Loading timeline…
Loading timeline…
Every recorded change for this company, newest first. Back to the entity page →
257 events
DeepSeek V3 scores 30.67% on SWE-bench Lite
DeepSeek V3 scores 36.67% on SWE-bench Lite
DeepSeek V3 0324 scores 42% on SWE-bench Verified
DeepSeek V3.2 Reasoner scores 60% on SWE-bench Verified
DeepSeek V3.2 scores 70% on SWE-bench Verified
DeepSeek V3.2 scores 59% on SWE-bench Multilingual
DeepSeek-V4.1-Flash scores 70.033% on LiveBench
DeepSeek-V4.1-Flash scores 81.19% on LiveBench
DeepSeek-V4.1-Flash scores 79.253% on LiveBench
DeepSeek-V4.1-Flash scores 93.29% on LiveBench
DeepSeek-V4.1-Flash scores 77.273% on LiveBench
DeepSeek-V4.1-Flash scores 80.037% on LiveBench
DeepSeek-V4.1-Flash scores 86.692% on LiveBench
DeepSeek-V4.1-Flash scores 81.11% on LiveBench
DeepSeek V4 Flash Vision Exp scores 70.958% on LiveBench
DeepSeek V4 Flash Vision Exp scores 80.36% on LiveBench
DeepSeek V4 Flash Vision Exp scores 79.477% on LiveBench
DeepSeek V4 Flash Vision Exp scores 87.807% on LiveBench
DeepSeek V4 Flash Vision Exp scores 65.101% on LiveBench
DeepSeek V4 Flash Vision Exp scores 68.203% on LiveBench
DeepSeek V4 Flash Vision Exp scores 85.399% on LiveBench
DeepSeek V4 Flash Vision Exp scores 76.758% on LiveBench
DeepSeek-V4-Pro-0813 scores 67.7% on LiveBench
DeepSeek-V4-Pro-0813 scores 82.074% on LiveBench
DeepSeek-V4-Pro-0813 scores 79.243% on LiveBench
DeepSeek-V4-Pro-0813 scores 95.086% on LiveBench
DeepSeek-V4-Pro-0813 scores 54.95% on LiveBench
DeepSeek-V4-Pro-0813 scores 77.159% on LiveBench
DeepSeek-V4-Pro-0813 scores 85.841% on LiveBench
DeepSeek-V4-Pro-0813 scores 77.436% on LiveBench
DeepSeek V4 Flash (0731) scores 65.517% on LiveBench
DeepSeek V4 Flash (0731) scores 79.175% on LiveBench
DeepSeek V4 Flash (0731) scores 79.327% on LiveBench
DeepSeek V4 Flash (0731) scores 86.79% on LiveBench
DeepSeek V4 Flash (0731) scores 46.768% on LiveBench
DeepSeek V4 Flash (0731) scores 74.984% on LiveBench
DeepSeek V4 Flash (0731) scores 86.635% on LiveBench
DeepSeek V4 Flash (0731) scores 74.171% on LiveBench
deepseek-v4-pro scores 62.35% on LiveBench
deepseek-v4-pro scores 78.13% on LiveBench
deepseek-v4-pro scores 74.538% on LiveBench
deepseek-v4-pro scores 90.675% on LiveBench
deepseek-v4-pro scores 42.626% on LiveBench
deepseek-v4-pro scores 69.994% on LiveBench
deepseek-v4-pro scores 82.692% on LiveBench
deepseek-v4-pro scores 71.572% on LiveBench
deepseek-v4-flash scores 63.137% on LiveBench
deepseek-v4-flash scores 70.124% on LiveBench
deepseek-v4-flash scores 68.023% on LiveBench
deepseek-v4-flash scores 79.648% on LiveBench
deepseek-v4-flash scores 37.626% on LiveBench
deepseek-v4-flash scores 69.228% on LiveBench
deepseek-v4-flash scores 70.582% on LiveBench
deepseek-v4-flash scores 65.481% on LiveBench
deepseek-v3-2-0925 scores 25% on Terminal-Bench
deepseek-v3-2-0925 scores 33.92% on τ²-bench
deepseek-v3-2-0925 scores 43.13% on IFBench
deepseek-v3-2-0925 scores 9.04% on Humanity's Last Exam
deepseek-v3-2-0925 scores 73.84% on GPQA
deepseek-v3-2-0925 scores 13.88 on Artificial Analysis Intelligence Index
deepseek-v3-1-terminus-reasoning scores 30.3% on Terminal-Bench
deepseek-v3-1-terminus-reasoning scores 44.94% on Terminal-Bench
deepseek-v3-1-terminus-reasoning scores 0% on Terminal-Bench
deepseek-v3-1-terminus-reasoning scores 37.13% on τ²-bench
deepseek-v3-1-terminus-reasoning scores 57.01% on IFBench
deepseek-v3-1-terminus-reasoning scores 37.96% on SciCode
deepseek-v3-1-terminus-reasoning scores 16.36% on Humanity's Last Exam
deepseek-v3-1-terminus-reasoning scores 79.19% on GPQA
deepseek-v3-1-terminus-reasoning scores 15.4 on Artificial Analysis Intelligence Index
deepseek-r1-0120 scores 6.06% on Terminal-Bench
deepseek-r1-0120 scores 19.1% on Terminal-Bench
deepseek-r1-0120 scores 0% on Terminal-Bench
deepseek-r1-0120 scores 11.4% on τ²-bench
deepseek-r1-0120 scores 38.98% on IFBench
deepseek-r1-0120 scores 38.31% on SciCode
deepseek-r1-0120 scores 8.5% on Humanity's Last Exam
deepseek-r1-0120 scores 70.81% on GPQA
deepseek-r1-0120 scores 11.41 on Artificial Analysis Intelligence Index
deepseek-r1-distill-llama-8b scores 17.55% on IFBench
deepseek-r1-distill-llama-8b scores 30.2% on GPQA
deepseek-r1-distill-llama-8b scores 6.48 on Artificial Analysis Intelligence Index
deepseek-v3-1-reasoning scores 25% on Terminal-Bench
deepseek-v3-1-reasoning scores 37.43% on τ²-bench
deepseek-v3-1-reasoning scores 41.5% on IFBench
deepseek-v3-1-reasoning scores 14.27% on Humanity's Last Exam
deepseek-v3-1-reasoning scores 77.88% on GPQA
deepseek-v3-1-reasoning scores 13.48 on Artificial Analysis Intelligence Index
deepseek-v2 scores 5.51 on Artificial Analysis Intelligence Index
deepseek-v3 scores 6.82% on Terminal-Bench
deepseek-v3 scores 16.85% on Terminal-Bench
deepseek-v3 scores 2.9% on Humanity's Last Exam
deepseek-v3 scores 8.49 on Artificial Analysis Intelligence Index
DeepSeek-R1-Distill-Qwen-1.5B scores 13.2% on IFBench
DeepSeek-R1-Distill-Qwen-1.5B scores 3.08% on Humanity's Last Exam
DeepSeek-R1-Distill-Qwen-1.5B scores 9.8% on GPQA
DeepSeek-R1-Distill-Qwen-1.5B scores 5.51 on Artificial Analysis Intelligence Index
R1 Distill Llama 70B scores 1.52% on Terminal-Bench
R1 Distill Llama 70B scores 21.93% on τ²-bench
R1 Distill Llama 70B scores 27.55% on IFBench
R1 Distill Llama 70B scores 5.13% on Humanity's Last Exam
R1 Distill Llama 70B scores 40.2% on GPQA
R1 Distill Llama 70B scores 7.89 on Artificial Analysis Intelligence Index
deepseek-v3-2-speciale scores 34.85% on Terminal-Bench
deepseek-v3-2-speciale scores 0% on τ²-bench
deepseek-v3-2-speciale scores 63.88% on IFBench
deepseek-v3-2-speciale scores 28.73% on Humanity's Last Exam
deepseek-v3-2-speciale scores 87.07% on GPQA
deepseek-v3-2-speciale scores 14.46 on Artificial Analysis Intelligence Index
deepseek-v4-pro-0424-high scores 41.67% on Terminal-Bench
deepseek-v4-pro-0424-high scores 64.79% on Terminal-Bench
deepseek-v4-pro-0424-high scores 94.15% on τ²-bench
deepseek-v4-pro-0424-high scores 71.29% on IFBench
deepseek-v4-pro-0424-high scores 35.22% on Humanity's Last Exam
deepseek-v4-pro-0424-high scores 90.51% on GPQA
deepseek-v4-pro-0424-high scores 30.11 on Artificial Analysis Intelligence Index
DeepSeek-R1-0528-Qwen3-8B scores 1.52% on Terminal-Bench
DeepSeek-R1-0528-Qwen3-8B scores 0% on τ²-bench
DeepSeek-R1-0528-Qwen3-8B scores 19.86% on IFBench
DeepSeek-R1-0528-Qwen3-8B scores 5.93% on Humanity's Last Exam
DeepSeek-R1-0528-Qwen3-8B scores 61.21% on GPQA
DeepSeek-R1-0528-Qwen3-8B scores 8.08 on Artificial Analysis Intelligence Index
DeepSeek V3 scores 32.58% on Terminal-Bench
DeepSeek V3 scores 11.21% on Humanity's Last Exam
DeepSeek V3 scores 16.04 on Artificial Analysis Intelligence Index
deepseek-v4-pro-0424-non-reasoning scores 36.36% on Terminal-Bench
deepseek-v4-pro-0424-non-reasoning scores 91.23% on τ²-bench
deepseek-v4-pro-0424-non-reasoning scores 45.78% on IFBench
deepseek-v4-pro-0424-non-reasoning scores 8.25% on Humanity's Last Exam
deepseek-v4-pro-0424-non-reasoning scores 71.72% on GPQA
deepseek-v4-pro-0424-non-reasoning scores 20.83 on Artificial Analysis Intelligence Index
DeepSeek V3 0324 scores 15.15% on Terminal-Bench
DeepSeek V3 0324 scores 13.86% on Terminal-Bench
DeepSeek V3 0324 scores 0% on Terminal-Bench
DeepSeek V3 0324 scores 47.08% on τ²-bench
DeepSeek V3 0324 scores 41.02% on IFBench
DeepSeek V3 0324 scores 39% on SciCode
DeepSeek V3 0324 scores 4.74% on Humanity's Last Exam
DeepSeek V3 0324 scores 65.45% on GPQA
DeepSeek V3 0324 scores 9.72 on Artificial Analysis Intelligence Index
deepseek-v4-flash-vision scores 74.16% on Terminal-Bench
deepseek-v4-flash-vision scores 12.12% on Terminal-Bench
deepseek-v4-flash-vision scores 74.8% on MMMU-Pro
deepseek-v4-flash-vision scores 49.65% on SciCode
deepseek-v4-flash-vision scores 34.48% on Humanity's Last Exam
deepseek-v4-flash-vision scores 91.31% on GPQA
deepseek-v4-flash-vision scores 35.01 on Artificial Analysis Intelligence Index
deepseek-llm-67b-chat scores 5.3 on Artificial Analysis Intelligence Index
deepseek-v4-pro scores 78.65% on Terminal-Bench
deepseek-v4-pro scores 14.14% on Terminal-Bench
deepseek-v4-pro scores 51.04% on SciCode
deepseek-v4-pro scores 41.01% on Humanity's Last Exam
deepseek-v4-pro scores 92.83% on GPQA
deepseek-v4-pro scores 36.28 on Artificial Analysis Intelligence Index
deepseek-v4-flash-0420-high scores 38.64% on Terminal-Bench
deepseek-v4-flash-0420-high scores 56.93% on Terminal-Bench
deepseek-v4-flash-0420-high scores 3.03% on Terminal-Bench
deepseek-v4-flash-0420-high scores 95.61% on τ²-bench
deepseek-v4-flash-0420-high scores 73.47% on IFBench
deepseek-v4-flash-0420-high scores 40.16% on SciCode
deepseek-v4-flash-0420-high scores 30.26% on Humanity's Last Exam
deepseek-v4-flash-0420-high scores 86.67% on GPQA
deepseek-v4-flash-0420-high scores 24.84 on Artificial Analysis Intelligence Index
deepseek-v2-5-sep-2024 scores 6.55 on Artificial Analysis Intelligence Index
deepseek-coder-v2 scores 5.98 on Artificial Analysis Intelligence Index
deepseek-r1 scores 15.91% on Terminal-Bench
deepseek-r1 scores 15.85% on Humanity's Last Exam
deepseek-r1 scores 13.12 on Artificial Analysis Intelligence Index
deepseek-v4-flash-0420-non-reasoning scores 34.09% on Terminal-Bench
deepseek-v4-flash-0420-non-reasoning scores 94.44% on τ²-bench
deepseek-v4-flash-0420-non-reasoning scores 47.21% on IFBench
deepseek-v4-flash-0420-non-reasoning scores 7.78% on Humanity's Last Exam
deepseek-v4-flash-0420-non-reasoning scores 71.62% on GPQA
deepseek-v4-flash-0420-non-reasoning scores 18.88 on Artificial Analysis Intelligence Index
DeepSeek V3.2 Exp scores 31.06% on Terminal-Bench
DeepSeek V3.2 Exp scores 33.92% on τ²-bench
DeepSeek V3.2 Exp scores 54.15% on IFBench
DeepSeek V3.2 Exp scores 14.87% on Humanity's Last Exam
DeepSeek V3.2 Exp scores 79.7% on GPQA
DeepSeek V3.2 Exp scores 16.58 on Artificial Analysis Intelligence Index
deepseek-r1-distill-qwen-14b scores 22.11% on IFBench
deepseek-r1-distill-qwen-14b scores 4.13% on Humanity's Last Exam
deepseek-r1-distill-qwen-14b scores 48.38% on GPQA
deepseek-r1-distill-qwen-14b scores 7.85 on Artificial Analysis Intelligence Index
deepseek-v2-5 scores 6.62 on Artificial Analysis Intelligence Index
deepseek-v4-pro-0424 scores 46.21% on Terminal-Bench
deepseek-v4-pro-0424 scores 64.04% on Terminal-Bench
deepseek-v4-pro-0424 scores 14.65% on Terminal-Bench
deepseek-v4-pro-0424 scores 96.2% on τ²-bench
deepseek-v4-pro-0424 scores 76.46% on IFBench
deepseek-v4-pro-0424 scores 50.81% on SciCode
deepseek-v4-pro-0424 scores 37.53% on Humanity's Last Exam
deepseek-v4-pro-0424 scores 88.79% on GPQA
deepseek-v4-pro-0424 scores 30.87 on Artificial Analysis Intelligence Index
deepseek-coder-v2-lite scores 5.36% on Humanity's Last Exam
deepseek-coder-v2-lite scores 31.92% on GPQA
deepseek-coder-v2-lite scores 5.34 on Artificial Analysis Intelligence Index
DeepSeek V3.2 scores 35.61% on Terminal-Bench
DeepSeek V3.2 scores 46.82% on Terminal-Bench
DeepSeek V3.2 scores 90.64% on τ²-bench
DeepSeek V3.2 scores 24.56% on Humanity's Last Exam
DeepSeek V3.2 scores 21.49 on Artificial Analysis Intelligence Index
deepseek-v4-flash-0420 scores 35.61% on Terminal-Bench
deepseek-v4-flash-0420 scores 61.8% on Terminal-Bench
deepseek-v4-flash-0420 scores 2.53% on Terminal-Bench
deepseek-v4-flash-0420 scores 95.03% on τ²-bench
deepseek-v4-flash-0420 scores 79.18% on IFBench
deepseek-v4-flash-0420 scores 45.25% on SciCode
deepseek-v4-flash-0420 scores 34.85% on Humanity's Last Exam
deepseek-v4-flash-0420 scores 89.39% on GPQA
deepseek-v4-flash-0420 scores 24.63 on Artificial Analysis Intelligence Index
DeepSeek-V4.1-Flash scores 26.77% on Terminal-Bench
DeepSeek-V4.1-Flash scores 76.99% on MMMU-Pro
DeepSeek-V4.1-Flash scores 51.85% on SciCode
DeepSeek-V4.1-Flash scores 39.25% on Humanity's Last Exam
DeepSeek-V4.1-Flash scores 39.55 on Artificial Analysis Intelligence Index
DeepSeek-R1-Distill-Qwen-32B scores 22.93% on IFBench
DeepSeek-R1-Distill-Qwen-32B scores 4.58% on Humanity's Last Exam
DeepSeek-R1-Distill-Qwen-32B scores 61.52% on GPQA
DeepSeek-R1-Distill-Qwen-32B scores 8.38 on Artificial Analysis Intelligence Index
DeepSeek V3.1 Terminus scores 31.82% on Terminal-Bench
DeepSeek V3.1 Terminus scores 37.13% on τ²-bench
DeepSeek V3.1 Terminus scores 41.22% on IFBench
DeepSeek V3.1 Terminus scores 8.67% on Humanity's Last Exam
DeepSeek V3.1 Terminus scores 75.05% on GPQA
DeepSeek V3.1 Terminus scores 13.93 on Artificial Analysis Intelligence Index
DeepSeek V3.1 scores 24.24% on Terminal-Bench
DeepSeek V3.1 scores 6.67% on Humanity's Last Exam
DeepSeek V3.1 scores 13.71 on Artificial Analysis Intelligence Index
deepseek-v4-flash scores 78.65% on Terminal-Bench
deepseek-v4-flash scores 12.12% on Terminal-Bench
deepseek-v4-flash scores 50.35% on SciCode
deepseek-v4-flash scores 38.55% on Humanity's Last Exam
deepseek-v4-flash scores 90.81% on GPQA
deepseek-v4-flash scores 34.53 on Artificial Analysis Intelligence Index
DeepSeek V3 0324 scores 99.6% on Aider polyglot
DeepSeek V3 0324 scores 55.1% on Aider polyglot
Showing up to 400 events. Narrow by year or category, or use the changes feed for cursor-paged history. Times are UTC.