src/data/open/stats.csv

"Model Name"	"Link"	"Comment"	"Group"	"Med. Len."	"Med. Resp. Len."	"Parameter Size (B)"	"Type"	"Model Type"	"Think"	"Overall"	"Content Generation"	"Editing"	"Data Analysis"	"Reasoning"	"Hallucination"	"Safety"	"Repetition"	"Summarization"	"Translation"	"Multi-Turn"
"GPT-5 (Reasoning: medium)"	"https://platform.openai.com/docs/models/gpt-5"	"Reasoning: medium"	"GPT"	""	""	""	"Proprietary"	"Think"	"On"	"70.73"	"71.0"	"74.38"	"76.49"	"79.75"	"64.94"	"56.2"	"82.86"	"80.16"	"69.38"	"54.36"
"o3-pro (Reasoning: medium)"	"https://platform.openai.com/docs/models/o3-pro"	"Reasoning: medium"	"GPT"	""	""	""	"Proprietary"	"Think"	"On"	"66.47"	"72.5"	"70.31"	"75.7"	"83.88"	"64.37"	"33.88"	"74.29"	"65.48"	"64.33"	"48.32"
"GPT-5.2 (Reasoning: medium)"	"https://platform.openai.com/docs/models/gpt-5.2"	"Reasoning: medium"	"GPT"	"347.0"	"264.0"	""	"Proprietary"	"Hybrid"	"On"	"66.18"	"69.25"	"65.62"	"71.31"	"78.51"	"70.69"	"52.07"	"51.43"	"80.56"	"55.9"	"55.03"
"GPT-5.1 (Reasoning: medium, verbosity: medium)"	"https://platform.openai.com/docs/models/gpt-5.1"	"Reasoning: medium, verbosity: medium"	"GPT"	""	""	""	"Proprietary"	"Hybrid"	"On"	"64.57"	"67.0"	"70.0"	"72.51"	"82.64"	"65.52"	"52.07"	"51.43"	"67.06"	"59.55"	"45.64"
"Claude 4.5 Opus (think, budget: 16K)"	"https://www.anthropic.com/claude/opus"	"thinking budget: 16K"	"Claude"	""	""	""	"Proprietary"	"Hybrid"	"On"	"63.41"	"63.5"	"62.5"	"73.71"	"77.69"	"82.76"	"52.89"	"58.57"	"63.49"	"56.74"	"45.97"
"Claude 4 Opus (20250514) (think)"	"https://www.anthropic.com/claude/opus"	"version: 20250514"	"Claude"	""	""	""	"Proprietary"	"Hybrid"	"On"	"63.29"	"60.75"	"59.69"	"73.31"	"69.83"	"78.74"	"53.72"	"55.71"	"65.48"	"65.45"	"48.99"
"Claude 4.1 Opus (20250805) (think)"	"https://www.anthropic.com/claude/opus"	"version: 20250805"	"Claude"	""	""	""	"Proprietary"	"Hybrid"	"On"	"63.24"	"61.25"	"60.0"	"78.49"	"72.73"	"77.01"	"56.2"	"57.14"	"61.9"	"62.64"	"46.98"
"GPT-5 mini (Reasoning: medium)"	"https://platform.openai.com/docs/models/gpt-5-mini"	"Reasoning: medium"	"GPT"	""	""	""	"Proprietary"	"Think"	"On"	"62.56"	"68.0"	"62.5"	"74.9"	"76.86"	"55.17"	"47.93"	"44.29"	"74.6"	"56.18"	"45.3"
"Gemini 3 Pro Preview (Thinking Level: High)"	"https://deepmind.google/models/gemini/pro/"	"Thinking Level: High"	"Gemini"	"1930.5"	"378.0"	""	"Proprietary"	"Think"	"On"	"62.48"	"59.5"	"64.38"	"76.49"	"78.93"	"70.69"	"39.67"	"65.71"	"61.51"	"58.15"	"48.99"
"Claude 4 Sonnet (20250514) (think)"	"https://www.anthropic.com/claude/sonnet"	"version: 20250514"	"Claude"	""	""	""	"Proprietary"	"Hybrid"	"On"	"61.8"	"58.0"	"58.44"	"76.49"	"67.77"	"79.31"	"57.02"	"44.29"	"65.08"	"62.92"	"44.97"
"o3"	"https://platform.openai.com/docs/models/o3"	""	"GPT"	""	""	""	"Proprietary"	"Think"	"On"	"60.91"	"68.75"	"60.0"	"73.31"	"79.34"	"54.02"	"34.71"	"64.29"	"60.71"	"55.06"	"46.98"
"Gemini 2.5 Pro"	"https://deepmind.google/models/gemini/pro/"	""	"Gemini"	""	""	""	"Proprietary"	"Think"	"On"	"59.34"	"54.0"	"60.94"	"78.88"	"73.14"	"63.22"	"17.36"	"52.86"	"67.86"	"53.93"	"52.68"
"Gemini 3 Flash Preview (Thinking Level: High)"	"https://deepmind.google/models/gemini/flash/"	"Thinking Level: High"	"Gemini"	"1296.5"	"424.5"	""	"Proprietary"	"Think"	"On"	"59.26"	"59.5"	"59.69"	"75.3"	"79.34"	"63.22"	"34.71"	"57.14"	"59.92"	"50.84"	"46.31"
"GLM-4.7 FP8"	"https://huggingface.co/zai-org/GLM-4.7-FP8"	"temperature: 1.0
top-p: 0.95"	"GLM"	"2252.5"	"328.0"	"358.0"	"Open"	"Hybrid"	"On"	"59.22"	"62.75"	"60.0"	"75.3"	"75.21"	"58.05"	"29.75"	"35.71"	"66.67"	"53.93"	"45.3"
"DeepSeek V3.2 Speciale"	"https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Speciale"	"temperature: 1.0
top-p: 0.95"	"DeepSeek"	"3226.5"	"249.5"	"671.0"	"Open"	"Think"	"On"	"59.14"	"64.0"	"67.19"	"74.5"	"78.1"	"48.28"	"20.66"	"58.57"	"66.27"	"53.09"	"38.93"
"Grok-4"	"https://x.ai/news/grok-4"	"temperature: 0.6
top-p: 0.95"	"Grok"	""	""	""	"Proprietary"	"Think"	"On"	"58.74"	"61.0"	"66.25"	"72.51"	"63.22"	"66.09"	"16.53"	"58.57"	"66.27"	"54.21"	"44.3"
"Gemini 2.5 Flash"	"https://deepmind.google/models/gemini/flash/"	""	"Gemini"	""	""	""	"Proprietary"	"Hybrid"	"On"	"58.62"	"57.25"	"62.19"	"70.52"	"72.31"	"56.9"	"28.93"	"47.14"	"68.65"	"55.06"	"46.98"
"o4-mini"	"https://platform.openai.com/docs/models/o4-mini"	""	"GPT"	""	""	""	"Proprietary"	"Think"	"On"	"57.57"	"67.25"	"61.25"	"71.71"	"75.62"	"45.4"	"39.67"	"44.29"	"59.92"	"47.19"	"41.95"
"Kimi K2 Thinking"	"https://huggingface.co/moonshotai/Kimi-K2-Thinking"	"temperature:1.0
top-p: 0.95"	"moonshot"	"1692.0"	"330.0"	"1000.0"	"Open"	"Think"	"On"	"56.84"	"58.25"	"50.31"	"69.72"	"77.27"	"60.92"	"44.63"	"38.57"	"59.92"	"52.25"	"44.3"
"Qwen3 235B A22B Thinking 2507"	"https://huggingface.co/Qwen/Qwen3-235B-A22B-Thinking-2507"	"temperature: 0.6
top-p: 0.95"	"Qwen"	"2404.5"	"423.0"	"235.0"	"Open"	"Think"	"On"	"55.48"	"57.5"	"53.12"	"73.31"	"75.21"	"55.17"	"25.62"	"35.71"	"55.56"	"56.18"	"40.27"
"GPT-5 nano (Reasoning: medium)"	"https://platform.openai.com/docs/models/gpt-5-nano"	"Reasoning: medium"	"GPT"	""	""	""	"Proprietary"	"Think"	"On"	"55.39"	"63.5"	"47.19"	"68.92"	"75.21"	"55.17"	"52.07"	"34.29"	"63.49"	"40.73"	"42.95"
"GLM-4.5 FP8"	"https://huggingface.co/zai-org/GLM-4.5-FP8"	"temperature: 0.6
top-p: 0.95"	"GLM"	"1442.0"	"604.0"	"358.0"	"Open"	"Hybrid"	"On"	"54.03"	"60.75"	"53.75"	"68.92"	"74.38"	"47.13"	"33.06"	"41.43"	"60.32"	"46.07"	"35.91"
"GLM-4.6 FP8"	"https://huggingface.co/zai-org/GLM-4.6-FP8"	"temperature: 1.0
top-p: 0.95"	"GLM"	"2645.5"	"522.0"	"358.0"	"Open"	"Hybrid"	"On"	"53.3"	"57.5"	"51.25"	"71.31"	"71.9"	"53.45"	"24.79"	"28.57"	"58.33"	"44.38"	"43.29"
"Gemini 2.5 Flash-lite Preview (09-2025)"	"https://deepmind.google/models/gemini/"	"version: 09-2025"	"Gemini"	""	""	""	"Proprietary"	"Think"	"On"	"53.06"	"55.0"	"55.94"	"68.13"	"70.25"	"47.7"	"23.97"	"30.0"	"60.71"	"46.63"	"42.28"
"Qwen3 235B A22B Instruct 2507"	"https://huggingface.co/Qwen/Qwen3-235B-A22B-Instruct-2507"	"temperature: 0.7
top-p: 0.8"	"Qwen"	"433.0"	"433.0"	"235.0"	"Open"	"Instruct"	"Off"	"52.94"	"58.0"	"49.69"	"68.13"	"73.97"	"55.17"	"45.45"	"30.0"	"55.95"	"38.48"	"41.61"
"DeepSeek V3.2"	"https://huggingface.co/deepseek-ai/DeepSeek-V3.2"	"temperature: 1.0
top-p: 0.95"	"DeepSeek"	"762.5"	"312.0"	"671.0"	"Open"	"Think"	"On"	"52.17"	"51.25"	"51.56"	"70.92"	"72.31"	"51.15"	"36.36"	"37.14"	"60.32"	"40.17"	"39.93"
"DeepSeek V3.1 (think)"	"https://huggingface.co/deepseek-ai/DeepSeek-V3.1"	"temperature: 0.6
top-p: 0.95"	"DeepSeek"	"710.5"	"356.0"	"671.0"	"Open"	"Hybrid"	"On"	"51.45"	"52.0"	"50.0"	"67.33"	"69.83"	"50.0"	"33.88"	"35.71"	"59.52"	"41.85"	"40.27"
"DeepSeek V3.1 Terminus (think)"	"https://huggingface.co/deepseek-ai/DeepSeek-V3.1-Terminus"	"temperature: 0.6
top-p: 0.95"	"DeepSeek"	"831.5"	"377.0"	"671.0"	"Open"	"Hybrid"	"On"	"51.37"	"51.5"	"52.19"	"69.32"	"73.14"	"51.72"	"25.62"	"38.57"	"57.14"	"38.76"	"40.94"
"Qwen3 30B A3B Thinking 2507"	"https://huggingface.co/Qwen/Qwen3-30B-A3B-Thinking-2507"	"temperature: 0.6
top-p: 0.95"	"Qwen"	"2830.0"	"351.0"	"30.0"	"Open"	"Think"	"On"	"50.44"	"56.25"	"45.0"	"69.32"	"69.01"	"50.0"	"29.75"	"30.0"	"48.02"	"47.47"	"36.58"
"MiMo V2 Flash"	"https://huggingface.co/XiaomiMiMo/MiMo-V2-Flash"	"temperature: 0.8
top-p: 0.95"	"XiaomiMiMo"	"1477.5"	"373.0"	"309.0"	"Open"	"Think"	"On"	"50.32"	"54.0"	"48.12"	"67.73"	"68.18"	"44.83"	"48.76"	"28.57"	"53.97"	"40.73"	"35.91"
"gpt-oss-120B (Reasoning: medium)"	"https://huggingface.co/openai/gpt-oss-120b"	"Reasoning: medium
temperature: 1.0
top-p: 1.0"	"GPT"	"759.5"	"370.5"	"117.0"	"Open"	"Think"	"On"	"49.11"	"58.5"	"48.44"	"68.92"	"69.83"	"41.38"	"39.67"	"25.71"	"50.79"	"35.67"	"32.21"
"DeepSeek R1 (0528) (top_p: 0.95, temp:0.6)"	"https://huggingface.co/deepseek-ai/DeepSeek-R1-0528"	"version: 0528
temperature: 0.6
top-p: 0.95"	"DeepSeek"	"1177.5"	"554.0"	"671.0"	"Open"	"Think"	"On"	"48.79"	"49.75"	"50.0"	"65.34"	"59.09"	"48.85"	"38.02"	"32.86"	"57.94"	"36.52"	"38.93"
"Gauss2.3 Hybrid"	""	""	"Gauss"	"546.0"	"308.0"	""	"Proprietary"	"Hybrid"	"On"	"46.58"	"52.0"	"46.25"	"59.76"	"66.94"	"41.95"	"34.71"	"25.71"	"53.17"	"34.55"	"33.22"
"Mistral Large 3 675B Instruct 2512"	"https://huggingface.co/mistralai/Mistral-Large-3-675B-Instruct-2512"	"temperature: 0.15"	"mistralai"	"448.0"	"448.0"	"675.0"	"Open"	"Instruct"	"Off"	"45.21"	"44.0"	"50.62"	"65.34"	"60.33"	"33.33"	"14.88"	"37.14"	"53.97"	"36.52"	"35.91"
"DeepSeek V3 (0324) (top_p: 0.95, temp:1.3)"	"https://huggingface.co/deepseek-ai/DeepSeek-V3-0324"	"version: 0324
temperature: 1.3
top-p: 0.95"	"DeepSeek"	"408.0"	"408.0"	"671.0"	"Open"	"Instruct"	"Off"	"45.09"	"46.25"	"45.0"	"58.96"	"60.33"	"41.95"	"21.49"	"30.0"	"55.95"	"38.48"	"33.22"
"Qwen3 32B (think)"	"https://huggingface.co/Qwen/Qwen3-32B"	"temperature: 0.6
top-p: 0.95"	"Qwen"	"1113.0"	"390.0"	"32.8"	"Open"	"Hybrid"	"On"	"44.44"	"52.25"	"41.56"	"68.92"	"66.53"	"35.06"	"19.83"	"25.71"	"46.43"	"30.9"	"32.89"
"Qwen3 30B A3B Instruct 2507"	"https://huggingface.co/Qwen/Qwen3-30B-A3B-Instruct-2507"	"temperature: 0.7
top-p: 0.8"	"Qwen"	"441.5"	"441.5"	"30.0"	"Open"	"Instruct"	"Off"	"42.79"	"45.0"	"35.0"	"56.18"	"66.12"	"51.15"	"33.06"	"24.29"	"46.83"	"28.09"	"35.57"
"MiniMax-M2 (230B A10B)"	"https://huggingface.co/MiniMaxAI/MiniMax-M2"	"temperature:1.0
top-p: 0.95"	"MiniMaxAI"	"1142.0"	"325.0"	"230.0"	"Open"	"Think"	"On"	"42.43"	"48.75"	"35.62"	"53.39"	"57.02"	"43.1"	"44.63"	"28.57"	"49.21"	"30.06"	"31.21"
"A.X 4.0"	"https://huggingface.co/skt/A.X-4.0"	""	"SKT"	"412.5"	"412.5"	"71.9"	"Open"	"Instruct"	"Off"	"41.59"	"56.0"	"43.75"	"43.43"	"42.56"	"40.23"	"15.7"	"24.29"	"53.97"	"33.43"	"32.21"
"gpt-oss-20B (Reasoning: medium)"	"https://huggingface.co/openai/gpt-oss-20b"	"Reasoning: medium
temperature: 1.0
top-p: 1.0"	"GPT"	"953.5"	"326.0"	"21.0"	"Open"	"Think"	"On"	"41.18"	"52.0"	"40.0"	"61.35"	"65.7"	"43.1"	"41.32"	"22.86"	"36.51"	"20.51"	"22.82"
"Gemma 3 27B it"	"https://huggingface.co/google/gemma-3-27b-it"	"temperature: 1.0
top-p: 0.95"	"Gemma"	"380.0"	"380.0"	"27.0"	"Open"	"Instruct"	"Off"	"40.86"	"44.25"	"45.0"	"45.82"	"36.78"	"31.61"	"32.23"	"22.86"	"57.14"	"32.87"	"39.93"
"Tongyi DeepResearch 30B A3B"	"https://huggingface.co/Alibaba-NLP/Tongyi-DeepResearch-30B-A3B"	"temperature: 0.6
top-p: 0.95"	"Alibaba"	"1147.0"	"408.0"	"30.0"	"Open"	"Think"	"On"	"40.1"	"41.25"	"33.12"	"62.15"	"68.18"	"44.25"	"23.97"	"18.57"	"41.67"	"26.12"	"29.19"
"Mistral Small 3.2 24B Instruct 2506"	"https://huggingface.co/mistralai/Mistral-Small-3.2-24B-Instruct-2506"	"temperature: 0.15
top-p: 0.95"	"mistralai"	"369.0"	"369.0"	"24.0"	"Open"	"Instruct"	"Off"	"39.09"	"43.0"	"44.69"	"43.43"	"51.65"	"25.86"	"22.31"	"25.71"	"51.98"	"31.18"	"30.2"
"K2-Think"	"https://huggingface.co/LLM360/K2-Think"	"temperature: 1.0
top-p: 0.95"	"LLM360"	"1835.0"	"486.0"	"32.8"	"Open"	"Think"	"On"	"35.06"	"35.5"	"36.56"	"56.18"	"47.11"	"35.06"	"14.05"	"12.86"	"49.21"	"21.63"	"23.15"
"Kanana 2 30B A3B Thinking"	"https://huggingface.co/kakaocorp/kanana-2-30b-a3b-thinking"	"temperature: 0.6
top-p: 0.95
top-k: 20"	"Kakao"	"4263.0"	"854.5"	"31.0"	"Open"	"Think"	"On"	"34.5"	"37.5"	"25.0"	"57.77"	"54.55"	"39.66"	"20.66"	"15.71"	"38.1"	"24.72"	"20.47"
"KAT Dev 72B Exp"	"https://huggingface.co/Kwaipilot/KAT-Dev-72B-Exp"	"temperature:0.6
top-p: 0.95"	"KAT"	"397.0"	"397.0"	"72.0"	"Open"	"Instruct"	"Off"	"33.94"	"29.25"	"44.06"	"46.22"	"46.69"	"25.86"	"18.18"	"20.0"	"42.86"	"25.56"	"25.5"
"Olmo 3 32B Think"	"https://huggingface.co/allenai/Olmo-3-32B-Think"	"temperature: 1
top-p: 0.95
top-k: 50"	"allenai"	"3360.5"	"473.0"	"32.0"	"Open"	"Think"	"On"	"33.94"	"35.25"	"30.94"	"57.37"	"66.53"	"33.33"	"28.93"	"24.29"	"34.52"	"11.8"	"19.8"
"EXAONE 4.0 32B (think)"	"https://huggingface.co/LGAI-EXAONE/EXAONE-4.0-32B"	"temperature: 0.6
top-p: 0.95"	"Exaone"	"1274.5"	"503.0"	"32.0"	"Open"	"Hybrid"	"On"	"33.82"	"34.25"	"29.38"	"56.97"	"57.44"	"24.71"	"27.27"	"17.14"	"38.49"	"18.54"	"25.5"
"Apriel 1.5 15B Thinker"	"https://huggingface.co/ServiceNow-AI/Apriel-1.5-15b-Thinker"	"temperature: 0.6
top-p: 0.95"	"Apriel"	"2238.0"	"375.0"	"15.0"	"Open"	"Think"	"On"	"31.92"	"44.25"	"26.56"	"47.41"	"59.09"	"22.99"	"37.19"	"20.0"	"26.98"	"20.22"	"10.07"
"HyperCLOVAX SEED Think 14B (think)"	"https://huggingface.co/naver-hyperclovax/HyperCLOVAX-SEED-Think-14B"	"temperature: 0.5
top-p: 0.6"	"HCX"	"1444.0"	"382.5"	"14.7"	"Open"	"Hybrid"	"On"	"31.84"	"35.0"	"26.56"	"53.78"	"58.68"	"27.59"	"26.45"	"17.14"	"29.76"	"17.13"	"20.47"
"Kanana 2 30B A3B Instruct"	"https://huggingface.co/kakaocorp/kanana-2-30b-a3b-instruct"	"temperature: 0"	"Kakao"	"1195.0"	"1195.0"	"31.0"	"Open"	"Instruct"	"Off"	"30.84"	"38.0"	"25.62"	"35.86"	"47.11"	"37.93"	"23.97"	"18.57"	"35.32"	"20.51"	"19.46"
"Dhanishtha-2.0 Preview"	"https://huggingface.co/HelpingAI/Dhanishtha-2.0-preview"	"temperature: 0.7
top-p: 0.9"	"HelpingAI"	"520.0"	"356.0"	"14.8"	"Open"	"Think"	"On"	"25.81"	"28.25"	"19.38"	"30.28"	"33.47"	"43.1"	"47.93"	"20.0"	"31.75"	"12.08"	"13.09"
"ERNIE 4.5 21B A3B Thinking"	"https://huggingface.co/baidu/ERNIE-4.5-21B-A3B-Thinking"	"temperature: 0.6
top-p: 0.95"	"ERNIE"	"1637.0"	"541.0"	"21.0"	"Open"	"Think"	"On"	"25.32"	"27.25"	"20.31"	"42.23"	"49.59"	"23.56"	"31.4"	"17.14"	"28.17"	"7.3"	"13.76"
"Solar Pro Preview (top_p:0.95, temp: 0.7)"	"https://huggingface.co/upstage/solar-pro-preview-instruct"	"temperature: 0.7
top-p: 0.95"	"Solar"	"260.0"	"260.0"	"22.0"	"Open"	"Instruct"	"Off"	"20.73"	"28.0"	"24.69"	"16.73"	"19.42"	"17.24"	"28.1"	"11.43"	"31.35"	"13.76"	"11.74"
"Mi:dm 2.0 Base Instruct"	"https://huggingface.co/K-intelligence/Midm-2.0-Base-Instruct"	"temperature: 0.8
top-p: 0.7"	"KT"	"316.0"	"316.0"	"11.5"	"Open"	"Instruct"	"Off"	"20.25"	"21.75"	"17.5"	"16.73"	"18.6"	"27.59"	"59.5"	"14.29"	"25.4"	"12.64"	"11.41"
"Kanana 1.5 15.7B A3B Instruct"	"https://huggingface.co/kakaocorp/kanana-1.5-15.7b-a3b-instruct"	"temperature: 1.0
top-p: 0.95"	"Kakao"	"414.0"	"414.0"	"15.7"	"Open"	"Instruct"	"Off"	"11.71"	"14.25"	"10.62"	"13.55"	"11.16"	"22.41"	"22.31"	"4.29"	"11.9"	"6.74"	"5.37"