llmrun Composite Score
The best LLMs, open and proprietary together, on one open-ended scale where 100 is the average model (overall capability). Switch to open models to see only what you can download and run.
46 benchmarks4 sourcesUpdated 14 Nov 2026Reference scale 2026-Q4How the Composite Score is built
Composite Score vs VRAM needed
This chart doesn't show proprietary models.
| # | Model | llmrun Composite Score | Coding | Agents | Math | Science | Reasoning | Benchmarks | VRAM |
|---|---|---|---|---|---|---|---|---|---|
| 121 | Grok Build 0.15 benchmarks | Coding 111 | Agents – | Math – | Science 118 | Reasoning – | 5 | – | |
| 122 | Qwen3 235B A22B Thinking 2507open143 GB · 13 benchmarks | Coding 102 | Agents – | Math – | Science 108 | Reasoning 108 | 13 | 143 GB | |
| 123 | Gemini 2.5 Pro16 benchmarks | Coding 112 | Agents 102 | Math 109 | Science 113 | Reasoning 108 | 16 | – | |
| 124 | MiMo V2.5open188 GB · 4 benchmarks | Coding 103 | Agents – | Math – | Science 107 | Reasoning – | 4 | 188 GB | |
| 125 | Kimi K2 Thinkingopen617 GB · 9 benchmarks | Coding 103 | Agents 108 | Math – | Science – | Reasoning – | 9 | 617 GB | |
| 126 | MiniMax M2.7open140 GB · 7 benchmarks | Coding 103 | Agents 112 | Math – | Science 112 | Reasoning – | 7 | 140 GB | |
| 127 | DeepSeek V3.1 Terminusopen412 GB · 5 benchmarks | Coding 107 | Agents – | Math – | Science 99 | Reasoning 108 | 5 | 412 GB | |
| 128 | GPT 5.5 Instant6 benchmarks | Coding – | Agents – | Math 105 | Science 112 | Reasoning – | 6 | – | |
| 129 | Qwen3.6 35B A3Bopen22.0 GB · 11 benchmarks | Coding 105 | Agents – | Math 109 | Science 110 | Reasoning 104 | 11 | 22.0 GB | |
| 130 | Claude Opus 4.1 (Aug 05, 2025)14 benchmarks | Coding 106 | Agents 108 | Math 103 | Science 105 | Reasoning 117 | 14 | – | |
| 131 | Gemini 2.5 Pro Preview (Mar 25)5 benchmarks | Coding – | Agents – | Math – | Science – | Reasoning 106 | 5 | – | |
| 132 | Gemma 4 31B ITopen21.7 GB · 14 benchmarks | Coding 107 | Agents – | Math – | Science 105 | Reasoning 111 | 14 | 21.7 GB | |
| 133 | Qwen3.5 Flash10 benchmarks | Coding – | Agents – | Math 106 | Science – | Reasoning 110 | 10 | – | |
| 134 | Gemma 4 26B A4B ITopen16.5 GB · 8 benchmarks | Coding 104 | Agents – | Math – | Science 102 | Reasoning 102 | 8 | 16.5 GB | |
| 135 | Qwen3.6 Flash10 benchmarks | Coding – | Agents – | Math 108 | Science – | Reasoning 103 | 10 | – | |
| 136 | Claude Opus 4 (May 14, 2025)13 benchmarks | Coding 107 | Agents – | Math – | Science 104 | Reasoning 108 | 13 | – | |
| 137 | Mercury 24 benchmarks | Coding 106 | Agents – | Math – | Science 100 | Reasoning – | 4 | – | |
| 138 | Claude Haiku 4.5 (Oct 01, 2025)17 benchmarks | Coding 105 | Agents 104 | Math – | Science 101 | Reasoning 108 | 17 | – | |
| 139 | Qwen3.5 35B A3Bopen22.0 GB · 8 benchmarks | Coding 86 | Agents – | Math – | Science 108 | Reasoning 107 | 8 | 22.0 GB | |
| 140 | Qwen3 Max (Sep 23, 2025)11 benchmarks | Coding – | Agents – | Math 105 | Science – | Reasoning 107 | 11 | – | |
| 141 | O1 (Dec 17, 2024)13 benchmarks | Coding 104 | Agents – | Math 104 | Science 104 | Reasoning 102 | 13 | – | |
| 142 | Gemini 2.5 Pro Preview (May 06)4 benchmarks | Coding – | Agents – | Math – | Science 98 | Reasoning – | 4 | – | |
| 143 | MiniMax M2.1open140 GB · 4 benchmarks | Coding – | Agents – | Math – | Science – | Reasoning – | 4 | 140 GB | |
| 144 | GPT 5.4 2026 03.056 benchmarks | Coding 118 | Agents – | Math – | Science – | Reasoning 101 | 6 | – | |
| 145 | Claude Sonnet 4 (May 14, 2025)16 benchmarks | Coding 104 | Agents – | Math – | Science 104 | Reasoning 107 | 16 | – | |
| 146 | Claude 3.7 Sonnet (Feb 19, 2025)10 benchmarks | Coding – | Agents – | Math – | Science 105 | Reasoning 104 | 10 | – | |
| 147 | Qwen3 Coder 480B A35B Instructopen291 GB · 6 benchmarks | Coding 101 | Agents 105 | Math – | Science – | Reasoning – | 6 | 291 GB | |
| 148 | Gemini 2.5 Flash Preview (May 20)7 benchmarks | Coding 100 | Agents – | Math – | Science – | Reasoning 104 | 7 | – | |
| 149 | Qwen3.5 27Bopen17.9 GB · 6 benchmarks | Coding 98 | Agents – | Math – | Science – | Reasoning 111 | 6 | 17.9 GB | |
| 150 | DeepSeek R1 0528open412 GB · 10 benchmarks | Coding 107 | Agents – | Math – | Science – | Reasoning 100 | 10 | 412 GB | |
| 151 | Seed 1.64 benchmarks | Coding – | Agents – | Math – | Science – | Reasoning – | 4 | – | |
| 152 | GLM 4.6open217 GB · 6 benchmarks | Coding 96 | Agents 104 | Math – | Science 100 | Reasoning – | 6 | 217 GB | |
| 153 | Kimi K2 Instruct 0905open617 GB · 6 benchmarks | Coding 100 | Agents – | Math – | Science – | Reasoning – | 6 | 617 GB | |
| 154 | Seed OSS 36B Instructopen24.1 GB · 3 benchmarks | Coding – | Agents – | Math – | Science – | Reasoning – | 3 | 24.1 GB | |
| 155 | MiniMax M2open140 GB · 6 benchmarks | Coding – | Agents 105 | Math – | Science – | Reasoning – | 6 | 140 GB | |
| 156 | Mistral Medium 3.5 128Bopen82.8 GB · 9 benchmarks | Coding 102 | Agents – | Math – | Science 101 | Reasoning 102 | 9 | 82.8 GB | |
| 157 | O3 Mini (Jan 31, 2025)19 benchmarks | Coding 103 | Agents – | Math 106 | Science 106 | Reasoning 100 | 19 | – | |
| 158 | Grok 3 Mini Beta6 benchmarks | Coding 99 | Agents – | Math – | Science – | Reasoning – | 6 | – | |
| 159 | GLM 4.5open218 GB · 7 benchmarks | Coding 99 | Agents 105 | Math – | Science – | Reasoning – | 7 | 218 GB | |
| 160 | Qwen3 30B A3B Thinking 2507open19.4 GB · 7 benchmarks | Coding – | Agents – | Math – | Science 99 | Reasoning 94 | 7 | 19.4 GB | |
| 161 | Gemini 2.5 Flash9 benchmarks | Coding – | Agents 94 | Math – | Science – | Reasoning 104 | 9 | – | |
| 162 | GPT 5.2 2025 12.116 benchmarks | Coding – | Agents – | Math – | Science – | Reasoning 95 | 6 | – | |
| 163 | DeepSeek V3.1open412 GB · 7 benchmarks | Coding – | Agents – | Math – | Science – | Reasoning 106 | 7 | 412 GB | |
| 164 | Kimi K2 Instructopen617 GB · 10 benchmarks | Coding 102 | Agents 102 | Math – | Science – | Reasoning 93 | 10 | 617 GB | |
| 165 | Qwen3 235B A22Bopen143 GB · 9 benchmarks | Coding 101 | Agents – | Math – | Science – | Reasoning 101 | 9 | 143 GB | |
| 166 | Gemini 2.5 Flash Preview (Apr 17)5 benchmarks | Coding – | Agents – | Math – | Science – | Reasoning – | 5 | – | |
| 167 | Qwen3.5 9Bopen6.6 GB · 8 benchmarks | Coding – | Agents – | Math – | Science 105 | Reasoning 97 | 8 | 6.6 GB | |
| 168 | GPT 5 Nano (Aug 07, 2025)17 benchmarks | Coding 102 | Agents – | Math 108 | Science – | Reasoning 90 | 17 | – | |
| 169 | DeepSeek R1open412 GB · 12 benchmarks | Coding 100 | Agents – | Math – | Science 99 | Reasoning 95 | 12 | 412 GB | |
| 170 | Grok Code Fast 13 benchmarks | Coding 99 | Agents – | Math – | Science – | Reasoning – | 3 | – | |
| 171 | Grok 3 Mini3 benchmarks | Coding – | Agents – | Math – | Science – | Reasoning 97 | 3 | – | |
| 172 | Qwen3 32Bopen22.6 GB · 8 benchmarks | Coding 93 | Agents – | Math – | Science 96 | Reasoning 92 | 8 | 22.6 GB | |
| 173 | DeepSeek Chat5 benchmarks | Coding – | Agents – | Math – | Science – | Reasoning 86 | 5 | – | |
| 174 | Qwen3 235B A22B Instruct 2507open143 GB · 8 benchmarks | Coding 102 | Agents – | Math – | Science – | Reasoning 98 | 8 | 143 GB | |
| 175 | Qwen3.5 4Bopen3.4 GB · 3 benchmarks | Coding – | Agents – | Math – | Science – | Reasoning – | 3 | 3.4 GB | |
| 176 | GLM 4.5 Airopen67.6 GB · 4 benchmarks | Coding – | Agents – | Math – | Science – | Reasoning – | 4 | 67.6 GB | |
| 177 | Grok 3 Beta5 benchmarks | Coding – | Agents – | Math – | Science – | Reasoning – | 5 | – | |
| 178 | Qwen3 14Bopen11.9 GB · 7 benchmarks | Coding – | Agents – | Math – | Science 94 | Reasoning 88 | 7 | 11.9 GB | |
| 179 | GPT OSS 120Bopen70.8 GB · 19 benchmarks | Coding 98 | Agents 82 | Math – | Science 103 | Reasoning 96 | 19 | 70.8 GB | |
| 180 | DeepSeek R1 Distill Qwen 32Bopen24.3 GB · 3 benchmarks | Coding – | Agents – | Math – | Science – | Reasoning – | 3 | 24.3 GB | |
| 181 | Qwen3 30B A3B Instruct 2507open19.4 GB · 4 benchmarks | Coding – | Agents – | Math – | Science – | Reasoning 93 | 4 | 19.4 GB | |
| 182 | GPT OSS 20Bopen13.1 GB · 10 benchmarks | Coding 102 | Agents – | Math – | Science 93 | Reasoning 91 | 10 | 13.1 GB | |
| 183 | QwQ 32Bopen24.3 GB · 5 benchmarks | Coding – | Agents – | Math – | Science – | Reasoning – | 5 | 24.3 GB | |
| 184 | NVIDIA Nemotron 3 Super 120B A12B BF16open74.7 GB · 4 benchmarks | Coding 96 | Agents – | Math – | Science 98 | Reasoning – | 4 | 74.7 GB | |
| 185 | GPT 4.1 (Apr 14, 2025)16 benchmarks | Coding 99 | Agents – | Math 92 | Science 96 | Reasoning 92 | 16 | – | |
| 186 | GPT 4.5 Preview (Feb 27, 2025)10 benchmarks | Coding 96 | Agents – | Math – | Science 98 | Reasoning 96 | 10 | – | |
| 187 | Mercury 2.54 benchmarks | Coding 95 | Agents – | Math – | Science 99 | Reasoning – | 4 | – | |
| 188 | DeepSeek v3 0324open412 GB · 12 benchmarks | Coding 100 | Agents – | Math – | Science 98 | Reasoning 88 | 12 | 412 GB | |
| 189 | Qwen3 8Bopen7.6 GB · 7 benchmarks | Coding – | Agents – | Math – | Science 88 | Reasoning 81 | 7 | 7.6 GB | |
| 190 | Qwen3 30B A3Bopen19.4 GB · 6 benchmarks | Coding – | Agents – | Math – | Science – | Reasoning 84 | 6 | 19.4 GB | |
| 191 | Grok 34 benchmarks | Coding – | Agents – | Math – | Science – | Reasoning 92 | 4 | – | |
| 192 | GPT 5.4 Nano 2026 03.176 benchmarks | Coding – | Agents – | Math 95 | Science – | Reasoning 94 | 6 | – | |
| 193 | GPT 5.1 2025 11.137 benchmarks | Coding – | Agents – | Math – | Science 96 | Reasoning 91 | 7 | – | |
| 194 | O1 Mini (Sep 12, 2024)7 benchmarks | Coding 91 | Agents – | Math – | Science – | Reasoning 85 | 7 | – | |
| 195 | GPT 4.1 Mini (Apr 14, 2025)15 benchmarks | Coding 92 | Agents – | Math 95 | Science 97 | Reasoning 91 | 15 | – | |
| 196 | Gemini 2.0 Flash Thinking Exp (Jan 21)6 benchmarks | Coding – | Agents – | Math – | Science 89 | Reasoning – | 6 | – | |
| 197 | Mistral Medium 25086 benchmarks | Coding 92 | Agents – | Math – | Science 91 | Reasoning 92 | 6 | – | |
| 198 | Gemini 2.0 Flash 0016 benchmarks | Coding – | Agents – | Math – | Science – | Reasoning 87 | 6 | – | |
| 199 | O1 Preview (Sep 12, 2024)5 benchmarks | Coding – | Agents – | Math – | Science – | Reasoning 99 | 5 | – | |
| 200 | GPT 5.4 Mini 2026 03.176 benchmarks | Coding – | Agents – | Math 89 | Science – | Reasoning 96 | 6 | – | |
| 201 | Gemini 2.0 Pro Exp (Feb 05)3 benchmarks | Coding – | Agents – | Math – | Science – | Reasoning – | 3 | – | |
| 202 | Claude 3.5 Sonnet (Oct 22, 2024)10 benchmarks | Coding 99 | Agents 100 | Math – | Science 88 | Reasoning 97 | 10 | – | |
| 203 | Gemini 2.5 Flash Lite Preview Thinking (Jun 17)5 benchmarks | Coding 95 | Agents – | Math – | Science – | Reasoning 87 | 5 | – | |
| 204 | Mistral Medium 25054 benchmarks | Coding – | Agents – | Math – | Science 91 | Reasoning – | 4 | – | |
| 205 | DeepSeek v3open412 GB · 8 benchmarks | Coding 97 | Agents – | Math – | Science 90 | Reasoning 87 | 8 | 412 GB | |
| 206 | Magistral Small 2506open17.8 GB · 4 benchmarks | Coding – | Agents – | Math – | Science – | Reasoning 88 | 4 | 17.8 GB | |
| 207 | Qwen Max (Jan 25, 2025)4 benchmarks | Coding – | Agents – | Math – | Science – | Reasoning – | 4 | – | |
| 208 | Mistral Large 3 675B Instruct 2512open454 GB · 6 benchmarks | Coding 93 | Agents – | Math – | Science 97 | Reasoning 86 | 6 | 454 GB | |
| 209 | Llama 4 Maverick 17B 128E Instructopen273 GB · 15 benchmarks | Coding 81 | Agents – | Math – | Science 96 | Reasoning 86 | 15 | 273 GB | |
| 210 | Mistral Small 3.2 24B Instruct 2506open18.1 GB · 5 benchmarks | Coding – | Agents – | Math – | Science 82 | Reasoning – | 5 | 18.1 GB | |
| 211 | Magistral Small 2509open18.1 GB · 5 benchmarks | Coding – | Agents – | Math – | Science 83 | Reasoning – | 5 | 18.1 GB | |
| 212 | Gemini 1.5 Pro 0028 benchmarks | Coding – | Agents – | Math – | Science 89 | Reasoning 83 | 8 | – | |
| 213 | Claude 3.5 Sonnet (Jun 20, 2024)6 benchmarks | Coding – | Agents – | Math – | Science – | Reasoning 93 | 6 | – | |
| 214 | Phi 4open12.5 GB · 5 benchmarks | Coding – | Agents – | Math – | Science 89 | Reasoning – | 5 | 12.5 GB | |
| 215 | Grok 2 (Dec 12)5 benchmarks | Coding – | Agents – | Math – | Science – | Reasoning 87 | 5 | – | |
| 216 | Llama 3.1 405B Instructopen276 GB · 8 benchmarks | Coding – | Agents – | Math – | Science 85 | Reasoning 86 | 8 | 276 GB | |
| 217 | GPT 4o (May 13, 2024)6 benchmarks | Coding – | Agents – | Math – | Science – | Reasoning 90 | 6 | – | |
| 218 | Mistral Large Instruct 2411open79.8 GB · 5 benchmarks | Coding – | Agents – | Math – | Science – | Reasoning 87 | 5 | 79.8 GB | |
| 219 | Qwen2.5 72B Instructopen49.3 GB · 8 benchmarks | Coding – | Agents – | Math – | Science – | Reasoning 88 | 8 | 49.3 GB | |
| 220 | Llama 4 Scout 17B 16E Instructopen77.0 GB · 11 benchmarks | Coding – | Agents – | Math – | Science 84 | Reasoning 81 | 11 | 77.0 GB | |
| 221 | Qwen2.5 Coder 32B Instructopen24.3 GB · 3 benchmarks | Coding – | Agents 84 | Math – | Science – | Reasoning – | 3 | 24.3 GB | |
| 222 | Mistral Large Instruct 2407open86.4 GB · 6 benchmarks | Coding – | Agents – | Math – | Science – | Reasoning 86 | 6 | 86.4 GB | |
| 223 | GPT 4o (Aug 06, 2024)7 benchmarks | Coding – | Agents – | Math 75 | Science – | Reasoning 77 | 7 | – | |
| 224 | Claude 3 Opus (Feb 29, 2024)9 benchmarks | Coding – | Agents – | Math – | Science – | Reasoning 86 | 9 | – | |
| 225 | Qwen2.5 32B Instructopen24.3 GB · 3 benchmarks | Coding – | Agents – | Math – | Science – | Reasoning – | 3 | 24.3 GB | |
| 226 | GPT 4o (Nov 20, 2024)10 benchmarks | Coding 82 | Agents – | Math – | Science 82 | Reasoning 90 | 10 | – | |
| 227 | Llama 3.3 70B Instructopen51.3 GB · 12 benchmarks | Coding 76 | Agents – | Math – | Science 81 | Reasoning 83 | 12 | 51.3 GB | |
| 228 | C4ai Command A 03 2025open78.7 GB · 4 benchmarks | Coding – | Agents – | Math – | Science – | Reasoning 84 | 4 | 78.7 GB | |
| 229 | Gemini 1.5 Flash 0025 benchmarks | Coding – | Agents – | Math – | Science – | Reasoning – | 5 | – | |
| 230 | GPT 4 Turbo (Apr 09, 2024)6 benchmarks | Coding – | Agents – | Math 75 | Science – | Reasoning 93 | 6 | – | |
| 231 | Gemma 3 27B ITopen21.7 GB · 9 benchmarks | Coding 70 | Agents – | Math – | Science 81 | Reasoning 74 | 9 | 21.7 GB | |
| 232 | Mistral Small 3.1 24B Instruct 2503open18.1 GB · 5 benchmarks | Coding – | Agents – | Math – | Science 81 | Reasoning – | 5 | 18.1 GB | |
| 233 | Claude 3.5 Haiku (Oct 22, 2024)8 benchmarks | Coding 88 | Agents – | Math – | Science 73 | Reasoning – | 8 | – | |
| 234 | Gemini 1.5 Pro 0014 benchmarks | Coding – | Agents – | Math – | Science – | Reasoning 80 | 4 | – | |
| 235 | GPT 4.1 Nano (Apr 14, 2025)13 benchmarks | Coding 75 | Agents – | Math – | Science 82 | Reasoning 72 | 13 | – | |
| 236 | Llama 3.1 70B Instructopen51.3 GB · 7 benchmarks | Coding – | Agents – | Math – | Science – | Reasoning 83 | 7 | 51.3 GB | |
| 237 | Qwen2 72B Instructopen49.3 GB · 3 benchmarks | Coding – | Agents – | Math – | Science – | Reasoning – | 3 | 49.3 GB | |
| 238 | GPT 4 (Jun 13)7 benchmarks | Coding – | Agents – | Math – | Science – | Reasoning 89 | 7 | – | |
| 239 | Meta Llama 3 70B Instructopen51.3 GB · 4 benchmarks | Coding – | Agents – | Math – | Science – | Reasoning – | 4 | 51.3 GB | |
| 240 | Gemma 3 12B ITopen10.9 GB · 7 benchmarks | Coding – | Agents – | Math – | Science 72 | Reasoning 66 | 7 | 10.9 GB |
The range after each score is a 90% interval: given the boards a model has results on, its true score is very likely inside it. Short ranges mean many agreeing results; long ranges mean few or conflicting ones.
Why some models are missing. A model receives a score only if it has results on at least 4 benchmarks across at least 2 categories, with one being reasoning or coding, or on 3 benchmarks that narrow its 90% range to at most 15.6 points. The results must come from at least two different benchmarks: categories of one benchmark, such as LiveBench, count once. Skill scores require at least 2 benchmarks for that skill; otherwise they display as –.
VRAM is llmrun's estimate at Q4_K_M (or the smallest quantization we track) for the weights plus room for a 16K-token context. Longer contexts need more memory. Proprietary models can't run locally, so the VRAM filter hides them.
How the llmrun Composite Score is built · llmrun doesn't run these benchmarks; scores come from public sources.
Dataset. Grab the scores of every open model as a dataset on Hugging Face, including a timestamped snapshot for each refresh.