← Back to Test Cases
Generate EM Trending Report from Scattered Data
Task CompletionEm Reporthard
Cross-Model Comparison
| Model | Score | Latency | Tokens In | Tokens Out |
|---|---|---|---|---|
| Qwen3.8-Flash | N/A | N/A | - | - |
| GLM-5.3-Flash | N/A | N/A | - | - |
| GLM-5.3 | N/A | N/A | - | - |
| GLM-5.3 | N/A | N/A | - | - |
| Hy4 Preview | N/A | N/A | - | - |
| Hy4 Preview | N/A | N/A | - | - |
| GLM-5.3 | N/A | N/A | - | - |
| Hy4 Preview | N/A | N/A | - | - |
| Muse Glimmer 30B | N/A | N/A | - | - |
| Muse Glimmer 30B | N/A | N/A | - | - |
| Muse Glimmer 30B | N/A | N/A | - | - |
| GLM-5.3-Flash | N/A | N/A | - | - |
| MiniMax M3 | N/A | N/A | - | - |
| Qwen3.8 Max (2.4T-A95B) | N/A | N/A | - | - |
| Qwen3.8 Max (2.4T-A95B) | N/A | N/A | - | - |
| Qwen3.8 Max (2.4T-A95B) | N/A | N/A | - | - |
| Qwen3.8-Flash | N/A | N/A | - | - |
| MiniMax M3 | N/A | N/A | - | - |
| MiniMax M3 | N/A | N/A | - | - |
| Qwen3.8-Flash | N/A | N/A | - | - |
| Claude Sonnet 4.6 | 95.0% | 207.0s | 1,097 | 14,026 |
| Claude Opus 4.6 | 94.8% | 212.6s | 1,097 | 12,719 |
| DeepSeek-R1 | 94.3% | 54.5s | 1,042 | 2,001 |
| Claude Opus 5 | 92.3% | 297.0s | 1,349 | 20,143 |
| Hy4 Preview | 92.0% | 252.3s | 1,064 | 20,322 |
| Qwen3.8-Flash | 92.0% | 239.7s | 1,393 | 31,340 |
| Claude Opus 4.8 | 92.0% | 48.4s | 1,349 | 3,911 |
| Kimi K3 | 91.8% | 689.9s | 1,161 | 12,507 |
| Claude Opus 5 | 91.8% | 276.8s | 1,349 | 23,707 |
| Qwen3.8-Flash | 91.7% | 242.7s | 1,393 | 30,973 |
| GLM-5.3 | 91.6% | 37.5s | 1,054 | 5,354 |
| Qwen3.8 Max (2.4T-A95B) | 91.6% | 205.6s | 1,393 | 22,620 |
| Qwen3.5-35B-A3B | 91.6% | 37.0s | 1,355 | 5,316 |
| Hy4 Preview | 91.5% | 263.8s | 1,064 | 21,382 |
| Qwen3.8 Max (2.4T-A95B) | 91.5% | 122.9s | 1,393 | 29,031 |
| GPT-5.4 | 91.5% | 44.5s | 1,037 | 3,121 |
| Qwen3.8-Flash | 91.3% | 235.3s | 1,393 | 29,873 |
| GLM-5.3-Flash | 90.8% | 386.8s | 1,053 | 16,833 |
| Kimi K3 | 90.5% | 109.2s | 1,126 | 10,433 |
| Qwen3.8 27B | 90.5% | 747.3s | 1,393 | 42,384 |
| GLM-5.3 | 90.0% | 33.8s | 1,054 | 4,973 |
| Claude Opus 5 | 89.8% | 256.9s | 1,349 | 21,383 |
| GPT-5.6 Luna | 89.8% | 48.2s | 1,037 | 4,878 |
| GPT-5.6 Luna | 89.8% | 51.4s | 1,037 | 5,041 |
| Qwen3.6 35B A3B | 89.5% | 37.6s | 1,355 | 6,657 |
| GLM-5.3-Flash | 89.1% | 234.5s | 1,053 | 19,462 |
| Qwen3.8 Max (2.4T-A95B) | 88.8% | 652.0s | 1,393 | 29,682 |
| Qwen3.8 27B | 88.7% | 665.3s | 1,393 | 29,804 |
| Qwen3.8 27B | 88.7% | 295.6s | 1,393 | 23,714 |
| DeepSeek V4 Pro | 88.5% | 241.6s | 1,042 | 9,297 |
| GPT-5.6 Terra | 88.4% | 70.3s | 1,037 | 5,684 |
| GPT-5.6 Sol | 88.2% | 72.2s | 1,037 | 6,013 |
| Gemini 3.1 Pro | 88.0% | 281.2s | 1,384 | 5,510 |
| Kimi K3 | 88.0% | 48.5s | 1,161 | 10,195 |
| Qwen3.5-397B-A17B | 87.5% | 74.5s | 1,355 | 5,115 |
| GPT-5.6 Terra | 86.5% | 68.8s | 1,037 | 5,878 |
| Claude Sonnet 5 | 85.8% | 118.6s | 1,349 | 12,119 |
| MiniMax M3 | 85.5% | 39.6s | 1,149 | 6,577 |
| Muse Glimmer 30B | 85.5% | 124.4s | 1,054 | 6,847 |
| MiniMax M3 | 85.0% | 33.9s | 1,201 | 7,796 |
| GLM-5.3 | 84.5% | 43.1s | 1,054 | 6,242 |
| Qwen3.6 27B | 84.4% | 124.0s | 1,355 | 7,575 |
| GLM-5.2 | 84.4% | 24.2s | 1,053 | 4,421 |
| Hy4 Preview | 84.0% | 294.8s | 1,064 | 23,708 |
| GPT-5.6 Sol | 83.8% | 68.6s | 1,037 | 6,221 |
| Gemini 3 Flash | 83.1% | 8.2s | 1,384 | 1,229 |
| Qwen3.6 27B | 82.5% | 231.6s | 1,355 | 7,626 |
| Gemma 4 26B A4B IT | 82.4% | 9.8s | 1,402 | 1,524 |
| MiniMax M2.7 | 81.8% | 123.8s | 1,047 | 8,126 |
| GPT-5.6 Sol | 81.8% | 60.4s | 1,037 | 5,178 |
| Claude Sonnet 5 | 81.8% | 216.3s | 1,349 | 21,485 |
| GPT-5.6 Luna | 80.7% | 55.4s | 1,037 | 5,689 |
| Qwen3.6 27B | 80.3% | 121.8s | 1,355 | 7,788 |
| GLM-5.3-Flash | 80.0% | 258.8s | 1,053 | 12,714 |
| Qwen3.5-397B-A17B | 79.8% | 57.9s | 1,355 | 5,303 |
| DeepSeek V4 Pro | 79.5% | 74.2s | 1,042 | 5,184 |
| Muse Glimmer 30B | 78.7% | 58.2s | 1,054 | 5,773 |
| Claude Haiku 4.5 | 78.2% | 35.0s | 1,096 | 4,736 |
| Muse Glimmer 30B | 77.8% | 138.0s | 1,054 | 7,180 |
| Qwen3.5-35B-A3B | 77.6% | 177.3s | 1,355 | 6,685 |
| DeepSeek V4 Flash | 77.5% | 206.3s | 1,042 | 7,162 |
| Claude Sonnet 5 | 76.3% | 116.8s | 1,349 | 12,015 |
| Qwen3.6 35B A3B | 76.2% | 33.8s | 1,355 | 7,177 |
| DeepSeek-V3.2 | 76.1% | 66.7s | 1,042 | 1,403 |
| DeepSeek V4 Flash | 76.0% | 40.0s | 1,042 | 6,731 |
| Qwen3.5-35B-A3B | 76.0% | 30.7s | 1,355 | 5,303 |
| GPT-5.4 mini | 75.7% | 13.7s | 1,037 | 2,691 |
| GPT-5.6 Terra | 75.6% | 75.1s | 1,037 | 5,953 |
| DeepSeek V4 Flash | 75.3% | 157.0s | 1,042 | 4,946 |
| DeepSeek V4 Pro | 75.0% | 131.3s | 1,042 | 6,243 |
| Gemma 4 31B IT | 75.0% | 54.7s | 1,417 | 1,328 |
| GLM-5.2 | 74.5% | 101.6s | 1,053 | 7,002 |
| Qwen3.5-35B-A3B | 74.1% | 36.1s | 1,355 | 6,184 |
| MiniMax M2.7 | 72.8% | 47.9s | 1,044 | 4,300 |
| Qwen3.6 35B A3B | 72.7% | 31.6s | 1,355 | 7,507 |
| Gemma 4 31B IT | 71.8% | 45.1s | 1,401 | 1,338 |
| MiniMax M3 | 71.0% | 42.0s | 1,149 | 6,536 |
| Llama 4 Maverick | 71.0% | 40.3s | 1,041 | 992 |
| GLM-5.2 | 70.8% | 217.2s | 1,053 | 14,328 |
| MiniMax M2.7 | 70.3% | 75.0s | 1,044 | 7,083 |
| Qwen3.6 27B | 69.8% | 202.9s | 1,355 | 7,458 |
| Claude Haiku 4.5 | 69.5% | 63.0s | 1,096 | 9,532 |
| GPT-5.4 nano | 68.8% | 14.6s | 1,037 | 3,058 |
| DeepSeek V4 Flash | 68.5% | 68.9s | 1,042 | 6,064 |
| Gemma 4 26B A4B IT | 68.5% | 20.2s | 1,401 | 1,413 |
| DeepSeek-V3.2 | 68.3% | 75.6s | 1,042 | 1,920 |
| Gemma 4 31B IT | 67.8% | 40.6s | 1,401 | 1,339 |
| Mistral Large 3 675B | 67.8% | 32.2s | 1,363 | 2,233 |
| Qwen3.6 35B A3B | 67.3% | 27.1s | 1,355 | 6,800 |
| Qwen3.5-397B-A17B | 66.3% | 54.2s | 1,355 | 5,176 |
| Claude Haiku 4.5 | 65.8% | 52.7s | 1,096 | 7,431 |
| DeepSeek-V3.2 | 65.8% | 56.2s | 1,042 | 1,589 |
| Gemma 4 26B A4B IT | 65.8% | 13.9s | 1,402 | 1,380 |
| Llama 3.3 70B Instruct | 65.3% | 26.7s | 1,044 | 723 |
| Mistral Small 2603 | 65.0% | 12.8s | 1,375 | 2,445 |
| Gemma 4 26B A4B IT | 64.8% | 26.7s | 1,401 | 1,393 |
| DeepSeek-R1-Distill-Qwen-32B | 64.8% | 145.2s | 1,341 | 2,187 |
| DeepSeek-V3.2 | 64.0% | 52.8s | 1,042 | 1,467 |
| Mistral Large 3 675B | 63.2% | 28.5s | 1,363 | 2,450 |
| Llama 4 Maverick | 63.2% | 38.8s | 1,041 | 855 |
| Mistral Small 2603 | 61.3% | 17.9s | 1,375 | 2,172 |
| Claude Haiku 4.5 | 60.8% | 42.9s | 1,096 | 5,860 |
| DeepSeek V4 Pro | 60.5% | 81.3s | 1,042 | 2,417 |
| MiniMax M2.7 | 60.3% | 44.0s | 1,044 | 4,618 |
| Mistral Small 2603 | 60.0% | 16.7s | 1,375 | 2,667 |
| Gemini 3.1 Flash-Lite | 59.8% | 4.2s | 1,384 | 877 |
| Qwen3.5-397B-A17B | 59.5% | 102.4s | 1,355 | 5,762 |
| Mistral Large 3 675B | 58.8% | 24.6s | 1,363 | 2,238 |
| DeepSeek-R1 | 58.8% | 256.6s | 1,040 | 6,576 |
| GLM-5.2 | 58.8% | 155.1s | 1,053 | 9,687 |
| Gemma 4 31B IT | 58.8% | 72.8s | 1,401 | 1,269 |
| Mistral Large 3 675B | 57.8% | 29.3s | 1,363 | 2,528 |
| DeepSeek-V3.2 | 57.3% | 52.0s | 1,042 | 1,446 |
| Mistral Small 2603 | 55.8% | 11.6s | 1,375 | 1,725 |
| DeepSeek-R1 | 54.0% | 205.5s | 1,040 | 7,010 |
| Llama 4 Maverick | 53.3% | 15.3s | 1,041 | 740 |
| Llama 3.3 70B Instruct | 52.8% | 29.1s | 1,063 | 839 |
| DeepSeek-R1 | 51.5% | 199.9s | 1,040 | 6,377 |
| Llama 4 Scout | 50.2% | 30.1s | 1,041 | 921 |
| Llama 4 Scout | 48.8% | 9.7s | 1,041 | 839 |
| Llama 4 Maverick | 47.8% | 52.0s | 1,041 | 831 |
| Llama 4 Scout | 47.3% | 35.8s | 1,041 | 838 |
| Llama 4 Scout | 47.0% | 30.8s | 1,041 | 751 |
| Llama 3.3 70B Instruct | 44.0% | 31.6s | 1,063 | 1,037 |
| Llama 3.3 70B Instruct | 40.3% | 10.8s | 1,044 | 733 |
Tags
environmental_monitoringtrendingdata_analysis