.025 | — | — |
| 146 | ▼ 5 | MLlama 3.2 Instruct 11B (Vision)OpenMeta | 13.2 | $0.10 | — | — |
| 147 | ▼ 12 | AQwen1.5 Chat 110BOpenAlibaba | 13.2 | $0.000 | — | — |
| 148 | ▼ 12 | MPhi-3 Medium Instruct 14BOpenMicrosoft Azure | 12.7 | $0.30 | — | — |
| 149 | ▼ 12 | AClaude 2.1ClosedAnthropic | 12.2 | $12 | — | — |
| 150 | ▼ 12 | AClaude 3 HaikuClosedAnthropic | 12.1 | $0.50 | — | — |
| 151 | ▼ 11 | MPixtral 12B (2409)OpenMistral | 11.4 | $0.15 | — | — |
| 152 | ▼ 10 | AQwen3 0.6B (Reasoning)OpenAlibaba · 1 more variant | 11.3 | $0.40 | — | — |
| 153 | ▼ 10 | AClaude 2.0ClosedAnthropic | 11.1 | $12 | — | — |
| 153 | ▼ 10 | DDeepSeek-V2-ChatOpenDeepSeek | 11.1 | $0.18 | — | — |
| 155 | ▼ 10 | MMistral MediumClosedMistral | 10.9 | $4.1 | — | — |
| 156 | ▼ 10 | OGPT-3.5 TurboClosedOpenAI | 10.8 | $0.75 | — | — |
| 157 | ▼ 10 | GGemma 3n E2B InstructOpenGoogle | 10.4 | $0.000 | — | — |
| 158 | ▼ 10 | MMinistral 8BOpenMistral | 10.4 | $0.10 | — | — |
| 159 | ▼ 10 | GGemma 2 9BOpenGoogle | 10.2 | $0.20 | — | — |
| 160 | ▼ 10 | MPhi-3 Mini Instruct 3.8BOpenMicrosoft Azure | 10.1 | $0.000 | — | — |
| 161 | ▼ 10 | SArctic InstructOpenSnowflake | 10.0 | $0.000 | — | — |
| 161 | ▼ 10 | AQwen Chat 72BOpenAlibaba | 10.0 | $1.0 | — | — |
| 163 | ▼ 10 | LLFM 40BClosedLiquid AI | 9.7 | $0.15 | — | — |
| 164 | ▼ 10 | CCommand-R+ (Aug '24)OpenCohere · 3 more variants | 9.5 | $4.4 | — | — |
| 165 | ▼ 10 | MLlama 3 Instruct 8BOpenMeta | 9.5 | $0.058 | — | — |
| 166 | ▼ 10 | GPALM-2ClosedGoogle | 9.0 | $0.000 | — | — |
| 167 | ▼ 10 | GGemini 1.0 ProClosedGoogle | 8.5 | $0.75 | — | — |
| 168 | ▼ 34 | DDeepSeek Coder V2 Lite InstructOpenDeepSeek | 8.4 | $0.000 | — | — |
| 169 | ▼ 10 | CAya Expanse 32BOpenCohere | 8.0 | $0.75 | — | — |
| 170 | ▼ 10 | DDeepSeek LLM 67B Chat (V1)OpenDeepSeek | 7.9 | $0.000 | — | — |
| 170 | ▼ 10 | MLlama 2 Chat 70BOpenMeta | 7.9 | $0.000 | — | — |
| 172 | ▼ 10 | MLlama 2 Chat 13BOpenMeta | 7.9 | $0.000 | — | — |
| 173 | — | OOpenChat 3.5 (1210)OpenOpenChat | 7.7 | $0.000 | — | — |
| 174 | ▼ 11 | DDBRX InstructOpenDatabricks | 7.7 | $0.000 | — | — |
| 175 | ▼ 11 | MMinistral 3BClosedMistral | 7.5 | $0.040 | — | — |
| 176 | ▼ 11 | MMistral NeMoOpenMistral | 7.5 | $0.15 | — | — |
| 177 | ▼ 11 | MLlama 3.2 Instruct 3BOpenMeta | 7.4 | $0.035 | — | — |
| 178 | ▼ 11 | DDeepSeek R1 Distill Qwen 1.5BOpenDeepSeek | 7.1 | $0.000 | — | — |
| 179 | ▼ 11 | AJamba 1.5 MiniOpenAI21 Labs | 6.3 | $0.25 | — | — |
| 180 | ▼ 11 | AJamba 1.7 MiniOpenAI21 Labs | 5.8 | $0.25 | — | — |
| 181 | ▼ 11 | AJamba 1.6 MiniOpenAI21 Labs | 5.5 | $0.25 | — | — |
| 182 | ▼ 11 | MMixtral 8x7B InstructOpenMistral | 4.8 | $0.70 | — | — |
| 183 | ▼ 8 | NDeepHermes 3 - Llama-3.1 8B PreviewOpenNous Research | 4.0 | $0.000 | — | — |
| 184 | ▼ 8 | CAya Expanse 8BOpenCohere | 3.8 | $0.75 | — | — |
| 185 | ▼ 8 | AClaude InstantClosedAnthropic | 1.7 | $1.2 | — | — |
| 185 | ▼ 8 | AQwen Chat 14BOpenAlibaba | 1.7 | $0.000 | — | — |
| 187 | ▼ 8 | MCodestral-MambaOpenMistral | 1.6 | $0.000 | — | — |
| 188 | ▼ 8 | GGemma 3 1B InstructOpenGoogle | 1.1 | $0.000 | — | — |
| 189 | ▼ 6 | MLlama 3.2 Instruct 1BOpenMeta | 1.0 | $0.053 | — | — |
| 189 | ▼ 8 | MLlama 65BOpenMeta | 1.0 | $0.000 | — | — |
| 189 | ▼ 7 | MMistral 7B InstructOpenMistral | 1.0 | $0.25 | — | — |
