| 1 |
GPT-5.6 Sol (max)OpenAI |
|
| 2 |
Claude Fable 5 (max reasoning)Anthropic |
|
| 2 |
GPT-5.6 Sol (medium reasoning)OpenAI |
|
| 2 |
GPT-5.6 Terra (xhigh)OpenAI |
|
| 5 |
GPT-5.6 Sol (high reasoning)OpenAI |
|
| 6 |
GPT-5.6 Sol (xhigh)OpenAI |
|
| 7 |
GPT-5.5 (xhigh reasoning)OpenAI |
|
| 7 |
GPT-5.6 Sol (low reasoning)OpenAI |
|
| 9 |
GPT-5.5 (high)OpenAI |
|
| 10 |
Claude Opus 4.8 (max reasoning)Anthropic |
|
| 11 |
GPT-5.4 (xhigh reasoning)OpenAI |
|
| 11 |
GPT-5.5 (medium reasoning)OpenAI |
|
| 11 |
GPT-5.6 Terra (high reasoning)OpenAI |
|
| 11 |
GPT-5.6 Terra (max)OpenAI |
|
| 15 |
Claude Opus 4.7 (off)Anthropic |
|
| 16 |
Gemini 3.1 Pro PreviewGoogle |
|
| 17 |
Claude Sonnet 4.6 (max reasoning)Anthropic |
|
| 17 |
GPT-5.3-Codex (xhigh)OpenAI |
|
| 19 |
GPT-5.4 Mini (xhigh)OpenAI |
|
| 19 |
GPT-5.5 (low reasoning)OpenAI |
|
| 21 |
Claude Opus 4.7 (max reasoning)Anthropic |
|
| 22 |
Qwen3.7 MaxAlibaba |
|
| 22 |
GLM 5.2 (max)Z.ai |
|
| 24 |
GPT-5.5 (no reasoning)OpenAI |
|
| 25 |
Claude Opus 4.6 (off)Anthropic |
|
| 26 |
Qwen3.7 PlusAlibaba |
|
| 26 |
Claude Opus 4.5 (thinking reasoning)Anthropic |
|
| 26 |
GPT-5.2 (xhigh)OpenAI |
|
| 29 |
Claude Opus 4.6 (max reasoning)Anthropic |
|
| 29 |
Claude Sonnet 4.6 (off)Anthropic |
|
| 29 |
deepseek-v4-pro-preview (max reasoning)DeepSeek |
|
| 29 |
Gemini 3.5 Flash (minimal reasoning)Google |
|
| 33 |
muse-sparkMeta |
|
| 33 |
GPT-5.1 (high)OpenAI |
|
| 35 |
Kimi K2.7 CodeMoonshot AI |
|
| 36 |
Qwen3.6 Max PreviewAlibaba |
|
| 36 |
Qwen3.6 PlusAlibaba |
|
| 36 |
Kimi K2.6Moonshot AI |
|
| 36 |
GPT-5.6 Terra (low reasoning)OpenAI |
|
| 40 |
GPT-5.2 (medium reasoning)OpenAI |
|
| 40 |
GPT-5.4 (low reasoning)OpenAI |
|
| 40 |
MiMo-V2.5-Pro (thinking reasoning)Xiaomi |
|
| 40 |
GLM 5.1Z.ai |
|
| 40 |
GLM 5Z.ai |
|
| 45 |
MiniMax M3MiniMax |
|
| 45 |
GPT-5.4 Nano (xhigh)OpenAI |
|
| 45 |
GPT-5.5 Instant (26 May)OpenAI |
|
| 48 |
deepseek-v4-pro-preview (high reasoning)DeepSeek |
|
| 48 |
gemini-3-pro (high)Google |
|
| 48 |
MiMo-V2.5Xiaomi |
|
| 51 |
Qwen3.5 397B A17BAlibaba |
|
| 51 |
Claude Opus 4.5 (no reasoning)Anthropic |
|
| 51 |
Gemini 3.5 Flash (high)Google |
|
| 51 |
grok-4.20-0309-reasoningxAI |
|
| 55 |
Gemini 3.5 Flash (medium)Google |
|
| 55 |
MiniMax M2.7MiniMax |
|
| 55 |
GLM 5 (no reasoning)Z.ai |
|
| 58 |
deepseek-v4-flash-preview (high reasoning)DeepSeek |
|
| 58 |
gemini-3-flash (thinking reasoning)Google |
|
| 60 |
Kimi K2.6 (no reasoning)Moonshot AI |
|
| 60 |
GPT-5.4 (no reasoning)OpenAI |
|
| 60 |
GPT-5-Codex (high)OpenAI |
|
| 60 |
GPT-5 (medium)OpenAI |
|
| 60 |
Grok 4.20xAI |
|
| 60 |
Grok 4.3 (high)xAI |
|
| 60 |
grok-4xAI |
|
| 67 |
GPT-5.2-Codex (xhigh)OpenAI |
|
| 67 |
o3OpenAI |
|
| 69 |
deepseek-v4-pro-preview (no reasoning)DeepSeek |
|
| 69 |
Gemma 4 31BGoogle |
|
| 71 |
Qwen3.5 397B A17B (no reasoning)Alibaba |
|
| 71 |
Claude Sonnet 4.5 (thinking reasoning)Anthropic |
|
| 71 |
DeepSeek V3.2DeepSeek |
|
| 71 |
deepseek-v4-flash-preview (max reasoning)DeepSeek |
|
| 71 |
MiMo-V2.5-Pro (no reasoning)Xiaomi |
|
| 71 |
GLM 5.1 (no reasoning)Z.ai |
|
| 77 |
Qwen3.6 27BAlibaba |
|
| 77 |
Qwen3.6 35B A3BAlibaba |
|
| 77 |
deepseek-v3.2-specialeDeepSeek |
|
| 77 |
MiniMax M2.5MiniMax |
|
| 77 |
Kimi K2.5Moonshot AI |
|
| 77 |
GPT-5.1-Codex (high)OpenAI |
|
| 83 |
Claude Opus 4.1 (thinking reasoning)Anthropic |
|
| 84 |
deepseek-v4-flash-preview (no reasoning)DeepSeek |
|
| 84 |
gemini-3-pro (low)Google |
|
| 84 |
GPT-5.4 Mini (medium)OpenAI |
|
| 84 |
Hy3 preview (thinking reasoning)Tencent |
|
| 88 |
Mistral Medium 3.5Mistral |
|
| 88 |
GPT-5.1-Codex-Mini (high)OpenAI |
|
| 88 |
GPT-5.4 Nano (medium)OpenAI |
|
| 88 |
GPT-5 Mini (high)OpenAI |
|
| 88 |
GLM 5 TurboZ.ai |
|
| 93 |
Qwen3.5-27BAlibaba |
|
| 93 |
DeepSeek V3.2 (no reasoning)DeepSeek |
|
| 93 |
GPT-5 (high)OpenAI |
|
| 93 |
GLM 5V TurboZ.ai |
|
| 97 |
Qwen3.5-27B (no reasoning)Alibaba |
|
| 97 |
DeepSeek V3.1 Terminus (no reasoning)DeepSeek |
|
| 97 |
gemini-3-flash (off)Google |
|
| 97 |
GPT-5.2 (no reasoning)OpenAI |
|
| 97 |
Hy3 preview (no reasoning)Tencent |
|
| 97 |
GLM 4.7Z.ai |
|
| 103 |
Qwen3.5-122B-A10BAlibaba |
|
| 103 |
Claude Sonnet 4 (thinking reasoning)Anthropic |
|
| 103 |
DeepSeek V3.2 ExpDeepSeek |
|
| 103 |
Kimi K2 ThinkingMoonshot AI |
|
| 107 |
DeepSeek V3.1 TerminusDeepSeek |
|
| 107 |
Gemma 4 31B (off)Google |
|
| 107 |
Grok 4.3 (medium)xAI |
|
| 107 |
GLM 4.7 (no reasoning)Z.ai |
|
| 111 |
Qwen3.5-122B-A10B (no reasoning)Alibaba |
|
| 112 |
Claude Sonnet 4.5 (no reasoning)Anthropic |
|
| 112 |
MiniMax M2.1MiniMax |
|
| 112 |
Nemotron 3 SuperNVIDIA |
|
| 112 |
GPT-5 Mini (medium)OpenAI |
|
| 112 |
GLM 4.6 (no reasoning)Z.ai |
|
| 117 |
Claude Haiku 4.5 (no reasoning)Anthropic |
|
| 117 |
Claude Haiku 4.5 (thinking reasoning)Anthropic |
|
| 117 |
Claude Sonnet 4 (no reasoning)Anthropic |
|
| 117 |
Step 3.5 FlashStepfun |
|
| 121 |
Qwen3.5-35B-A3BAlibaba |
|
| 121 |
Gemini 2.5 ProGoogle |
|
| 121 |
Mercury 2Inception |
|
| 121 |
GPT-5 (low reasoning)OpenAI |
|
| 121 |
Grok 4.3 (low)xAI |
|
| 126 |
Qwen3.6 35B A3B (no reasoning)Alibaba |
|
| 126 |
MiniMax M2MiniMax |
|
| 128 |
DeepSeek V3.1DeepSeek |
|
| 128 |
DeepSeek V3.2 Exp (no reasoning)DeepSeek |
|
| 128 |
Gemma 4 26B A4B (off)Google |
|
| 128 |
GLM 4.6 (thinking reasoning)Z.ai |
|
| 132 |
Qwen3.5-9BAlibaba |
|
| 132 |
Qwen3 Max ThinkingAlibaba |
|
| 132 |
DeepSeek V3.1 (no reasoning)DeepSeek |
|
| 132 |
Gemini 3.1 Flash Lite PreviewGoogle |
|
| 132 |
GPT-5.4 Nano (no reasoning)OpenAI |
|
| 132 |
grok-4-1-fast-reasoningxAI |
|
| 138 |
Kimi K2 0905Moonshot AI |
|
| 138 |
gpt-oss-120b (high)OpenAI |
|
| 140 |
Trinity Large ThinkingArcee Ai |
|
| 140 |
GPT-5.1 (off)OpenAI |
|
| 142 |
grok-4.20-0309-non-reasoning (no reasoning)xAI |
|
| 142 |
GLM 4.5Z.ai |
|
| 142 |
GLM 4.7 FlashZ.ai |
|
| 145 |
Qwen3.5 Omni PlusAlibaba |
|
| 145 |
Qwen3.6 27B (no reasoning)Alibaba |
|
| 147 |
Qwen3 MaxAlibaba |
|
| 147 |
GLM 4.5 AirZ.ai |
|
| 149 |
qwen3-max-previewAlibaba |
|
| 150 |
Qwen3 Coder 480B A35BAlibaba |
|
| 150 |
Devstral 2 2512Mistral |
|
| 150 |
Kimi K2.5Moonshot AI |
|
| 150 |
Grok 4.3 (off)xAI |
|
| 150 |
grok-4-fast-reasoningxAI |
|
| 155 |
qwen3.5-4b (thinking reasoning)Alibaba |
|
| 155 |
Qwen3.5-9B (no reasoning)Alibaba |
|
| 155 |
Qwen3 Coder NextAlibaba |
|
| 155 |
gemma-4-12b-itGoogle |
|
| 155 |
GPT-5.4 Mini (no reasoning)OpenAI |
|
| 155 |
GPT-5 (minimal reasoning)OpenAI |
|
| 161 |
Qwen3 Max Thinking (preview)Alibaba |
|
| 161 |
Nova 2 Lite (medium reasoning)Amazon |
|
| 161 |
Mistral Small 4Mistral |
|
| 161 |
GPT-5 Nano (medium)OpenAI |
|
| 161 |
Grok Code Fast 1xAI |
|
| 166 |
Nova 2 Lite (high reasoning)Amazon |
|
| 166 |
gemini-2.5-flash-preview-09-2025 (thinking reasoning)Google |
|
| 166 |
devstral-small-2-24b-instruct-2512Mistral |
|
| 166 |
Grok 4.20 (off)xAI |
|
| 170 |
R1 0528DeepSeek |
|
| 170 |
Mistral Large 3 2512Mistral |
|
| 170 |
Kimi K2 0711Moonshot AI |
|
| 173 |
Qwen3 235B A22B Instruct 2507Alibaba |
|
| 173 |
Qwen3 Coder 30B A3B InstructAlibaba |
|
| 173 |
DeepSeek V3 0324DeepSeek |
|
| 173 |
o4 Mini (high reasoning)OpenAI |
|
| 177 |
gemini-2.5-flash-preview-09-2025 (no reasoning)Google |
|
| 177 |
GPT-5 Mini (minimal)OpenAI |
|
| 177 |
grok-4-1-fast-non-reasoning (no reasoning)xAI |
|
| 177 |
GLM 4.6V (thinking reasoning)Z.ai |
|
| 181 |
Gemma 4 26B A4BGoogle |
|
| 182 |
Qwen3 235B A22B Thinking 2507Alibaba |
|
| 182 |
Gemini 2.5 Flash (thinking reasoning)Google |
|
| 182 |
Nemotron 3 Nano 30B A3B (thinking reasoning)NVIDIA |
|
| 182 |
GPT-4.1OpenAI |
|
| 186 |
gemini-2.5-flash-lite-preview-09-2025 (thinking reasoning)Google |
|
| 186 |
Magistral Medium 1.2Mistral |
|
| 186 |
gpt-5-chatOpenAI |
|
| 186 |
o1OpenAI |
|
| 190 |
Gemini 2.5 Flash (no reasoning)Google |
|
| 190 |
Nemotron 3 Nano 30B A3B (no reasoning)NVIDIA |
|
| 190 |
GPT-5 Nano (high)OpenAI |
|
| 190 |
grok-4-fast-non-reasoning (no reasoning)xAI |
|
| 194 |
qwen3.5-4b (no reasoning)Alibaba |
|
| 194 |
Qwen3 VL 235B A22B ThinkingAlibaba |
|
| 194 |
gemma-4-12b-it (no reasoning)Google |
|
| 194 |
kimi-linear-48b-a3b-instructMoonshot AI |
|
| 198 |
Qwen3.5-35B-A3B (no reasoning)Alibaba |
|
| 198 |
Mistral Medium 3.1Mistral |
|
| 198 |
Mistral Small 4 (no reasoning)Mistral |
|
| 198 |
gpt-oss-20b (high reasoning)OpenAI |
|
| 202 |
Qwen3 Next 80B A3B ThinkingAlibaba |
|
| 203 |
Devstral MediumMistral |
|
| 204 |
Qwen3.5 Omni FlashAlibaba |
|
| 204 |
Qwen3 VL 32B InstructAlibaba |
|
| 204 |
gemma-4-e4b-itGoogle |
|
| 204 |
GPT-4o (2024-08-06)OpenAI |
|
| 208 |
Qwen3 Next 80B A3B InstructAlibaba |
|
| 208 |
qwen3-vl-32b-thinkingAlibaba |
|
| 208 |
gemini-2.5-flash-lite-preview-09-2025 (no reasoning)Google |
|
| 208 |
gemma-4-e4b-it (no reasoning)Google |
|
| 208 |
Mistral Small 3.1 24BMistral |
|
| 208 |
GPT-4.1 MiniOpenAI |
|
| 208 |
Solar Pro 3Upstage |
|
| 215 |
Qwen3 30B A3B (no reasoning)Alibaba |
|
| 215 |
Qwen3 VL 235B A22B InstructAlibaba |
|
| 215 |
Nova 2 Lite (no reasoning)Amazon |
|
| 215 |
DeepSeek V3DeepSeek |
|
| 215 |
Llama 4 MaverickMeta |
|
| 215 |
Mistral Small 3.2 24BMistral |
|
| 215 |
GPT-5 Nano (minimal)OpenAI |
|
| 215 |
o3 MiniOpenAI |
|
| 215 |
GLM 4.5V (off)Z.ai |
|
| 224 |
Qwen3 235B A22BAlibaba |
|
| 224 |
Qwen3 235B A22B (thinking reasoning)Alibaba |
|
| 224 |
Qwen3 30B A3B Instruct 2507Alibaba |
|
| 224 |
Qwen3 VL 30B A3B InstructAlibaba |
|
| 224 |
Nova Pro 1.0Amazon |
|
| 224 |
R1DeepSeek |
|
| 224 |
Devstral Small 1.1Mistral |
|
| 224 |
o3 Mini HighOpenAI |
|
| 232 |
Qwen3 14B (no reasoning)Alibaba |
|
| 232 |
Qwen3 30B A3B Thinking 2507Alibaba |
|
| 232 |
Qwen3 VL 30B A3B ThinkingAlibaba |
|
| 232 |
gpt-oss-120b (low)OpenAI |
|
| 232 |
GLM 4.5V (thinking reasoning)Z.ai |
|
| 237 |
Qwen2.5 72B InstructAlibaba |
|
| 237 |
qwen3-4b-instruct-2507Alibaba |
|
| 237 |
Gemini 2.5 Flash Lite (thinking reasoning)Google |
|
| 237 |
magistral-small-2509Mistral |
|
| 237 |
Ministral 3 14B 2512Mistral |
|
| 237 |
Ministral 3 8B 2512Mistral |
|
| 237 |
gpt-oss-20b (low reasoning)OpenAI |
|
| 244 |
Qwen3 14B (thinking reasoning)Alibaba |
|
| 244 |
qwen3.5-2b (no reasoning)Alibaba |
|
| 244 |
qwen3.5-2b (thinking reasoning)Alibaba |
|
| 244 |
qwen3-omni-30b-a3b-thinkingAlibaba |
|
| 244 |
Qwen3 VL 8B ThinkingAlibaba |
|
| 244 |
Nova 2 Lite (low reasoning)Amazon |
|
| 244 |
Gemma 3 27BGoogle |
|
| 244 |
Phi 4Microsoft |
|
| 244 |
Mistral Medium 3Mistral |
|
| 244 |
GPT-4.1 NanoOpenAI |
|
| 244 |
GLM 4.7 Flash (no reasoning)Z.ai |
|
| 255 |
Qwen3 32B (thinking reasoning)Alibaba |
|
| 255 |
gemma-4-e2b-itGoogle |
|
| 255 |
Llama 3.1 70B InstructMeta |
|
| 255 |
Llama 3.3 70B InstructMeta |
|
| 255 |
GLM 4.6V (no reasoning)Z.ai |
|
| 260 |
Qwen3 30B A3B (thinking reasoning)Alibaba |
|
| 260 |
Qwen3 8B (no reasoning)Alibaba |
|
| 260 |
Qwen3 8B (thinking reasoning)Alibaba |
|
| 260 |
Qwen3 VL 8B InstructAlibaba |
|
| 260 |
Gemini 2.5 Flash Lite (no reasoning)Google |
|
| 260 |
gemma-4-e2b-it (no reasoning)Google |
|
| 266 |
qwen3-4b-thinking-2507Alibaba |
|
| 266 |
Qwen3 Omni 30B A3B InstructAlibaba |
|
| 266 |
qwen3-vl-4b-thinkingAlibaba |
|
| 266 |
Nova Micro 1.0Amazon |
|
| 266 |
Llama 4 ScoutMeta |
|
| 271 |
Nova Lite 1.0Amazon |
|
| 271 |
Command ACohere |
|
| 271 |
Gemma 3 12BGoogle |
|
| 271 |
Gemma 3 4BGoogle |
|
| 271 |
Llama 3.1 8B InstructMeta |
|
| 276 |
qwen3.5-0.8b (no reasoning)Alibaba |
|
| 276 |
qwen3.5-0.8b (thinking reasoning)Alibaba |
|
| 276 |
qwen3-vl-4b-instructAlibaba |
|
| 276 |
Gemma 3 270MGoogle |
|
| 276 |
Llama 3.2 1B InstructMeta |
|
| 276 |
Ministral 3 3B 2512Mistral |
|
| 276 |
Reka Flash 3Rekaai |
|