llmrun Composite Score · Reasoning
The best open LLMs for reasoning, ranked on hard multi-step reasoning boards such as ARC-AGI and HLE. The score shown is the overall llmrun Composite Score; the highlighted column is the reasoning skill score used for the order.
40 benchmarks4 sourcesUpdated 10 Oct 2026Reference scale 2026-Q4How the Composite Score is built
Reasoning score vs VRAM needed
This chart doesn't show proprietary models.
| # (open / overall) | Model | llmrun Composite Score | Coding | Agents | Math | Science | Reasoning | Benchmarks | VRAM |
|---|---|---|---|---|---|---|---|---|---|
| 1 / 53 | Qwen3.8 27B17.9 GB · 12 benchmarks | 112 | – | 118 | 112 | 124 | 12 | 17.9 GB | |
| 2 / 88 | Qwen3.5 122B A10B75.5 GB · 6 benchmarks | – | – | – | 96 | 112 | 6 | 75.5 GB | |
| 3 / 99 | Qwen3.5 27B17.9 GB · 6 benchmarks | 98 | – | – | – | 111 | 6 | 17.9 GB | |
| 4 / 103 | Gemma 4 31B IT21.7 GB · 11 benchmarks | 108 | – | – | 105 | 109 | 11 | 21.7 GB | |
| 5 / 110 | Qwen3.6 35B A3B22.0 GB · 12 benchmarks | 105 | – | 109 | 110 | 107 | 12 | 22.0 GB | |
| 6 / 111 | Qwen3.6 27B17.9 GB · 12 benchmarks | 102 | – | 114 | 111 | 106 | 12 | 17.9 GB | |
| 7 / 115 | Qwen3.5 35B A3B22.0 GB · 8 benchmarks | – | – | – | 108 | 106 | 8 | 22.0 GB | |
| 8 / 125 | Gemma 4 26B A4B IT16.5 GB · 9 benchmarks | 104 | – | – | 102 | 101 | 9 | 16.5 GB | |
| 9 / 132 | Qwen3.5 9B6.6 GB · 9 benchmarks | – | – | – | 104 | 97 | 9 | 6.6 GB | |
| 10 / 134 | GPT OSS 120B70.8 GB · 20 benchmarks | 98 | 82 | – | 103 | 97 | 20 | 70.8 GB | |
| 11 / 138 | Mistral Small 4 119B 260381.6 GB · 3 benchmarks | — | – | – | – | – | 96 | 3 | 81.6 GB |
| 12 / 142 | Qwen3 30B A3B Thinking 250719.4 GB · 8 benchmarks | – | – | – | 99 | 94 | 8 | 19.4 GB | |
| 13 / 144 | Qwen3 30B A3B Instruct 250719.4 GB · 5 benchmarks | – | – | – | – | 92 | 5 | 19.4 GB | |
| 14 / 150 | Qwen3 32B22.6 GB · 9 benchmarks | 93 | – | – | 96 | 91 | 9 | 22.6 GB | |
| 15 / 151 | GPT OSS 20B13.1 GB · 11 benchmarks | 101 | – | – | 92 | 91 | 11 | 13.1 GB | |
| 16 / 156 | Magistral Small 250617.8 GB · 4 benchmarks | – | – | – | – | 88 | 4 | 17.8 GB | |
| 17 / 158 | Qwen3 14B11.9 GB · 8 benchmarks | – | – | – | 94 | 88 | 8 | 11.9 GB | |
| 18 / 167 | Qwen2.5 72B Instruct49.3 GB · 8 benchmarks | – | – | – | – | 86 | 8 | 49.3 GB | |
| 19 / 171 | Magistral Small 250918.1 GB · 6 benchmarks | – | – | – | 83 | 85 | 6 | 18.1 GB | |
| 20 / 173 | Mistral Large Instruct 241179.8 GB · 5 benchmarks | – | – | – | – | 84 | 5 | 79.8 GB | |
| 21 / 175 | C4ai Command A 03 202578.7 GB · 3 benchmarks | — | – | – | – | – | 84 | 3 | 78.7 GB |
| 22 / 176 | Qwen3 30B A3B19.4 GB · 7 benchmarks | – | – | – | – | 83 | 7 | 19.4 GB | |
| 23 / 177 | Llama 3.1 70B Instruct51.3 GB · 7 benchmarks | – | – | – | – | 83 | 7 | 51.3 GB | |
| 24 / 178 | Mistral Large Instruct 240786.4 GB · 6 benchmarks | – | – | – | – | 83 | 6 | 86.4 GB | |
| 25 / 179 | Mistral Small 3.2 24B Instruct 250618.1 GB · 6 benchmarks | – | – | – | 82 | 83 | 6 | 18.1 GB | |
| 26 / 181 | Llama 3.3 70B Instruct51.3 GB · 12 benchmarks | 76 | – | – | 81 | 82 | 12 | 51.3 GB | |
| 27 / 182 | Mistral Small 3.1 24B Instruct 250318.1 GB · 6 benchmarks | – | – | – | 81 | 82 | 6 | 18.1 GB | |
| 28 / 184 | Qwen3 8B7.6 GB · 8 benchmarks | – | – | – | 88 | 81 | 8 | 7.6 GB | |
| 29 / 186 | Llama 4 Scout 17B 16E Instruct77.0 GB · 11 benchmarks | – | – | – | 83 | 80 | 11 | 77.0 GB | |
| 30 / 188 | Mixtral 8x22B Instruct v0.188.4 GB · 5 benchmarks | – | – | – | – | 76 | 5 | 88.4 GB | |
| 31 / 189 | C4ai Command R Plus 08 202473.8 GB · 3 benchmarks | — | – | – | – | – | 74 | 3 | 73.8 GB |
| 32 / 190 | Gemma 3 27B IT21.7 GB · 10 benchmarks | 69 | – | – | 80 | 74 | 10 | 21.7 GB | |
| 33 / 194 | Llama 3.1 8B Instruct7.9 GB · 10 benchmarks | 56 | – | – | 56 | 69 | 10 | 7.9 GB | |
| 34 / 195 | Mixtral 8x7B Instruct v0.130.5 GB · 4 benchmarks | – | – | – | – | 69 | 4 | 30.5 GB | |
| 35 / 196 | Gemma 3 4B IT5.0 GB · 6 benchmarks | – | – | – | – | 69 | 6 | 5.0 GB | |
| 36 / 199 | Gemma 3 12B IT10.9 GB · 8 benchmarks | – | – | – | 72 | 66 | 8 | 10.9 GB | |
| 37 / 201 | Qwen2.5 7B Instruct5.8 GB · 6 benchmarks | – | – | – | – | 65 | 6 | 5.8 GB | |
| 38 / 203 | C4ai Command R 08 202425.1 GB · 2 benchmarks | — | – | – | – | – | 64 | 2 | 25.1 GB |
| 39 / 204 | Meta Llama 3 8B Instruct7.9 GB · 6 benchmarks | – | – | – | – | 64 | 6 | 7.9 GB | |
| 40 / 205 | Llama 2 13B Chat HF11.5 GB · 2 benchmarks | — | – | – | – | – | 57 | 2 | 11.5 GB |
| 41 / 207 | Llama 2 70B Chat HF50.2 GB · 4 benchmarks | – | – | – | – | 45 | 4 | 50.2 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. 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.