| 1 | New | Oo3-proClosedOpenAI | 71.0 | $35 | — | — |
| 2 | ▲ 1 | GGemini 2.5 Pro Preview (Jun '25)ClosedGoogle · 2 more variants | 70.5 | $3.4 | — | — |
| 3 | ▼ 2 | Oo3ClosedOpenAI | 70.0 | $3.5 | — | — |
| 4 | ▼ 2 | Oo4-mini (high)ClosedOpenAI | 69.8 | $1.9 | — | — |
| 5 | ▼ 1 | DDeepSeek R1 0528 (May '25)OpenDeepSeek · 1 more variant | 68.3 | $0.96 | — | — |
| 6 | ▼ 1 | XGrok 3 mini Reasoning (high)ClosedxAI | 66.7 | $0.35 | — | — |
| 7 | ▼ 1 | Oo3-mini (high)ClosedOpenAI · 1 more variant | 65.5 | $1.9 | — | — |
| 8 | ▼ 1 | GGemini 2.5 Flash Preview (May '25) (Reasoning)ClosedGoogle · 3 more variants | 65.1 | $0.99 | — | — |
| 9 | ▼ 1 | AClaude 4 Opus (Extended Thinking)ClosedAnthropic · 1 more variant | 64.4 | $30 | — | — |
| 10 | ▼ 1 | AQwen3 235B A22B (Reasoning)OpenAlibaba · 1 more variant | 62.3 | $2.6 | — | — |
| 11 | ▼ 1 | Oo1ClosedOpenAI · 1 more variant | 61.9 | $26 | — | — |
| 12 | ▼ 1 | NLlama 3.1 Nemotron Ultra 253B v1 (Reasoning)OpenNVIDIA | 60.8 | $0.90 | — | — |
| 13 | ▼ 1 | AClaude 4 Sonnet (Extended Thinking)ClosedAnthropic · 1 more variant | 60.8 | $6.0 | — | — |
| 14 | ▼ 1 | AQwen3 32B (Reasoning)OpenAlibaba · 1 more variant | 59.2 | $2.6 | — | — |
| 15 | ▼ 1 | AQwQ 32BOpenAlibaba | 58.1 | $0.54 | — | — |
| 16 | ▼ 1 | AClaude 3.7 Sonnet (Extended Thinking)ClosedAnthropic · 1 more variant | 57.4 | $6.0 | — | — |
| 17 | ▼ 1 | XGrok 3 Reasoning BetaClosedxAI | 56.1 | $0.000 | — | — |
| 17 | ▼ 1 | Oo1-proClosedOpenAI | 56.1 | $263 | — | — |
| 19 | ▼ 1 | AQwen3 14B (Reasoning)OpenAlibaba · 1 more variant | 55.7 | $1.3 | — | — |
| 20 | ▼ 1 | AQwen3 30B A3B (Reasoning)OpenAlibaba · 1 more variant | 55.6 | $0.75 | — | — |
| 21 | ▼ 1 | Oo1-miniClosedOpenAI | 53.8 | $1.9 | — | — |
| 22 | ▼ 1 | DDeepSeek V3 0324 (Mar '25)OpenDeepSeek · 1 more variant | 53.2 | $0.48 | — | — |
| 23 | ▼ 1 | OGPT-4.5 (Preview)ClosedOpenAI | 53.0 | $94 | — | — |
| 24 | ▼ 1 | OGPT-4.1 miniClosedOpenAI | 52.9 | $0.70 | — | — |
| 25 | ▼ 1 | OGPT-4.1ClosedOpenAI | 52.6 | $3.5 | — | — |
| 26 | ▼ 1 | GGemini 2.0 Flash Thinking Experimental (Jan '25)ClosedGoogle · 1 more variant | 52.3 | $0.000 | — | — |
| 27 | New | DDeepSeek R1 0528 Qwen3 8BOpenDeepSeek | 52.2 | $0.065 | — | — |
| 28 | ▼ 2 | DDeepSeek R1 Distill Qwen 32BOpenDeepSeek | 51.9 | $0.30 | — | — |
| 29 | ▼ 2 | AQwen3 8B (Reasoning)OpenAlibaba · 1 more variant | 51.4 | $0.66 | — | — |
| 30 | ▼ 2 | NLlama 3.3 Nemotron Super 49B v1 (Reasoning)OpenNVIDIA · 1 more variant | 51.2 | $0.000 | — | — |
| 31 | ▼ 2 | XGrok 3ClosedxAI | 50.6 | $6.0 | — | — |
| 32 | ▼ 2 | MLlama 4 MaverickOpenMeta | 50.5 | $0.38 | — | — |
| 33 | ▼ 2 | OGPT-4o (March 2025, chatgpt-4o-latest)ClosedOpenAI · 4 more variants | 50.3 | $7.5 | — | — |
| 34 | ▼ 2 | GGemini 2.0 Pro Experimental (Feb '25)ClosedGoogle | 49.2 | $0.000 | — | — |
| 35 | ▼ 2 | DDeepSeek R1 Distill Qwen 14BOpenDeepSeek | 49.0 | $0.20 | — | — |
| 36 | ▼ 2 | MMistral Medium 3ClosedMistral | 49.0 | $0.80 | — | — |
| 37 | ▼ 2 | PSonar ReasoningClosedPerplexity | 48.8 | $2.0 | — | — |
| 38 | ▼ 2 | DDeepSeek R1 Distill Llama 70BOpenDeepSeek | 48.2 | $0.72 | — | — |
| 39 | ▼ 2 | GGemini 2.0 Flash (Feb '25)ClosedGoogle · 1 more variant | 48.1 | $0.18 | — | — |
| 40 | ▼ 2 | AQwen3 4B (Reasoning)OpenAlibaba · 1 more variant | 47.3 | $0.40 | — | — |
| 41 | ▼ 2 | RReka Flash 3OpenReka AI | 47.1 | $0.35 | — | — |
| 42 | ▼ 2 | AQwen2.5 MaxClosedAlibaba | 45.3 | $2.8 | — | — |
| 43 | New | NLlama 3.1 Nemotron Nano 4B v1.1 (Reasoning)OpenNVIDIA | 45.0 | $0.000 | — | — |
| 44 | ▼ 3 | GGemini 1.5 Pro (Sep '24)ClosedGoogle · 1 more variant | 44.6 | $2.2 | — | — |
| 45 | ▼ 3 | AClaude 3.5 Sonnet (Oct '24)ClosedAnthropic · 1 more variant | 44.4 | $6.0 | — | — |
| 46 | ▼ 3 | PSonarClosedPerplexity | 43.4 | $1.0 | — | — |
| 47 | ▼ 3 | MLlama 4 ScoutOpenMeta | 43.0 | $0.24 | — | — |
| 48 | ▼ 3 | PSonar ProClosedPerplexity | 42.7 | $6.0 | — | — |
| 49 | ▼ 3 | AQwQ 32B-PreviewOpenAlibaba | 42.6 | $0.20 | — | — |
| 50 | ▼ 3 | ANova PremierClosedAmazon | 42.6 | $5.0 | — | — |
| 51 | ▼ 3 | GGemini 2.0 Flash-Lite (Feb '25)ClosedGoogle · 1 more variant | 41.4 | $0.13 | — | — |
| 52 | ▼ 3 | MLlama 3.3 Instruct 70BOpenMeta | 41.1 | $0.62 | — | — |
| 53 | ▼ 3 | OGPT-4.1 nanoClosedOpenAI | 41.0 | $0.18 | — | — |
| 54 | ▼ 3 | MLlama 3.1 Instruct 405BOpenMeta | 40.5 | $3.5 | — | — |
| 55 | ▼ 3 | AQwen2.5 Instruct 72BOpenAlibaba | 40.4 | $0.000 | — | — |
| 56 | ▼ 3 | MMiniMax-Text-01OpenMiniMax | 40.2 | $0.43 | — | — |
| 57 | ▼ 3 | MPhi-4OpenMicrosoft Azure | 40.2 | $0.22 | — | — |
| 58 | ▼ 3 | CCommand AOpenCohere | 40.0 | $4.4 | — | — |
| 59 | ▼ 3 | ALlama 3.1 Tulu3 405BOpenAllen Institute for AI | 39.9 | $0.000 | — | — |
| 60 | ▼ 3 | XGrok 2 (Dec '24)ClosedxAI | 39.2 | $0.000 | — | — |
| 61 | ▼ 3 | GGemini 1.5 Flash (Sep '24)ClosedGoogle · 1 more variant | 39.0 | $0.13 | — | — |
| 62 | ▼ 3 | OGPT-4 TurboClosedOpenAI | 38.8 | $15 | — | — |
| 63 | ▼ 3 | MMistral Large 2 (Nov '24)OpenMistral · 1 more variant | 38.3 | $3.0 | — | — |
| 64 | ▼ 3 | AQwen3 1.7B (Reasoning)OpenAlibaba · 1 more variant | 38.2 | $0.40 | — | — |
| 65 | ▼ 3 | GGemma 3 27B InstructOpenGoogle | 37.6 | $0.000 | — | — |
| 66 | ▼ 3 | XGrok BetaClosedxAI | 37.5 | $7.5 | — | — |
| 67 | ▼ 3 | MPixtral LargeOpenMistral | 37.4 | $3.0 | — | — |
| 68 | ▼ 3 | AQwen2.5 Instruct 32BOpenAlibaba | 37.4 | $0.15 | — | — |
| 69 | ▼ 3 | NLlama 3.1 Nemotron Instruct 70BOpenNVIDIA | 37.3 | $0.16 | — | — |
| 70 | ▼ 3 | ANova ProClosedAmazon | 37.1 | $1.4 | — | — |
| 71 | ▼ 3 | AQwen2.5 Coder Instruct 32BOpenAlibaba | 36.3 | $0.15 | — | — |
| 72 | ▼ 3 | OGPT-4ClosedOpenAI | 36.0 | $38 | — | — |
| 73 | ▼ 3 | OGPT-4o miniClosedOpenAI | 35.7 | $0.26 | — | — |
| 74 | ▼ 3 | MLlama 3.1 Instruct 70BOpenMeta | 35.4 | $0.72 | — | — |
| 75 | ▼ 3 | MMistral Small 3.1OpenMistral | 35.3 | $0.15 | — | — |
| 76 | ▼ 3 | MMistral Small 3OpenMistral | 35.3 | $0.15 | — | — |
| 77 | ▼ 3 | DDeepSeek-V2.5 (Dec '24)OpenDeepSeek · 1 more variant | 35.3 | $0.18 | — | — |
| 78 | ▼ 3 | AClaude 3 OpusClosedAnthropic | 35.1 | $30 | — | — |
| 79 | ▼ 3 | AClaude 3.5 HaikuClosedAnthropic | 34.7 | $1.6 | — | — |
| 80 | ▼ 3 | MDevstralOpenMistral | 34.1 | $0.15 | — | — |
| 81 | ▼ 3 | MMistral SabaClosedMistral | 34.1 | $0.30 | — | — |
| 82 | ▼ 3 | DDeepSeek R1 Distill Llama 8BOpenDeepSeek | 34.0 | $0.040 | — | — |
| 83 | ▼ 3 | RReka CoreClosedReka AI | 33.9 | $2.0 | — | — |
| 84 | ▼ 3 | GGemma 3 12B InstructOpenGoogle | 33.8 | $0.063 | — | — |
| 85 | ▼ 3 | PR1 1776OpenPerplexity | 33.7 | $3.5 | — | — |
| 86 | ▼ 3 | AQwen2.5 TurboClosedAlibaba | 33.6 | $0.088 | — | — |
| 87 | ▼ 3 | RReka Flash (Sep '24)ClosedReka AI · 1 more variant | 33.6 | $0.35 | — | — |
| 88 | ▼ 3 | GGemma 3 1B InstructOpenGoogle | 33.4 | $0.000 | — | — |
| 89 | ▼ 3 | MLlama 3.2 Instruct 90B (Vision)OpenMeta | 33.4 | $0.72 | — | — |
| 89 | ▼ 3 | USolar MiniOpenUpstage | 33.4 | $0.15 | — | — |
| 91 | ▼ 3 | RReka EdgeClosedReka AI | 33.0 | $0.10 | — | — |
| 92 | ▼ 3 | AQwen2 Instruct 72BOpenAlibaba | 32.6 | $0.000 | — | — |
| 93 | ▼ 3 | ANova LiteClosedAmazon | 32.5 | $0.11 | — | — |
| 94 | ▼ 3 | GGemini 1.5 Flash-8BClosedGoogle | 30.8 | $0.066 | — | — |
| 95 | ▼ 3 | NDeepHermes 3 - Mistral 24B PreviewOpenNous Research | 30.0 | $0.000 | — | — |
| 96 | ▼ 3 | AJamba 1.5 LargeOpenAI21 Labs | 29.3 | $3.5 | — | — |
| 97 | ▼ 3 | NHermes 3 - Llama-3.1 70BOpenNous Research | 29.1 | $0.000 | — | — |
| 98 | ▼ 3 | DDeepSeek-Coder-V2OpenDeepSeek | 29.0 | $0.18 | — | — |
| 99 | ▼ 3 | AJamba 1.6 LargeOpenAI21 Labs | 28.8 | $3.5 | — | — |
| 100 | ▼ 3 | ANova MicroClosedAmazon | 28.3 | $0.061 | — | — |
| 101 | ▼ 3 | 0Yi-LargeClosed01.AI | 27.9 | $3.0 | — | — |
| 102 | ▼ 3 | AClaude 3 SonnetClosedAnthropic | 27.8 | $6.0 | — | — |
| 103 | ▼ 3 | MCodestral (Jan '25)ClosedMistral · 1 more variant | 27.6 | $0.45 | — | — |
| 104 | ▼ 3 | MLlama 3 Instruct 70BOpenMeta | 27.5 | $0.75 | — | — |
| 105 | ▼ 3 | MMistral Small (Sep '24)OpenMistral · 1 more variant | 27.4 | $0.30 | — | — |
| 106 | ▼ 3 | GGemini 1.0 UltraClosedGoogle | 27.3 | $0.000 | — | — |
| 107 | ▼ 3 | MPhi-4 Multimodal InstructOpenMicrosoft Azure | 26.9 | $0.000 | — | — |
| 108 | ▼ 3 | AQwen2.5 Coder Instruct 7BOpenAlibaba | 26.7 | $0.000 | — | — |
| 109 | ▼ 3 | MMistral Large (Feb '24)ClosedMistral | 26.4 | $6.0 | — | — |
| 110 | ▼ 3 | AJamba InstructClosedAI21 Labs | 26.3 | $0.000 | — | — |
| 111 | ▼ 3 | MMixtral 8x22B InstructOpenMistral | 26.2 | $3.0 | — | — |
| 112 | ▼ 3 | MPhi-4 Mini InstructOpenMicrosoft Azure | 26.0 | $0.000 | — | — |
| 113 | ▼ 3 | GGemma 2 27BOpenGoogle | 25.6 | $0.80 | — | — |
| 114 | ▼ 3 | MLlama 3.2 Instruct 11B (Vision)OpenMeta | 25.0 | $0.16 | — | — |
| 115 | ▼ 3 | AQwen1.5 Chat 110BOpenAlibaba | 25.0 | $0.000 | — | — |
| 116 | ▼ 3 | MPhi-3 Medium Instruct 14BOpenMicrosoft Azure | 24.5 | $0.30 | — | — |
| 117 | ▼ 3 | GGemma 3 4B InstructOpenGoogle | 24.5 | $0.025 | — | — |
| 118 | ▼ 3 | AClaude 2.1ClosedAnthropic | 24.1 | $12 | — | — |
| 119 | ▼ 3 | AClaude 3 HaikuClosedAnthropic | 24.0 | $0.50 | — | — |
| 120 | ▼ 3 | MLlama 3.1 Instruct 8BOpenMeta | 23.7 | $0.10 | — | — |
| 121 | ▼ 3 | MPixtral 12B (2409)OpenMistral | 23.4 | $0.15 | — | — |
| 122 | ▼ 3 | AQwen3 0.6B (Reasoning)OpenAlibaba · 1 more variant | 23.2 | $0.40 | — | — |
| 123 | ▼ 3 | AClaude 2.0ClosedAnthropic | 23.0 | $12 | — | — |
| 123 | ▼ 3 | DDeepSeek-V2-ChatOpenDeepSeek | 23.0 | $0.18 | — | — |
| 125 | ▼ 3 | MMistral MediumClosedMistral | 22.8 | $4.1 | — | — |
| 126 | ▼ 3 | OGPT-3.5 TurboClosedOpenAI | 22.7 | $0.75 | — | — |
| 127 | ▼ 3 | MMinistral 8BOpenMistral | 22.3 | $0.10 | — | — |
| 128 | ▼ 3 | GGemma 2 9BOpenGoogle | 22.2 | $0.12 | — | — |
| 129 | ▼ 3 | MPhi-3 Mini Instruct 3.8BOpenMicrosoft Azure | 22.1 | $0.000 | — | — |
| 130 | ▼ 3 | SArctic InstructOpenSnowflake | 22.0 | $0.000 | — | — |
| 130 | ▼ 3 | AQwen Chat 72BOpenAlibaba | 22.0 | $1.0 | — | — |
| 132 | ▼ 3 | LLFM 40BClosedLiquid AI | 21.7 | $0.15 | — | — |
| 133 | ▼ 3 | CCommand-R+ (Aug '24)OpenCohere · 3 more variants | 21.5 | $4.4 | — | — |
| 134 | ▼ 3 | MLlama 3 Instruct 8BOpenMeta | 21.5 | $0.080 | — | — |
| 135 | ▼ 3 | GPALM-2ClosedGoogle | 21.0 | $0.000 | — | — |
| 136 | ▼ 3 | GGemini 1.0 ProClosedGoogle | 20.6 | $0.75 | — | — |
| 137 | ▼ 3 | DDeepSeek Coder V2 Lite InstructOpenDeepSeek | 20.5 | $0.000 | — | — |
| 138 | ▼ 3 | CAya Expanse 32BOpenCohere | 20.1 | $0.75 | — | — |
| 139 | ▼ 3 | DDeepSeek LLM 67B Chat (V1)OpenDeepSeek | 20.0 | $0.000 | — | — |
| 139 | ▼ 3 | MLlama 2 Chat 70BOpenMeta | 20.0 | $0.000 | — | — |
| 141 | ▼ 3 | MLlama 2 Chat 13BOpenMeta | 19.9 | $0.000 | — | — |
| 142 | ▼ 3 | OOpenChat 3.5 (1210)OpenOpenChat | 19.8 | $0.050 | — | — |
| 143 | ▼ 3 | DDBRX InstructOpenDatabricks | 19.8 | $0.000 | — | — |
| 144 | ▼ 3 | MMinistral 3BClosedMistral | 19.6 | $0.040 | — | — |
| 145 | ▼ 3 | MMistral NeMoOpenMistral | 19.6 | $0.15 | — | — |
| 146 | ▼ 3 | MLlama 3.2 Instruct 3BOpenMeta | 19.5 | $0.048 | — | — |
| 147 | ▼ 3 | DDeepSeek R1 Distill Qwen 1.5BOpenDeepSeek | 19.2 | $0.18 | — | — |
| 148 | ▼ 3 | AJamba 1.5 MiniOpenAI21 Labs | 18.4 | $0.25 | — | — |
| 149 | ▼ 3 | AJamba 1.6 MiniOpenAI21 Labs | 17.7 | $0.25 | — | — |
| 150 | ▼ 3 | MMixtral 8x7B InstructOpenMistral | 17.0 | $0.70 | — | — |
| 151 | ▼ 3 | NDeepHermes 3 - Llama-3.1 8B PreviewOpenNous Research | 16.2 | $0.000 | — | — |
| 152 | ▼ 3 | CAya Expanse 8BOpenCohere | 16.0 | $0.75 | — | — |
| 153 | ▼ 3 | AClaude InstantClosedAnthropic | 14.0 | $1.2 | — | — |
| 153 | ▼ 3 | AQwen Chat 14BOpenAlibaba | 14.0 | $0.000 | — | — |
| 155 | ▼ 3 | MCodestral-MambaOpenMistral | 13.9 | $0.25 | — | — |
| 156 | ▼ 3 | MLlama 65BOpenMeta | 11.0 | $0.000 | — | — |
| 157 | ▼ 3 | MMistral 7B InstructOpenMistral | 10.1 | $0.25 | — | — |
| 158 | ▼ 3 | MLlama 3.2 Instruct 1BOpenMeta | 9.7 | $0.050 | — | — |
| 159 | ▼ 3 | MLlama 2 Chat 7BOpenMeta | 8.3 | $0.10 | — | — |