410 models · Rank position per sub-category (lower is better) · Click headers to sort
| Model | Overall | Expert | Hard | Code | Math | Creative | Instruct | Long |
|---|---|---|---|---|---|---|---|---|
| gemini-4-argon-high Google | 1 | 5 | 1 | 1 | 1 | 1 | 1 | 1 |
| claude-opus-4-6-high Anthropic | 2 | 2 | 2 | 3 | 5 | 4 | 3 | 3 |
| claude-fable-5-high Anthropic | 3 | 1 | 4 | 2 | 3 | 3 | 4 | 4 |
| claude-opus-5.5-high Anthropic | 4 | 4 | 3 | 11 | 9 | 2 | 2 | 2 |
| claude-opus-4-7-high Anthropic | 5 | 8 | 6 | 4 | 12 | 6 | 5 | 6 |
| claude-fable-5.1-max Anthropic | 6 | 16 | 7 | 17 | 4 | 10 | 7 | 7 |
| claude-opus-4-6 Anthropic | 7 | 9 | 5 | 5 | 11 | 12 | 6 | 5 |
| muse-spark-1.3-max Meta | 8 | 13 | 10 | 10 | 8 | 27 | 15 | 14 |
| claude-opus-4-7 Anthropic | 9 | 7 | 8 | 6 | 23 | 9 | 9 | 8 |
| muse-spark-1.2 (xHigh) Meta | 10 | 39 | 18 | 12 | — | 33 | 25 | 21 |
| gemini-3.8-flash-high Google | 11 | 15 | 12 | 18 | 6 | 8 | 14 | 9 |
| muse-spark-1.1 Meta | 12 | 34 | 15 | 13 | 24 | 41 | 27 | 36 |
| claude-opus-5-high Anthropic | 13 | 3 | 11 | 15 | 2 | 13 | 8 | 10 |
| claude-opus-5-max Anthropic | 14 | 12 | 13 | 21 | 7 | 15 | 10 | 16 |
| muse-spark Meta | 15 | 55 | 20 | 22 | 54 | 21 | 42 | 49 |
| gemini-3.7-flash-high Google | 16 | 27 | 17 | 39 | 10 | 5 | 16 | 13 |
| kimi-k3-max Moonshot | 17 | 10 | 9 | 7 | 16 | 26 | 13 | 11 |
| gemini-3.1-pro-preview Google | 18 | 28 | 19 | 33 | 28 | 11 | 18 | 17 |
| gemini-3-pro Google | 19 | 45 | 25 | 40 | 39 | 7 | 33 | 25 |
| gpt-5.6-sol-xhigh OpenAI | 20 | 6 | 16 | 14 | 22 | 19 | 11 | 18 |
| gemini-3.6-flash-high Google | 21 | 42 | 26 | 38 | 14 | 14 | 28 | 32 |
| gpt-5.5-high OpenAI | 22 | 22 | 28 | 37 | 21 | 34 | 22 | 28 |
| claude-opus-4-8-high Anthropic | 23 | 14 | 14 | 16 | 20 | 16 | 12 | 12 |
| qwen3.8-max Alibaba | 24 | 24 | 27 | 29 | 18 | 20 | 32 | 26 |
| mimo-v2.6-pro Xiaomi | 25 | 11 | 23 | 8 | 30 | 50 | 29 | 20 |
| glm-5.3-max Z.ai | 26 | 17 | 21 | 32 | 26 | 31 | 21 | 27 |
| gemini-3.5-flash-high Google | 27 | 53 | 40 | 60 | 19 | 22 | 41 | 39 |
| gpt-5.5 OpenAI | 28 | 25 | 32 | 57 | 17 | 40 | 23 | 31 |
| gemini-3.5-flash-medium Google | 29 | 61 | 41 | 62 | 32 | 17 | 39 | 43 |
| gpt-6-astra-max OpenAI | 30 | 21 | 29 | 9 | 27 | 39 | 30 | 34 |
| gpt-5.2-chat-latest-20260210 OpenAI | 31 | 56 | 35 | 43 | 67 | 67 | 52 | 54 |
| glm-5.2-max Z.ai | 32 | 38 | 37 | 51 | 29 | 30 | 35 | 30 |
| gpt-5.4-high OpenAI | 33 | 19 | 36 | 34 | 25 | 53 | 34 | 41 |
| grok-4.20-beta1 SpaceXAI | 34 | 75 | 51 | 59 | 74 | 24 | 63 | 66 |
| qwen3.7-max-preview Alibaba | 35 | 31 | 39 | 25 | 31 | 56 | 40 | 24 |
| claude-opus-4-8 Anthropic | 36 | 18 | 22 | 20 | 40 | 23 | 19 | 15 |
| claude-opus-4-5-20251101-high-32k Anthropic | 37 | 35 | 30 | 19 | 47 | 18 | 17 | 19 |
| glm-5.3-flash Z.ai | 38 | 29 | 31 | 26 | 15 | 65 | 31 | 44 |
| gpt-5.5-instant OpenAI | 39 | 81 | 44 | 47 | 59 | 29 | 53 | 51 |
| deepseek-v4.1-flash-max DeepSeek | 40 | 26 | 33 | 23 | 13 | 58 | 20 | 46 |
| gemini-3-flash Google | 41 | 48 | 42 | 64 | 44 | 28 | 51 | 50 |
| claude-sonnet-4-6 Anthropic | 42 | 30 | 24 | 24 | 57 | 37 | 26 | 23 |
| grok-4.20-beta-0309-reasoning SpaceXAI | 43 | 72 | 47 | 56 | 56 | 46 | 68 | 64 |
| grok-4.20-multi-agent-beta-0309 SpaceXAI | 44 | 69 | 57 | 58 | 65 | 42 | 74 | 76 |
| claude-opus-4-5-20251101 Anthropic | 45 | 37 | 34 | 27 | 58 | 25 | 24 | 22 |
| ernie-5.1 Baidu | 46 | 50 | 50 | 49 | 38 | 73 | 59 | 68 |
| mimo-v2.5-pro Xiaomi | 47 | 32 | 38 | 31 | 33 | 64 | 36 | 29 |
| grok-4.5 SpaceXAI | 48 | 59 | 46 | 46 | 46 | 35 | 45 | 42 |
| grok-4.1-thinking SpaceXAI | 49 | 93 | 68 | 77 | 85 | 74 | 92 | 94 |
| gpt-5.6-terra-xhigh OpenAI | 50 | 33 | 48 | 42 | 36 | 75 | 47 | 60 |
| gpt-5.4 OpenAI | 51 | 54 | 53 | 55 | 60 | 63 | 48 | 48 |
| qwen3.5-max-preview Alibaba | 52 | 40 | 43 | 45 | 51 | 47 | 38 | 40 |
| glm-5.1 Z.ai | 53 | 51 | 49 | 48 | 42 | 43 | 49 | 45 |
| deepseek-v4-pro-high-20260813 DeepSeek | 54 | 63 | 58 | 63 | 63 | 51 | 46 | 52 |
| claude-sonnet-5-high Anthropic | 55 | 23 | 45 | 36 | 45 | 61 | 37 | 38 |
| kimi-k2.6 Moonshot | 56 | 36 | 54 | 41 | 35 | 66 | 54 | 47 |
| qwen3.6-max-preview Alibaba | 57 | 41 | 60 | 52 | 41 | 59 | 64 | 53 |
| grok-4.1 SpaceXAI | 58 | 105 | 73 | 84 | 111 | 71 | 90 | 86 |
| gemini-3-flash (thinking-minimal) Google | 59 | 95 | 74 | 91 | 70 | 44 | 75 | 72 |
| deepseek-v4-pro DeepSeek | 60 | 71 | 62 | 76 | 81 | 45 | 60 | 56 |
| glm-5 Z.ai | 61 | 67 | 65 | 78 | 83 | 38 | 70 | 59 |
| hy3 Tencent | 62 | 60 | 67 | 73 | 34 | 78 | 69 | 65 |
| claude-sonnet-4-5-20250929-high-32k Anthropic | 63 | 47 | 52 | 35 | 66 | 36 | 43 | 33 |
| dola-seed-2.0-pro Bytedance | 64 | 73 | 61 | 44 | 73 | 101 | 84 | 82 |
| qwen3.7-plus Alibaba | 65 | 62 | 75 | 75 | 55 | 70 | 67 | 67 |
| gpt-6-sol-max OpenAI | 66 | 43 | 55 | 28 | 68 | 57 | 57 | 61 |
| gpt-5.1-high OpenAI | 67 | 68 | 69 | 86 | 61 | 72 | 61 | 74 |
| claude-sonnet-4-5-20250929 Anthropic | 68 | 64 | 59 | 50 | 108 | 32 | 44 | 37 |
| deepseek-v4-pro-high-preview DeepSeek | 69 | 76 | 76 | 95 | 53 | 55 | 66 | 69 |
| gemini-3.5-flash-lite Google | 70 | 87 | 77 | 74 | 87 | 62 | 76 | 71 |
| mimo-v2.6-flash Xiaomi | 71 | 20 | 56 | 30 | 50 | 128 | 58 | 70 |
| gpt-5.6-luna-xhigh OpenAI | 72 | 57 | 71 | 71 | 43 | 90 | 71 | 81 |
| grok-4.6-high SpaceXAI | 73 | 58 | 64 | 61 | 79 | 49 | 62 | 57 |
| gemma-4-31b Google | 74 | 46 | 70 | 70 | 49 | 83 | 56 | 58 |
| kimi-k2.5-thinking Moonshot | 75 | 65 | 79 | 69 | 48 | 76 | 78 | 75 |
| gpt-5.3-chat-latest OpenAI | 76 | 85 | 78 | 80 | 104 | 94 | 82 | 77 |
| claude-opus-4-1-20250805-thinking-16k Anthropic | 77 | 66 | 63 | 54 | 82 | 48 | 50 | 35 |
| ernie-5.0-preview-1203 Baidu | 78 | 111 | 84 | 119 | 139 | 82 | 108 | 113 |
| claude-opus-4-1-20250805 Anthropic | 79 | 90 | 66 | 66 | 101 | 54 | 55 | 55 |
| mimo-v2-pro Xiaomi | 80 | 52 | 72 | 67 | 72 | 77 | 72 | 63 |
| gpt-5.4-mini-high OpenAI | 81 | 70 | 81 | 83 | 90 | 104 | 86 | 93 |
| ernie-5.0-0110 Baidu | 82 | 119 | 83 | 90 | 96 | 81 | 101 | 109 |
| gemini-2.5-pro Google | 83 | 102 | 100 | 127 | 89 | 52 | 79 | 78 |
| gpt-4.5-preview-2025-02-27 OpenAI | 84 | 142 | 128 | 138 | 144 | 60 | 81 | 98 |
| gpt-6-luna-max OpenAI | 85 | 44 | 80 | 53 | 77 | 89 | 65 | 73 |
| qwen3.6-plus Alibaba | 86 | 77 | 82 | 81 | 69 | 93 | 83 | 79 |
| chatgpt-4o-latest-20250326 OpenAI | 87 | 140 | 105 | 124 | 150 | 80 | 96 | 111 |
| grok-4.7-xhigh SpaceXAI | 88 | 101 | 88 | 85 | 80 | 68 | 77 | 87 |
| inkling Thinking Machines | 89 | 82 | 90 | 87 | 37 | 140 | 99 | 110 |
| qwen3.5-397b-a17b Alibaba | 90 | 74 | 86 | 88 | 71 | 99 | 87 | 80 |
| glm-4.7 Z.ai | 91 | 112 | 91 | 99 | 107 | 98 | 100 | 85 |
| grok-4.3 SpaceXAI | 92 | 108 | 103 | 96 | 124 | 79 | 118 | 100 |
| minimax-m3 MiniMax | 93 | 84 | 87 | 82 | 100 | 97 | 85 | 84 |
| qwen3.8-27b Alibaba | 94 | 78 | 85 | 65 | 62 | 160 | 98 | 97 |
| gpt-5.1 OpenAI | 95 | 104 | 104 | 110 | 118 | 91 | 97 | 102 |
| deepseek-v4-flash-high-preview DeepSeek | 96 | 91 | 101 | 108 | 88 | 87 | 88 | 89 |
| gemma-4-26b-a4b Google | 97 | 79 | 93 | 101 | 52 | 108 | 80 | 96 |
| gpt-5.2-high OpenAI | 98 | 80 | 96 | 92 | 64 | 132 | 95 | 117 |
| longcat-flash-chat-2602-exp Meituan | 99 | 88 | 92 | 72 | 95 | 126 | 112 | 112 |
| deepseek-v4-flash DeepSeek | 100 | 103 | 97 | 100 | 115 | 92 | 93 | 91 |
| gpt-5.2 OpenAI | 101 | 100 | 94 | 102 | 102 | 118 | 103 | 107 |
| gpt-5-high OpenAI | 102 | 99 | 110 | 120 | 99 | 148 | 126 | 149 |
| qwen3-max-preview Alibaba | 103 | 94 | 99 | 105 | 98 | 115 | 102 | 99 |
| glm-5v-turbo Z.ai | 104 | 96 | 107 | 94 | 93 | 96 | 104 | 105 |
| mimo-v2.5 Xiaomi | 105 | 86 | 89 | 89 | 91 | 113 | 91 | 83 |
| gemini-3.1-flash-lite-preview Google | 106 | 122 | 120 | 141 | 94 | 86 | 128 | 127 |
| o3-2025-04-16 OpenAI | 107 | 113 | 125 | 134 | 76 | 135 | 136 | 151 |
| mimo-v2-omni Xiaomi | 108 | 97 | 98 | 93 | 97 | 112 | 94 | 88 |
| kimi-k2.5-instant Moonshot | 109 | 110 | 95 | 68 | 84 | 122 | 89 | 104 |
| grok-4-1-fast-reasoning SpaceXAI | 110 | 130 | 124 | 132 | 122 | 85 | 138 | 132 |
| kimi-k2-thinking-turbo Moonshot | 111 | 98 | 106 | 97 | 92 | 121 | 110 | 119 |
| mistral-medium-3.5 Mistral | 112 | 132 | 118 | 109 | 106 | 107 | 105 | 126 |
| gpt-5-chat OpenAI | 113 | 120 | 109 | 131 | 141 | 124 | 117 | 115 |
| amazon-nova-experimental-chat-26-02-10 Amazon | 114 | 49 | 108 | 98 | 110 | 177 | 119 | 121 |
| nvidia-nemotron-3-ultra-550b-a55b-nvfp4 Nvidia | 115 | 89 | 121 | 113 | 86 | 138 | 132 | 116 |
| claude-opus-4-20250514-thinking-16k Anthropic | 116 | 115 | 102 | 79 | 121 | 69 | 73 | 62 |
| muse-glimmer Meta | 117 | 124 | 114 | 107 | 75 | 154 | 123 | 134 |
| deepseek-v3.2-exp-thinking DeepSeek | 118 | 117 | 115 | 112 | 123 | 120 | 113 | 118 |
| deepseek-v3.2 DeepSeek | 119 | 114 | 112 | 121 | 109 | 105 | 107 | 108 |
| glm-4.6 Z.ai | 120 | 128 | 123 | 140 | 126 | 106 | 124 | 123 |
| qwen3-max-2025-09-23 Alibaba | 121 | 155 | 117 | 116 | 119 | 117 | 122 | 124 |
| deepseek-v3.2-thinking DeepSeek | 122 | 106 | 116 | 111 | 105 | 119 | 109 | 103 |
| qwen3-235b-a22b-instruct-2507 Alibaba | 123 | 116 | 111 | 117 | 127 | 142 | 121 | 120 |
| deepseek-v3.2-exp DeepSeek | 124 | 146 | 113 | 125 | 134 | 88 | 120 | 106 |
| deepseek-r1-0528 DeepSeek | 125 | 153 | 135 | 128 | 165 | 125 | 154 | 156 |
| grok-4-fast-chat SpaceXAI | 126 | 157 | 141 | 139 | 114 | 133 | 150 | 140 |
| ernie-5.0-preview-1022 Baidu | 127 | 136 | 145 | 179 | 164 | 95 | 144 | 138 |
| kimi-k2-0905-preview Moonshot | 128 | 154 | 129 | 123 | 129 | 136 | 155 | 157 |
| kimi-k2-0711-preview Moonshot | 129 | 158 | 136 | 136 | 174 | 152 | 171 | 171 |
| deepseek-v3.1 DeepSeek | 130 | 145 | 140 | 153 | 133 | 129 | 137 | 136 |
| deepseek-v3.1-terminus-thinking DeepSeek | 131 | — | 119 | 133 | — | 127 | 106 | 92 |
| qwen3.5-122b-a10b Alibaba | 132 | 125 | 138 | 137 | 112 | 156 | 131 | 141 |
| deepseek-v3.1-thinking DeepSeek | 133 | 137 | 131 | 144 | 132 | 103 | 111 | 95 |
| minimax-m2.7 MiniMax | 134 | 107 | 127 | 106 | 120 | 159 | 129 | 122 |
| gpt-4.1-2025-04-14 OpenAI | 135 | 165 | 139 | 143 | 185 | 102 | 134 | 130 |
| deepseek-v3.1-terminus DeepSeek | 136 | — | 149 | 162 | 160 | 100 | 152 | 139 |
| claude-opus-4-20250514 Anthropic | 137 | 133 | 132 | 126 | 149 | 84 | 115 | 90 |
| mistral-large-3 Mistral | 138 | 144 | 142 | 122 | 153 | 147 | 140 | 145 |
| claude-haiku-4-5-20251001 Anthropic | 139 | 109 | 126 | 103 | 155 | 131 | 116 | 114 |
| qwen3-vl-235b-a22b-instruct Alibaba | 140 | 127 | 130 | 130 | 140 | 166 | 127 | 137 |
| amazon-nova-experimental-chat-26-01-10 Amazon | 141 | 83 | 122 | 104 | 137 | 172 | 143 | 133 |
| grok-3-preview-02-24 SpaceXAI | 142 | 167 | 148 | 160 | 190 | 109 | 135 | 128 |
| glm-4.5 Z.ai | 143 | 121 | 134 | 145 | 136 | 149 | 133 | 142 |
| grok-4-0709 SpaceXAI | 144 | 139 | 151 | 170 | 113 | 111 | 147 | 146 |
| gemini-2.5-flash Google | 145 | 148 | 156 | 185 | 147 | 114 | 142 | 143 |
| hunyuan-hy3-preview Tencent | 146 | 118 | 133 | 147 | 103 | 169 | 148 | 135 |
| qwen3.5-27b Alibaba | 147 | 126 | 143 | 149 | 117 | 165 | 139 | 131 |
| mistral-medium-2508 Mistral | 148 | 161 | 146 | 146 | 162 | 141 | 151 | 154 |
| Inkling Small Thinking Machines | 149 | 123 | 144 | 115 | 78 | 215 | 153 | 169 |
| grok-4-fast-reasoning SpaceXAI | 150 | 149 | 167 | 164 | 138 | 134 | 156 | 148 |
| gemini-2.5-flash-preview-09-2025 Google | 151 | 138 | 153 | 183 | 142 | 139 | 141 | 144 |
| qwen3-235b-a22b-no-thinking Alibaba | 152 | 181 | 152 | 156 | 167 | 155 | 170 | 152 |
| o1-2024-12-17 OpenAI | 153 | 171 | 160 | 176 | 143 | 137 | 130 | 147 |
| claude-sonnet-4-20250514-thinking-32k Anthropic | 154 | 135 | 137 | 114 | 152 | 110 | 114 | 101 |
| longcat-flash-chat Meituan | 155 | 143 | 147 | 118 | 130 | 198 | 157 | 180 |
| gpt-5.4-nano-high OpenAI | 156 | 131 | 150 | 135 | 116 | 191 | 158 | 163 |
| qwen3-235b-a22b-thinking-2507 Alibaba | 157 | 92 | 161 | 161 | 161 | 153 | 162 | 164 |
| qwen3-next-80b-a3b-instruct Alibaba | 158 | 174 | 155 | 158 | 131 | 212 | 175 | 177 |
| deepseek-r1 DeepSeek | 159 | 170 | 158 | 157 | 135 | 145 | 145 | 167 |
| qwen3.5-flash Alibaba | 160 | 152 | 165 | 168 | 154 | 187 | 169 | 166 |
| deepseek-v3-0324 DeepSeek | 161 | 177 | 173 | 182 | 193 | 123 | 173 | 172 |
| hunyuan-vision-1.5-thinking Tencent | 162 | — | 154 | 166 | — | 143 | 146 | 159 |
| qwen3-vl-235b-a22b-thinking Alibaba | 163 | 129 | 163 | 150 | 156 | 185 | 166 | 162 |
| amazon-nova-experimental-chat-12-10 Amazon | 164 | 179 | 164 | 172 | 159 | 184 | 174 | 179 |
| qwen3.5-35b-a3b Alibaba | 165 | 151 | 171 | 169 | 158 | 183 | 159 | 168 |
| step-3.5-flash Stepfun | 166 | 141 | 169 | 151 | 145 | 178 | 163 | 160 |
| mimo-v2-flash (non-thinking) Xiaomi | 167 | 156 | 168 | 154 | 184 | 170 | 165 | 161 |
| minimax-m2.5 MiniMax | 168 | 147 | 162 | 155 | 166 | 167 | 167 | 158 |
| o4-mini-2025-04-16 OpenAI | 169 | 162 | 176 | 173 | 125 | 188 | 182 | 199 |
| claude-sonnet-4-20250514 Anthropic | 170 | 169 | 157 | 152 | 172 | 130 | 149 | 129 |
| gpt-5-mini-high OpenAI | 171 | 172 | 177 | 181 | 148 | 202 | 179 | 195 |
| o1-preview OpenAI | 172 | 193 | 185 | 194 | 177 | 157 | 168 | 183 |
| claude-3-7-sonnet-20250219-thinking-32k Anthropic | 173 | 160 | 159 | 148 | 178 | 116 | 125 | 125 |
| mistral-medium-2505 Mistral | 174 | 196 | 181 | 177 | 210 | 158 | 187 | 173 |
| qwen3-coder-480b-a35b-instruct Alibaba | 175 | 195 | 166 | 142 | 186 | 161 | 164 | 153 |
| hunyuan-t1-20250711 Tencent | 176 | 164 | 183 | 205 | 151 | 146 | 178 | 176 |
| mimo-v2-flash (thinking) Xiaomi | 177 | 159 | 170 | 175 | 188 | 189 | 176 | 165 |
| solar-pro4 Upstage | 178 | 134 | 172 | 129 | 128 | 219 | 172 | 181 |
| minimax-m2.1-preview MiniMax | 179 | 150 | 174 | 163 | 168 | 179 | 161 | 155 |
| qwen3-30b-a3b-instruct-2507 Alibaba | 180 | 182 | 175 | 165 | 183 | 208 | 185 | 184 |
| gpt-4.1-mini-2025-04-14 OpenAI | 181 | 192 | 179 | 174 | 206 | 174 | 180 | 175 |
| hunyuan-turbos-20250416 Tencent | 182 | 216 | 186 | 210 | 214 | 162 | 196 | 189 |
| gemini-2.5-flash-lite-preview-09-2025-no-thinking Google | 183 | 189 | 190 | 209 | 202 | 163 | 188 | 178 |
| glm-4.6v Z.ai | 184 | 183 | 194 | 192 | — | 173 | 184 | 185 |
| trinity-large-preview | 185 | 168 | 178 | 159 | 203 | 171 | 181 | 174 |
| qwen3-235b-a22b Alibaba | 186 | 191 | 188 | 178 | 170 | 204 | 195 | 187 |
| gemini-2.5-flash-lite-preview-06-17-thinking Google | 187 | 198 | 196 | 227 | 195 | 150 | 183 | 188 |
| claude-3-5-sonnet-20241022 Anthropic | 188 | 197 | 184 | 167 | 207 | 151 | 177 | 170 |
| qwen2.5-max Alibaba | 189 | 202 | 192 | 204 | 198 | 168 | 194 | 182 |
| glm-4.5-air Z.ai | 190 | 187 | 189 | 184 | 176 | 199 | 189 | 186 |
| claude-3-7-sonnet-20250219 Anthropic | 191 | 186 | 182 | 180 | 197 | 144 | 160 | 150 |
| qwen3-next-80b-a3b-thinking Alibaba | 192 | 184 | 191 | 187 | 169 | 201 | 192 | 194 |
| trinity-large-thinking | 193 | 173 | 193 | 195 | 179 | 195 | 193 | 202 |
| gemma-3-27b-it Google | 194 | 225 | 213 | 255 | 223 | 176 | 208 | 201 |
| glm-4.7-flash Z.ai | 195 | 190 | 195 | 186 | 201 | 222 | 200 | 197 |
| amazon-nova-experimental-chat-11-10 Amazon | 196 | 166 | 187 | 189 | 163 | 234 | 190 | 198 |
| minimax-m1 MiniMax | 197 | 204 | 197 | 191 | 192 | 207 | 202 | 204 |
| o3-mini-high OpenAI | 198 | 176 | 180 | 171 | 146 | 213 | 186 | 193 |
| grok-3-mini-high SpaceXAI | 199 | 163 | 200 | 212 | 173 | 197 | 191 | 190 |
| nvidia-nemotron-3-super-120b-a12b Nvidia | 200 | 185 | 199 | 200 | 189 | 228 | 209 | 209 |
| gemini-2.0-flash-001 Google | 201 | 211 | 220 | 247 | 205 | 182 | 201 | 203 |
| deepseek-v3 DeepSeek | 202 | 219 | 230 | 220 | 233 | 175 | 207 | 192 |
| grok-3-mini-beta SpaceXAI | 203 | 194 | 207 | 222 | 191 | 190 | 197 | 200 |
| mistral-small-2506 Mistral | 204 | 227 | 203 | 196 | 217 | 205 | 214 | 207 |
| intellect-3 | 205 | 212 | 201 | 193 | 187 | 217 | 217 | 213 |
| command-a-03-2025 Cohere | 206 | 221 | 209 | 218 | 234 | 192 | 210 | 196 |
| gemini-2.0-flash-lite-preview-02-05 Google | 207 | 228 | 232 | 274 | 221 | 181 | 220 | 216 |
| glm-4.5v Z.ai | 208 | 175 | 204 | 202 | 204 | 218 | 212 | 227 |
| gpt-oss-120b OpenAI | 209 | 210 | 217 | 217 | 181 | 261 | 227 | 256 |
| gemini-1.5-pro-002 Google | 210 | 223 | 229 | 258 | 216 | 164 | 211 | 208 |
| step-3 Stepfun | 211 | 207 | 198 | 199 | 199 | 214 | 204 | 219 |
| hunyuan-turbos-20250226 Tencent | 212 | — | 210 | 207 | 243 | 230 | 199 | 211 |
| nvidia-nemotron-3.5-lightning-30b-a3b-nvfp4 Nvidia | 213 | 188 | 208 | 188 | 194 | 266 | 205 | 228 |
| amazon-nova-experimental-chat-10-20 Amazon | 214 | 206 | 205 | 197 | 171 | 260 | 203 | 214 |
| o3-mini OpenAI | 215 | 205 | 206 | 190 | 180 | 233 | 206 | 206 |
| llama-3.1-nemotron-ultra-253b-v1 Nvidia | 216 | — | 202 | 215 | 182 | 196 | 198 | 224 |
| amazon-nova-experimental-chat-10-09 Amazon | 217 | — | 222 | 213 | — | 248 | 242 | 238 |
| qwen3-32b Alibaba | 218 | 178 | 211 | 201 | 157 | 227 | 221 | 210 |
| gpt-4o-2024-05-13 OpenAI | 219 | 248 | 240 | 239 | 238 | 186 | 225 | 244 |
| qwen-plus-0125 Alibaba | 220 | 200 | 227 | 231 | 222 | 210 | 218 | 205 |
| ling-flash-2.0 Ant Group | 221 | 208 | 214 | 198 | 211 | 273 | 238 | 248 |
| minimax-m2 MiniMax | 222 | 218 | 212 | 228 | 209 | 252 | 216 | 231 |
| mercury-2 Inception AI | 223 | 217 | 223 | 214 | — | 244 | 224 | 257 |
| claude-3-5-sonnet-20240620 Anthropic | 224 | 220 | 218 | 206 | 215 | 225 | 213 | 212 |
| nvidia-llama-3.3-nemotron-super-49b-v1.5 Nvidia | 225 | 199 | 216 | 203 | 175 | 226 | 229 | 226 |
| glm-4-plus-0111 Z.ai | 226 | 247 | 258 | 283 | 246 | 211 | 241 | 229 |
| gemma-3-12b-it Google | 227 | 279 | 247 | 289 | 225 | 194 | 230 | 218 |
| hunyuan-turbo-0110 Tencent | 228 | — | 233 | 237 | 266 | 231 | 245 | 223 |
| granite-4.2-30b IBM | 229 | 180 | 215 | 208 | — | 275 | 215 | 217 |
| gpt-5-nano-high OpenAI | 230 | 213 | 226 | 225 | 213 | 292 | 223 | 245 |
| o1-mini OpenAI | 231 | 215 | 221 | 221 | 200 | 256 | 219 | 222 |
| gemini-advanced-0514 Google | 232 | 258 | 257 | 278 | 237 | 180 | 233 | 252 |
| qwq-32b Alibaba | 233 | 209 | 225 | 226 | 196 | 241 | 228 | 239 |
| grok-2-2024-08-13 SpaceXAI | 234 | 241 | 255 | 254 | 252 | 209 | 247 | 237 |
| gpt-4o-2024-08-06 OpenAI | 235 | 246 | 253 | 253 | 236 | 200 | 232 | 230 |
| llama-3.1-405b-instruct-bf16 Meta | 236 | 245 | 236 | 232 | 228 | 232 | 243 | 247 |
| nova-2-lite Amazon | 237 | 214 | 224 | 211 | 220 | 271 | 222 | 242 |
| step-2-16k-exp-202412 Stepfun | 238 | 233 | 239 | 236 | 229 | 193 | 237 | 225 |
| llama-3.1-405b-instruct-fp8 Meta | 239 | 235 | 241 | 240 | 224 | 224 | 239 | 261 |
| olmo-3.1-32b-instruct Ai2 | 240 | 234 | 231 | 229 | 247 | 242 | 231 | 236 |
| yi-lightning 01.AI | 241 | 230 | 237 | 243 | 239 | 238 | 250 | 255 |
| llama-3.3-nemotron-49b-super-v1 Nvidia | 242 | — | 219 | 249 | — | 237 | 226 | 233 |
| llama-4-maverick-17b-128e-instruct Meta | 243 | 232 | 238 | 235 | 227 | 220 | 246 | 240 |
| qwen3-30b-a3b Alibaba | 244 | 222 | 235 | 224 | 208 | 255 | 249 | 232 |
| hunyuan-large-2025-02-10 Tencent | 245 | 236 | 248 | 245 | 253 | 229 | 236 | 191 |
| claude-3-5-haiku-20241022 Anthropic | 246 | 240 | 234 | 223 | 261 | 223 | 235 | 220 |
| gpt-4-turbo-2024-04-09 OpenAI | 247 | 262 | 270 | 268 | 249 | 206 | 253 | 263 |
| gemini-1.5-pro-001 Google | 248 | 238 | 252 | 269 | 244 | 203 | 248 | 215 |
| deepseek-v2.5-1210 DeepSeek | 249 | 251 | 251 | 233 | 254 | 216 | 244 | 234 |
| ring-flash-2.0 Ant Group | 250 | 203 | 228 | 216 | 218 | 283 | 234 | 243 |
| gpt-4.1-nano-2025-04-14 OpenAI | 251 | 243 | 245 | 234 | 272 | 221 | 257 | 254 |
| claude-3-opus-20240229 Anthropic | 252 | 239 | 249 | 259 | 230 | 247 | 240 | 246 |
| molmo-2-8b Ai2 | 253 | — | 242 | — | — | — | 252 | — |
| llama-4-scout-17b-16e-instruct Meta | 254 | 250 | 250 | 248 | 235 | 246 | 260 | 253 |
| step-1o-turbo-202506 Stepfun | 255 | 261 | 244 | 265 | 248 | 240 | 251 | 221 |
| glm-4-plus Z.ai | 256 | 253 | 265 | 264 | 260 | 245 | 256 | 251 |
| qwen-max-0919 Alibaba | 257 | 257 | 267 | 263 | 255 | 253 | 255 | 249 |
| llama-3.3-70b-instruct Meta | 258 | 259 | 262 | 271 | 251 | 251 | 267 | 268 |
| gpt-4o-mini-2024-07-18 OpenAI | 259 | 271 | 276 | 267 | 271 | 239 | 266 | 250 |
| gpt-oss-20b OpenAI | 260 | 242 | 260 | 242 | 219 | 298 | 279 | 277 |
| gemma-3n-e4b-it Google | 261 | 275 | 274 | 299 | 284 | 235 | 280 | 269 |
| qwen2.5-plus-1127 Alibaba | 262 | 237 | 256 | 257 | 240 | 267 | 264 | 273 |
| mistral-large-2407 Mistral | 263 | 255 | 264 | 261 | 258 | 249 | 259 | 275 |
| athene-v2-chat | 264 | 249 | 243 | 241 | 231 | 289 | 254 | 262 |
| nvidia-nemotron-3-nano-30b-a3b-bf16 Nvidia | 265 | 229 | 259 | 251 | 212 | 296 | 270 | 294 |
| gpt-4-0125-preview OpenAI | 266 | 274 | 279 | 281 | 245 | 257 | 271 | 271 |
| gpt-4-1106-preview OpenAI | 267 | 269 | 272 | 277 | 242 | 250 | 262 | 278 |
| hunyuan-standard-2025-02-10 Tencent | 268 | 270 | 277 | 282 | 256 | 262 | 278 | 241 |
| gemini-1.5-flash-002 Google | 269 | 273 | 284 | 288 | 257 | 236 | 272 | 258 |
| grok-2-mini-2024-08-13 SpaceXAI | 270 | 265 | 283 | 279 | 274 | 268 | 276 | 264 |
| deepseek-v2.5 DeepSeek | 271 | 263 | 261 | 244 | 259 | 277 | 269 | 267 |
| athene-70b-0725 | 272 | 256 | 273 | 266 | 282 | 269 | 284 | 286 |
| olmo-3-32b-think Ai2 | 273 | 252 | 254 | 252 | 232 | 276 | 261 | 260 |
| mercury Inception AI | 274 | — | 269 | 246 | — | 309 | 290 | 283 |
| mistral-large-2411 Mistral | 275 | 282 | 271 | 270 | 264 | 263 | 263 | 274 |
| magistral-medium-2506 Mistral | 276 | 267 | 246 | 219 | 262 | 258 | 258 | 235 |
| granite-4.1-8b IBM | 277 | 224 | 263 | 262 | 226 | 280 | 273 | 285 |
| gemma-3-4b-it Google | 278 | 292 | 294 | 321 | 287 | 265 | 293 | 270 |
| mistral-small-3.1-24b-instruct-2503 Mistral | 279 | 254 | 266 | 250 | 269 | 270 | 265 | 259 |
| qwen2.5-72b-instruct Alibaba | 280 | 266 | 268 | 260 | 250 | 288 | 268 | 265 |
| llama-3.1-nemotron-70b-instruct Nvidia | 281 | 264 | 278 | 285 | 267 | 264 | 282 | 296 |
| hunyuan-large-vision Tencent | 282 | 260 | 286 | 256 | 265 | 259 | 274 | 266 |
| llama-3.1-70b-instruct Meta | 283 | 278 | 289 | 280 | 278 | 285 | 287 | 284 |
| amazon-nova-pro-v1.0 Amazon | 284 | 280 | 287 | 272 | 279 | 301 | 286 | 281 |
| gemma-2-27b-it Google | 285 | 291 | 297 | 303 | 291 | 243 | 289 | 280 |
| jamba-1.5-large AI21 | 286 | 272 | 295 | 294 | 294 | 282 | 294 | 314 |
| granite-4.2-3b IBM | 287 | 231 | 275 | 230 | — | 317 | 277 | 282 |
| reka-core-20240904 Reka | 288 | 268 | 300 | 290 | 293 | 272 | 298 | 297 |
| gpt-4-0314 OpenAI | 289 | 287 | 280 | 284 | 263 | 286 | 275 | 300 |
| granite-4.2-8b IBM | 290 | 201 | 282 | 238 | — | 323 | 281 | 276 |
| ibm-granite-h-small IBM | 291 | 244 | 288 | 286 | 268 | 295 | 292 | 287 |
| llama-3.1-nemotron-51b-instruct Nvidia | 292 | 296 | 298 | 292 | 276 | 281 | 297 | 303 |
| gemini-1.5-flash-001 Google | 293 | 284 | 292 | 296 | 285 | 278 | 295 | 279 |
| olmo-3.1-32b-think Ai2 | 294 | 226 | 281 | 276 | 241 | 290 | 283 | 272 |
| llama-3.1-tulu-3-70b Ai2 | 295 | — | 305 | 298 | 281 | 291 | 288 | 302 |
| claude-3-sonnet-20240229 Anthropic | 296 | 281 | 296 | 287 | 288 | 293 | 291 | 292 |
| gemma-2-9b-it-simpo Google | 297 | 307 | 306 | 324 | 315 | 254 | 305 | 290 |
| nemotron-4-340b-instruct Nvidia | 298 | 290 | 299 | 297 | 289 | 299 | 299 | 288 |
| llama-3-70b-instruct Meta | 299 | 299 | 301 | 300 | 286 | 287 | 300 | 316 |
| command-r-plus-08-2024 Cohere | 300 | 298 | 314 | 313 | 300 | 279 | 303 | 295 |
| gpt-4-0613 OpenAI | 301 | 294 | 290 | 291 | 270 | 274 | 285 | 298 |
| mistral-small-24b-instruct-2501 Mistral | 302 | 293 | 293 | 293 | 283 | 304 | 302 | 299 |
| glm-4-0520 Z.ai | 303 | 297 | 302 | 295 | 292 | 297 | 301 | 305 |
| reka-flash-20240904 Reka | 304 | 276 | 310 | 309 | 298 | 294 | 306 | 310 |
| qwen2.5-coder-32b-instruct Alibaba | 305 | 277 | 285 | 275 | 277 | 315 | 296 | 293 |
| c4ai-aya-expanse-32b Cohere | 306 | 285 | 308 | 308 | 297 | 303 | 307 | 289 |
| gemma-2-9b-it Google | 307 | 304 | 316 | 325 | 306 | 284 | 310 | 309 |
| deepseek-coder-v2 DeepSeek | 308 | 286 | 291 | 273 | 275 | 316 | 304 | 291 |
| qwen2-72b-instruct Alibaba | 309 | 289 | 304 | 306 | 273 | 306 | 313 | 313 |
| command-r-plus Cohere | 310 | 302 | 318 | 322 | 309 | 302 | 314 | 312 |
| claude-3-haiku-20240307 Anthropic | 311 | 295 | 311 | 304 | 299 | 310 | 309 | 306 |
| amazon-nova-lite-v1.0 Amazon | 312 | 288 | 307 | 302 | 296 | 308 | 311 | 301 |
| gemini-1.5-flash-8b-001 Google | 313 | 301 | 315 | 323 | 301 | 300 | 315 | 307 |
| phi-4 Microsoft | 314 | 283 | 303 | 301 | 280 | 313 | 308 | 308 |
| olmo-2-0325-32b-instruct Ai2 | 315 | — | 313 | 315 | 303 | 305 | 318 | 320 |
| command-r-08-2024 Cohere | 316 | 309 | 317 | 312 | 316 | 314 | 317 | 311 |
| mistral-large-2402 Mistral | 317 | 310 | 312 | 307 | 295 | 312 | 316 | 319 |
| amazon-nova-micro-v1.0 Amazon | 318 | 300 | 321 | 310 | 304 | 320 | 323 | 317 |
| jamba-1.5-mini AI21 | 319 | 322 | 324 | 327 | 336 | 311 | 329 | 335 |
| ministral-8b-2410 Mistral | 320 | 303 | 319 | 320 | 310 | 307 | 325 | 315 |
| gemini-pro-dev-api Google | 321 | 331 | 328 | 345 | 325 | 318 | 327 | 326 |
| qwen1.5-110b-chat Alibaba | 322 | 311 | 320 | 314 | 305 | 326 | 320 | 324 |
| reka-flash-21b-20240226-online Reka | 323 | 313 | 326 | 316 | 312 | 335 | 331 | 333 |
| qwen1.5-72b-chat Alibaba | 324 | 305 | 323 | 318 | 314 | 331 | 324 | 321 |
| hunyuan-standard-256k Tencent | 325 | — | 309 | 305 | 290 | 325 | 312 | 304 |
| mixtral-8x22b-instruct-v0.1 Mistral | 326 | 317 | 322 | 317 | 302 | 329 | 322 | 332 |
| command-r Cohere | 327 | 321 | 343 | 341 | 337 | 324 | 332 | 322 |
| reka-flash-21b-20240226 Reka | 328 | 319 | 327 | 326 | 324 | 337 | 336 | 334 |
| gpt-3.5-turbo-0125 OpenAI | 329 | 327 | 332 | 319 | 321 | 328 | 321 | 330 |
| llama-3-8b-instruct Meta | 330 | 323 | 339 | 333 | 332 | 321 | 337 | 336 |
| gemini-pro Google | 331 | — | 330 | 337 | 320 | 332 | 319 | — |
| c4ai-aya-expanse-8b Cohere | 332 | 308 | 331 | 332 | 322 | 330 | 330 | 318 |
| mistral-medium Mistral | 333 | 312 | 325 | 328 | 307 | 327 | 326 | 331 |
| llama-3.1-tulu-3-8b Ai2 | 334 | — | 336 | 334 | 318 | 322 | 328 | 325 |
| zephyr-orpo-141b-A35b-v0.1 | 335 | 336 | 342 | 340 | 328 | 340 | 334 | 346 |
| yi-1.5-34b-chat 01.AI | 336 | 315 | 335 | 339 | 311 | 343 | 339 | 337 |
| llama-3.1-8b-instruct Meta | 337 | 326 | 337 | 331 | 335 | 336 | 338 | 328 |
| granite-3.1-8b-instruct IBM | 338 | 306 | 329 | 311 | 334 | 339 | 335 | 323 |
| gpt-3.5-turbo-1106 OpenAI | 339 | 320 | 333 | 329 | 319 | 345 | 333 | 343 |
| qwen1.5-32b-chat Alibaba | 340 | 314 | 338 | 330 | 323 | 367 | 341 | 327 |
| gemma-2-2b-it Google | 341 | 337 | 354 | 363 | 341 | 334 | 348 | 344 |
| phi-3-medium-4k-instruct Microsoft | 342 | 324 | 344 | 347 | 308 | 348 | 344 | 341 |
| mixtral-8x7b-instruct-v0.1 Mistral | 343 | 328 | 345 | 344 | 333 | 342 | 342 | 348 |
| dbrx-instruct-preview Databricks | 344 | 330 | 341 | 335 | 329 | 341 | 340 | 342 |
| qwen1.5-14b-chat Alibaba | 345 | 329 | 347 | 343 | 339 | 357 | 349 | 340 |
| internlm2_5-20b-chat | 346 | 316 | 334 | 338 | 317 | 368 | 343 | 339 |
| deepseek-llm-67b-chat DeepSeek | 347 | — | 359 | 350 | 347 | 362 | 351 | 345 |
| wizardlm-70b Microsoft | 348 | — | 361 | 362 | 345 | 319 | 350 | 349 |
| yi-34b-chat 01.AI | 349 | 342 | 355 | 356 | 350 | 346 | 358 | 352 |
| granite-3.0-8b-instruct IBM | 350 | 325 | 346 | 342 | 326 | 358 | 346 | 338 |
| openchat-3.5 | 351 | 340 | 358 | 358 | 358 | 333 | 354 | 347 |
| openchat-3.5-0106 | 352 | 341 | 352 | 348 | 344 | 350 | 353 | 353 |
| gemma-1.1-7b-it Google | 353 | 334 | 349 | 351 | 343 | 349 | 352 | 354 |
| snowflake-arctic-instruct | 354 | 339 | 353 | 349 | 342 | 354 | 356 | 371 |
| granite-3.1-2b-instruct IBM | 355 | 318 | 340 | 336 | 327 | 351 | 345 | 329 |
| tulu-2-dpo-70b | 356 | — | 351 | 352 | 352 | 352 | 347 | 351 |
| openhermes-2.5-mistral-7b | 357 | — | 356 | 365 | 349 | 344 | 357 | 366 |
| vicuna-33b | 358 | 346 | 365 | 361 | 364 | 338 | 362 | 368 |
| phi-3-small-8k-instruct Microsoft | 359 | 338 | 350 | 357 | 331 | 365 | 355 | 357 |
| starling-lm-7b-beta | 360 | 335 | 348 | 346 | 346 | 372 | 360 | 355 |
| llama-2-70b-chat Meta | 361 | 350 | 366 | 368 | 354 | 371 | 365 | 367 |
| starling-lm-7b-alpha | 362 | 349 | 363 | 355 | 356 | 359 | 363 | 359 |
| llama-3.2-3b-instruct Meta | 363 | 332 | 364 | 369 | 340 | 353 | 359 | 358 |
| nous-hermes-2-mixtral-8x7b-dpo | 364 | — | 384 | 370 | 371 | 363 | 380 | 374 |
| granite-3.0-2b-instruct IBM | 365 | 333 | 357 | 353 | 338 | 378 | 367 | 361 |
| llama2-70b-steerlm-chat Nvidia | 366 | — | 377 | 385 | 365 | 370 | 369 | 387 |
| qwq-32b-preview Alibaba | 367 | 343 | 362 | 371 | 313 | 373 | 361 | 350 |
| solar-10.7b-instruct-v1.0 | 368 | — | 369 | 367 | 369 | 356 | 377 | — |
| dolphin-2.2.1-mistral-7b | 369 | — | 371 | — | 359 | 364 | 368 | — |
| mpt-30b-chat | 370 | — | 368 | 373 | 370 | 366 | 364 | — |
| wizardlm-13b Microsoft | 371 | — | 388 | 383 | 380 | 355 | 371 | 360 |
| mistral-7b-instruct-v0.2 Mistral | 372 | 348 | 370 | 366 | 355 | 374 | 373 | 369 |
| falcon-180b-chat | 373 | — | 385 | — | — | 347 | 366 | — |
| qwen1.5-7b-chat Alibaba | 374 | 345 | 375 | 354 | 361 | 390 | 372 | 356 |
| phi-3-mini-4k-instruct-june-2024 Microsoft | 375 | 344 | 360 | 360 | 330 | 379 | 370 | 377 |
| vicuna-13b | 376 | 355 | 382 | 376 | 375 | 369 | 376 | 362 |
| llama-2-13b-chat Meta | 377 | 352 | 379 | 377 | 367 | 382 | 379 | 365 |
| qwen-14b-chat Alibaba | 378 | — | 378 | 359 | 357 | 375 | 374 | 372 |
| palm-2 Google | 379 | — | 376 | 381 | 363 | 386 | 375 | 364 |
| gemma-7b-it Google | 380 | 353 | 372 | 375 | 362 | 376 | 381 | 375 |
| codellama-34b-instruct Meta | 381 | — | 381 | 379 | 368 | 387 | 382 | 381 |
| zephyr-7b-beta | 382 | 356 | 387 | 382 | 377 | 360 | 389 | 378 |
| phi-3-mini-128k-instruct Microsoft | 383 | 358 | 383 | 380 | 353 | 388 | 385 | 386 |
| phi-3-mini-4k-instruct Microsoft | 384 | 347 | 373 | 364 | 351 | 393 | 378 | 376 |
| guanaco-33b | 385 | — | 393 | 391 | 378 | 361 | 396 | — |
| zephyr-7b-alpha | 386 | — | 386 | 374 | — | 377 | 386 | — |
| stripedhyena-nous-7b | 387 | — | 392 | 390 | 374 | 385 | 388 | 385 |
| codellama-70b-instruct Meta | 388 | — | 367 | — | — | — | 387 | — |
| gemma-1.1-2b-it Google | 389 | 354 | 380 | 372 | 366 | 380 | 384 | 373 |
| vicuna-7b | 390 | — | 394 | 388 | 382 | 384 | 392 | 363 |
| smollm2-1.7b-instruct | 391 | — | 374 | 378 | 348 | 391 | 383 | 370 |
| llama-3.2-1b-instruct Meta | 392 | 360 | 390 | 384 | 360 | 389 | 391 | 379 |
| mistral-7b-instruct Mistral | 393 | 359 | 389 | 386 | 376 | 383 | 390 | 380 |
| llama-2-7b-chat Meta | 394 | 351 | 395 | 393 | 373 | 394 | 395 | 384 |
| gemma-2b-it Google | 395 | — | 391 | 387 | 379 | 392 | 393 | 382 |
| qwen1.5-4b-chat Alibaba | 396 | 357 | 396 | 389 | 372 | 397 | 394 | 383 |
| olmo-7b-instruct Ai2 | 397 | — | 397 | 392 | 381 | 403 | 399 | — |
| koala-13b | 398 | — | 400 | 396 | 388 | 398 | 400 | — |
| alpaca-13b | 399 | — | 405 | 402 | 385 | 381 | 401 | — |
| gpt4all-13b-snoozy | 400 | — | 398 | — | 384 | 395 | 397 | — |
| mpt-7b-chat | 401 | — | 401 | 395 | 386 | 396 | 402 | — |
| chatglm3-6b | 402 | — | 399 | 394 | 383 | 399 | 398 | 388 |
| RWKV-4-Raven-14B | 403 | — | 404 | 397 | 387 | 401 | 406 | — |
| chatglm2-6b | 404 | — | 402 | 400 | 390 | 402 | 404 | — |
| oasst-pythia-12b | 405 | — | 403 | 398 | 391 | 400 | 403 | — |
| chatglm-6b | 406 | — | 406 | 399 | 389 | 406 | 405 | — |
| fastchat-t5-3b | 407 | — | 409 | 404 | 394 | 404 | 407 | — |
| dolly-v2-12b | 408 | — | 407 | 403 | 392 | 405 | 408 | — |
| llama-13b Meta | 409 | — | 410 | 405 | 393 | 407 | 409 | — |
| stablelm-tuned-alpha-7b | 410 | — | 408 | 401 | 395 | 408 | 410 | — |