Loading timeline…
Loading timeline…
Every recorded change for this company, newest first. Back to the entity page →
400 events
claude-35-sonnet scores 5.03% on SWE-bench Multimodal
claude-35-sonnet scores 6.19% on SWE-bench Multimodal
claude-35-sonnet scores 11.41% on SWE-bench Multimodal
Claude Sonnet 3.5 scores 11.99% on SWE-bench Multimodal
Claude Sonnet 3.5 scores 12.19% on SWE-bench Multimodal
claude-35-sonnet scores 25.34% on SWE-bench Multimodal
Claude 3.7 Sonnet scores 30.56% on SWE-bench Multimodal
Claude 3.7 Sonnet scores 31.33% on SWE-bench Multimodal
Claude Sonnet 4 scores 34.43% on SWE-bench Multimodal
Claude 4 Sonnet scores 35.59% on SWE-bench Multimodal
claude-3-opus scores 4.33% on SWE-bench Lite
claude-3-opus scores 11.67% on SWE-bench Lite
claude-35-sonnet scores 23% on SWE-bench Lite
GPT-4o & Claude 3 Opus scores 26.33% on SWE-bench Lite
CodeAct v1.8 scores 26.67% on SWE-bench Lite
claude-35-sonnet scores 26.67% on SWE-bench Lite
claude-3-5-sonnet-20241022 scores 30% on SWE-bench Lite
claude-35-sonnet scores 37% on SWE-bench Lite
claude-35-sonnet scores 38.33% on SWE-bench Lite
claude-35-sonnet scores 39% on SWE-bench Lite
claude-35-sonnet scores 40.67% on SWE-bench Lite
claude-35-sonnet scores 41% on SWE-bench Lite
claude-35-sonnet scores 41.33% on SWE-bench Lite
CodeAct v2.1 (claude-3-5-sonnet-20241022) scores 41.67% on SWE-bench Lite
claude-35-sonnet scores 42.67% on SWE-bench Lite
claude-35-sonnet scores 44.67% on SWE-bench Lite
claude-35-sonnet scores 46% on SWE-bench Lite
claude-35-sonnet scores 47.33% on SWE-bench Lite
Claude 3.7 Sonnet scores 48% on SWE-bench Lite
claude-35-sonnet scores 51.33% on SWE-bench Lite
Claude 4 Sonnet scores 56.67% on SWE-bench Lite
Claude 4 Sonnet scores 58.33% on SWE-bench Lite
Claude 4 Sonnet scores 60.33% on SWE-bench Lite
claude-2 scores 4.4% on SWE-bench Verified
claude-3-opus scores 7% on SWE-bench Verified
claude-3-opus scores 15.8% on SWE-bench Verified
claude-35-sonnet scores 33.6% on SWE-bench Verified
claude-35-sonnet scores 39.6% on SWE-bench Verified
Multiple scores 40.6% on SWE-bench Verified
Claude Haiku 3.5 scores 40.6% on SWE-bench Verified
claude-35-sonnet scores 40.6% on SWE-bench Verified
Multiple scores 41.6% on SWE-bench Verified
claude-3-5-sonnet-20241022 scores 46.2% on SWE-bench Verified
Multiple scores 46.6% on SWE-bench Verified
Multiple scores 47.2% on SWE-bench Verified
Multiple scores 48.6% on SWE-bench Verified
claude-35-sonnet scores 49% on SWE-bench Verified
Multiple scores 49.2% on SWE-bench Verified
claude-35-sonnet scores 50.8% on SWE-bench Verified
claude-3-5-sonnet-20241022 scores 51.6% on SWE-bench Verified
claude-35-sonnet scores 51.8% on SWE-bench Verified
Claude 3.7 Sonnet scores 52.8% on SWE-bench Verified
CodeAct v2.1 (claude-3-5-sonnet-20241022) scores 53% on SWE-bench Verified
claude-35-sonnet scores 54.2% on SWE-bench Verified
claude-35-sonnet scores 55.4% on SWE-bench Verified
Claude Sonnet 4 scores 57% on SWE-bench Verified
Multiple scores 57.2% on SWE-bench Verified
Multiple scores 58.2% on SWE-bench Verified
claude-35-sonnet scores 60.2% on SWE-bench Verified
swe-search scores 62.2% on SWE-bench Verified
Claude 3.7 Sonnet w/ Review Heavy scores 62.4% on SWE-bench Verified
claude-35-sonnet scores 62.8% on SWE-bench Verified
Claude 3.7 Sonnet scores 63.2% on SWE-bench Verified
claude-35-sonnet scores 63.4% on SWE-bench Verified
Claude 4 Sonnet scores 64.93% on SWE-bench Verified
Claude 3.7 Sonnet scores 66.4% on SWE-bench Verified
Claude 4.5 Haiku scores 66.6% on SWE-bench Verified
Claude 4 Sonnet scores 66.6% on SWE-bench Verified
claude-4-opus scores 67.6% on SWE-bench Verified
Multiple scores 68.2% on SWE-bench Verified
Multiple scores 70.2% on SWE-bench Verified
Claude 4 Sonnet scores 70.4% on SWE-bench Verified
Multiple scores 70.4% on SWE-bench Verified
Claude 4.5 Sonnet scores 70.6% on SWE-bench Verified
Claude 4 Sonnet scores 70.8% on SWE-bench Verified
Multiple scores 71.2% on SWE-bench Verified
Claude 4 Sonnet scores 71.2% on SWE-bench Verified
Claude 4.5 Sonnet scores 71.4% on SWE-bench Verified
Claude 4 Sonnet scores 72.4% on SWE-bench Verified
claude-4-opus scores 73.2% on SWE-bench Verified
Multiple scores 73.8% on SWE-bench Verified
Claude Opus 4.5 scores 74.4% on SWE-bench Verified
Multiple scores 74.4% on SWE-bench Verified
Multiple scores 74.6% on SWE-bench Verified
Claude 4 Sonnet scores 74.6% on SWE-bench Verified
Claude 4.5 Sonnet scores 74.8% on SWE-bench Verified
Claude Sonnet 4 scores 74.8% on SWE-bench Verified
Multiple scores 75.2% on SWE-bench Verified
Claude Opus 4.6 scores 75.6% on SWE-bench Verified
Multiple scores 75.6% on SWE-bench Verified
Multiple scores 76.4% on SWE-bench Verified
Claude Opus 4.5 scores 76.8% on SWE-bench Verified
Multiple scores 76.8% on SWE-bench Verified
Claude 4 Sonnet scores 76.8% on SWE-bench Verified
Claude Opus 4.5 scores 79.2% on SWE-bench Verified
Claude Opus 4.5 scores 79.2% on SWE-bench Verified
claude-2 scores 1.96% on SWE-bench (full test split)
claude-3-opus scores 3.79% on SWE-bench (full test split)
claude-3-opus scores 10.51% on SWE-bench (full test split)
claude-35-sonnet scores 18.13% on SWE-bench (full test split)
claude-3-5-sonnet-20241022 scores 24.89% on SWE-bench (full test split)
CodeAct v2.1 (claude-3-5-sonnet-20241022) scores 29.38% on SWE-bench (full test split)
Claude 3.7 Sonnet scores 33.83% on SWE-bench (full test split)
Multiple scores 44.25% on SWE-bench (full test split)
Claude Opus 4.5 scores 52.62% on SWE-bench (full test split)
Claude 4.5 Haiku scores 64.7% on SWE-bench Multilingual
Claude 4.5 Sonnet scores 67% on SWE-bench Multilingual
Claude Opus 4.5 scores 70.7% on SWE-bench Multilingual
Claude Opus 4.6 scores 72% on SWE-bench Multilingual
Claude Fable 5.1 Max Effort scores 72.988% on LiveBench
Claude Fable 5.1 Max Effort scores 89.501% on LiveBench
Claude Fable 5.1 Max Effort scores 80.276% on LiveBench
Claude Fable 5.1 Max Effort scores 97.007% on LiveBench
Claude Fable 5.1 Max Effort scores 66.061% on LiveBench
Claude Fable 5.1 Max Effort scores 86.375% on LiveBench
Claude Fable 5.1 Max Effort scores 91.692% on LiveBench
Claude Fable 5.1 Max Effort scores 83.414% on LiveBench
Claude 4.8 Opus Thinking Max Effort scores 72.034% on LiveBench
Claude 4.8 Opus Thinking Max Effort scores 79.659% on LiveBench
Claude 4.8 Opus Thinking Max Effort scores 66.033% on LiveBench
Claude 4.8 Opus Thinking Max Effort scores 94.317% on LiveBench
Claude 4.8 Opus Thinking Max Effort scores 50.505% on LiveBench
Claude 4.8 Opus Thinking Max Effort scores 81.828% on LiveBench
Claude 4.8 Opus Thinking Max Effort scores 89.192% on LiveBench
Claude 4.8 Opus Thinking Max Effort scores 76.224% on LiveBench
Claude Fable 5 xHigh Effort scores 75.771% on LiveBench
Claude Fable 5 xHigh Effort scores 90.684% on LiveBench
Claude Fable 5 xHigh Effort scores 80.538% on LiveBench
Claude Fable 5 xHigh Effort scores 95.986% on LiveBench
Claude Fable 5 xHigh Effort scores 62.172% on LiveBench
Claude Fable 5 xHigh Effort scores 85.992% on LiveBench
Claude Fable 5 xHigh Effort scores 89.654% on LiveBench
Claude Fable 5 xHigh Effort scores 82.971% on LiveBench
Claude Sonnet 5 xHigh Effort scores 63.858% on LiveBench
Claude Sonnet 5 xHigh Effort scores 74.97% on LiveBench
Claude Sonnet 5 xHigh Effort scores 71.741% on LiveBench
Claude Sonnet 5 xHigh Effort scores 92.942% on LiveBench
Claude Sonnet 5 xHigh Effort scores 59.394% on LiveBench
Claude Sonnet 5 xHigh Effort scores 80.68% on LiveBench
Claude Sonnet 5 xHigh Effort scores 88.692% on LiveBench
Claude Sonnet 5 xHigh Effort scores 76.04% on LiveBench
Claude 4.6 Opus Thinking High Effort scores 63.312% on LiveBench
Claude 4.6 Opus Thinking High Effort scores 83.27% on LiveBench
Claude 4.6 Opus Thinking High Effort scores 69.893% on LiveBench
Claude 4.6 Opus Thinking High Effort scores 89.317% on LiveBench
Claude 4.6 Opus Thinking High Effort scores 48.99% on LiveBench
Claude 4.6 Opus Thinking High Effort scores 78.184% on LiveBench
Claude 4.6 Opus Thinking High Effort scores 88.673% on LiveBench
Claude 4.6 Opus Thinking High Effort scores 74.52% on LiveBench
Claude Haiku 3.5 scores 2.27% on Terminal-Bench
Claude Haiku 3.5 scores 10.11% on Terminal-Bench
Claude Haiku 3.5 scores 24.56% on τ²-bench
Claude Haiku 3.5 scores 45.61% on MMMU-Pro
Claude Haiku 3.5 scores 42.79% on IFBench
Claude Haiku 3.5 scores 3.63% on Humanity's Last Exam
Claude Haiku 3.5 scores 40.81% on GPQA
Claude Haiku 3.5 scores 8.94 on Artificial Analysis Intelligence Index
claude-fable-5-1-low scores 85.02% on Terminal-Bench
claude-fable-5-1-low scores 40.4% on Terminal-Bench
claude-fable-5-1-low scores 56.71% on SciCode
claude-fable-5-1-low scores 48.89% on Humanity's Last Exam
claude-fable-5-1-low scores 88.08% on GPQA
claude-fable-5-1-low scores 47.04 on Artificial Analysis Intelligence Index
claude-35-sonnet scores 3.69% on Humanity's Last Exam
claude-35-sonnet scores 59.9% on GPQA
claude-35-sonnet scores 7.88 on Artificial Analysis Intelligence Index
claude-opus-5-xhigh scores 88.01% on Terminal-Bench
claude-opus-5-xhigh scores 46.46% on Terminal-Bench
claude-opus-5-xhigh scores 83.99% on MMMU-Pro
claude-opus-5-xhigh scores 55.67% on SciCode
claude-opus-5-xhigh scores 54.4% on Humanity's Last Exam
claude-opus-5-xhigh scores 93.74% on GPQA
claude-opus-5-xhigh scores 49.65 on Artificial Analysis Intelligence Index
claude-3-7-sonnet-thinking scores 21.21% on Terminal-Bench
claude-3-7-sonnet-thinking scores 54.68% on τ²-bench
claude-3-7-sonnet-thinking scores 48.3% on IFBench
claude-3-7-sonnet-thinking scores 9.67% on Humanity's Last Exam
claude-3-7-sonnet-thinking scores 77.17% on GPQA
claude-3-7-sonnet-thinking scores 17.71 on Artificial Analysis Intelligence Index
claude-sonnet-5-low scores 2.53% on Terminal-Bench
claude-sonnet-5-low scores 50.12% on SciCode
claude-sonnet-5-low scores 21.92% on Humanity's Last Exam
claude-sonnet-5-low scores 24.74 on Artificial Analysis Intelligence Index
Claude 3 Haiku scores 0.76% on Terminal-Bench
Claude 3 Haiku scores 21.05% on τ²-bench
Claude 3 Haiku scores 30.81% on MMMU-Pro
Claude 3 Haiku scores 36.12% on IFBench
Claude 3 Haiku scores 4.08% on Humanity's Last Exam
Claude 3 Haiku scores 5.58 on Artificial Analysis Intelligence Index
claude-opus-5-low scores 76.4% on Terminal-Bench
claude-opus-5-low scores 26.26% on Terminal-Bench
claude-opus-5-low scores 79.83% on MMMU-Pro
claude-opus-5-low scores 49.19% on SciCode
claude-opus-5-low scores 43.42% on Humanity's Last Exam
claude-opus-5-low scores 88.89% on GPQA
claude-opus-5-low scores 39.79 on Artificial Analysis Intelligence Index
Claude Sonnet 5 scores 80.52% on Terminal-Bench
Claude Sonnet 5 scores 14.14% on Terminal-Bench
Claude Sonnet 5 scores 77.28% on MMMU-Pro
Claude Sonnet 5 scores 54.28% on SciCode
Claude Sonnet 5 scores 41.29% on Humanity's Last Exam
Claude Sonnet 5 scores 91.11% on GPQA
Claude Sonnet 5 scores 38.36 on Artificial Analysis Intelligence Index
claude-opus-4-5-thinking scores 46.97% on Terminal-Bench
claude-opus-4-5-thinking scores 89.47% on τ²-bench
claude-opus-4-5-thinking scores 74.05% on MMMU-Pro
claude-opus-4-5-thinking scores 57.96% on IFBench
claude-opus-4-5-thinking scores 30.12% on Humanity's Last Exam
claude-opus-4-5-thinking scores 86.57% on GPQA
claude-opus-4-5-thinking scores 29.1 on Artificial Analysis Intelligence Index
Claude Sonnet 4.6 scores 46.21% on Terminal-Bench
Claude Sonnet 4.6 scores 79.53% on τ²-bench
Claude Sonnet 4.6 scores 70.58% on MMMU-Pro
Claude Sonnet 4.6 scores 41.16% on IFBench
Claude Sonnet 4.6 scores 13.35% on Humanity's Last Exam
Claude Sonnet 4.6 scores 79.9% on GPQA
Claude Sonnet 4.6 scores 24.69 on Artificial Analysis Intelligence Index
claude-opus-4-7-non-reasoning scores 54.55% on Terminal-Bench
claude-opus-4-7-non-reasoning scores 73.98% on τ²-bench
claude-opus-4-7-non-reasoning scores 76.36% on MMMU-Pro
claude-opus-4-7-non-reasoning scores 43.61% on IFBench
claude-opus-4-7-non-reasoning scores 33.32% on Humanity's Last Exam
claude-opus-4-7-non-reasoning scores 88.48% on GPQA
claude-opus-4-7-non-reasoning scores 30.93 on Artificial Analysis Intelligence Index
claude-fable-5-1-medium scores 88.01% on Terminal-Bench
claude-fable-5-1-medium scores 44.95% on Terminal-Bench
claude-fable-5-1-medium scores 56.37% on SciCode
claude-fable-5-1-medium scores 53.8% on Humanity's Last Exam
claude-fable-5-1-medium scores 88.59% on GPQA
claude-fable-5-1-medium scores 49.06 on Artificial Analysis Intelligence Index
Claude Fable 5.1 scores 91.39% on Terminal-Bench
Claude Fable 5.1 scores 52.02% on Terminal-Bench
Claude Fable 5.1 scores 63.08% on SciCode
Claude Fable 5.1 scores 59.13% on Humanity's Last Exam
Claude Fable 5.1 scores 93.74% on GPQA
Claude Fable 5.1 scores 53.37 on Artificial Analysis Intelligence Index
Claude Opus 4.5 scores 40.91% on Terminal-Bench
Claude Opus 4.5 scores 86.26% on τ²-bench
Claude Opus 4.5 scores 71.21% on MMMU-Pro
Claude Opus 4.5 scores 42.99% on IFBench
Claude Opus 4.5 scores 13.16% on Humanity's Last Exam
Claude Opus 4.5 scores 81.01% on GPQA
Claude Opus 4.5 scores 23.68 on Artificial Analysis Intelligence Index
Claude Opus 4.6 scores 48.48% on Terminal-Bench
Claude Opus 4.6 scores 84.8% on τ²-bench
Claude Opus 4.6 scores 72.54% on MMMU-Pro
Claude Opus 4.6 scores 44.63% on IFBench
Claude Opus 4.6 scores 19.09% on Humanity's Last Exam
Claude Opus 4.6 scores 84.04% on GPQA
Claude Opus 4.6 scores 26.35 on Artificial Analysis Intelligence Index
claude-4-opus scores 43.27% on IFBench
claude-4-opus scores 6.16% on Humanity's Last Exam
claude-4-opus scores 16.61 on Artificial Analysis Intelligence Index
claude-opus-4-6-adaptive scores 46.21% on Terminal-Bench
claude-opus-4-6-adaptive scores 92.11% on τ²-bench
claude-opus-4-6-adaptive scores 75.43% on MMMU-Pro
claude-opus-4-6-adaptive scores 53.13% on IFBench
claude-opus-4-6-adaptive scores 39.94% on Humanity's Last Exam
claude-opus-4-6-adaptive scores 89.6% on GPQA
claude-opus-4-6-adaptive scores 31.95 on Artificial Analysis Intelligence Index
claude-opus-5-high scores 87.64% on Terminal-Bench
claude-opus-5-high scores 45.96% on Terminal-Bench
claude-opus-5-high scores 82.43% on MMMU-Pro
claude-opus-5-high scores 55.44% on SciCode
claude-opus-5-high scores 52.83% on Humanity's Last Exam
claude-opus-5-high scores 93.74% on GPQA
claude-opus-5-high scores 48.24 on Artificial Analysis Intelligence Index
claude-3-opus scores 2.75% on Humanity's Last Exam
claude-3-opus scores 8.72 on Artificial Analysis Intelligence Index
claude-instant scores 3.53% on Humanity's Last Exam
claude-instant scores 5.03 on Artificial Analysis Intelligence Index
Claude Opus 4 scores 31.06% on Terminal-Bench
Claude Opus 4 scores 73.39% on τ²-bench
Claude Opus 4 scores 53.74% on IFBench
Claude Opus 4 scores 12.33% on Humanity's Last Exam
Claude Opus 4 scores 20.64 on Artificial Analysis Intelligence Index
claude-4-5-sonnet-thinking scores 35.61% on Terminal-Bench
claude-4-5-sonnet-thinking scores 55.81% on Terminal-Bench
claude-4-5-sonnet-thinking scores 0% on Terminal-Bench
claude-4-5-sonnet-thinking scores 78.07% on τ²-bench
claude-4-5-sonnet-thinking scores 68.73% on MMMU-Pro
claude-4-5-sonnet-thinking scores 57.28% on IFBench
claude-4-5-sonnet-thinking scores 45.72% on SciCode
claude-4-5-sonnet-thinking scores 17.79% on Humanity's Last Exam
claude-4-5-sonnet-thinking scores 83.43% on GPQA
claude-4-5-sonnet-thinking scores 21.18 on Artificial Analysis Intelligence Index
Claude Sonnet 4.5 scores 28.79% on Terminal-Bench
Claude Sonnet 4.5 scores 70.47% on τ²-bench
Claude Sonnet 4.5 scores 65.2% on MMMU-Pro
Claude Sonnet 4.5 scores 42.65% on IFBench
Claude Sonnet 4.5 scores 7.23% on Humanity's Last Exam
Claude Sonnet 4.5 scores 72.73% on GPQA
Claude Sonnet 4.5 scores 19.34 on Artificial Analysis Intelligence Index
Claude Opus 4.8 scores 58.33% on Terminal-Bench
Claude Opus 4.8 scores 84.64% on Terminal-Bench
Claude Opus 4.8 scores 21.72% on Terminal-Bench
Claude Opus 4.8 scores 94.44% on τ²-bench
Claude Opus 4.8 scores 62.24% on IFBench
Claude Opus 4.8 scores 54.4% on SciCode
Claude Opus 4.8 scores 48.66% on Humanity's Last Exam
Claude Opus 4.8 scores 92.02% on GPQA
Claude Opus 4.8 scores 41.99 on Artificial Analysis Intelligence Index
claude-sonnet-5-xhigh scores 7.07% on Terminal-Bench
claude-sonnet-5-xhigh scores 54.05% on SciCode
claude-sonnet-5-xhigh scores 39.02% on Humanity's Last Exam
claude-sonnet-5-xhigh scores 34.71 on Artificial Analysis Intelligence Index
claude-fable-5-1-xhigh scores 91.01% on Terminal-Bench
claude-fable-5-1-xhigh scores 55.05% on Terminal-Bench
claude-fable-5-1-xhigh scores 60.88% on SciCode
claude-fable-5-1-xhigh scores 58.71% on Humanity's Last Exam
claude-fable-5-1-xhigh scores 93.43% on GPQA
claude-fable-5-1-xhigh scores 53.18 on Artificial Analysis Intelligence Index
claude-fable-5-1-high scores 89.89% on Terminal-Bench
claude-fable-5-1-high scores 52.02% on Terminal-Bench
claude-fable-5-1-high scores 58.68% on SciCode
claude-fable-5-1-high scores 55.93% on Humanity's Last Exam
claude-fable-5-1-high scores 90.61% on GPQA
claude-fable-5-1-high scores 51.21 on Artificial Analysis Intelligence Index
claude-21 scores 3.89% on Humanity's Last Exam
claude-21 scores 5.59 on Artificial Analysis Intelligence Index
claude-4-5-haiku-reasoning scores 27.27% on Terminal-Bench
claude-4-5-haiku-reasoning scores 44.19% on Terminal-Bench
claude-4-5-haiku-reasoning scores 0% on Terminal-Bench
claude-4-5-haiku-reasoning scores 54.68% on τ²-bench
claude-4-5-haiku-reasoning scores 58.55% on MMMU-Pro
claude-4-5-haiku-reasoning scores 54.29% on IFBench
claude-4-5-haiku-reasoning scores 42.25% on SciCode
claude-4-5-haiku-reasoning scores 10.38% on Humanity's Last Exam
claude-4-5-haiku-reasoning scores 67.17% on GPQA
claude-4-5-haiku-reasoning scores 17.59 on Artificial Analysis Intelligence Index
claude-4-sonnet-thinking scores 31.06% on Terminal-Bench
claude-4-sonnet-thinking scores 36.33% on Terminal-Bench
claude-4-sonnet-thinking scores 64.62% on τ²-bench
claude-4-sonnet-thinking scores 61.79% on MMMU-Pro
claude-4-sonnet-thinking scores 54.69% on IFBench
claude-4-sonnet-thinking scores 10.7% on Humanity's Last Exam
claude-4-sonnet-thinking scores 77.68% on GPQA
claude-4-sonnet-thinking scores 18.92 on Artificial Analysis Intelligence Index
claude-35-sonnet-june-24 scores 3.23% on Humanity's Last Exam
claude-35-sonnet-june-24 scores 55.96% on GPQA
claude-35-sonnet-june-24 scores 7.21 on Artificial Analysis Intelligence Index
claude-3-sonnet scores 3.62% on Humanity's Last Exam
claude-3-sonnet scores 5.88 on Artificial Analysis Intelligence Index
Claude Opus 5 scores 89.14% on Terminal-Bench
Claude Opus 5 scores 48.99% on Terminal-Bench
Claude Opus 5 scores 84.74% on MMMU-Pro
Claude Opus 5 scores 56.37% on SciCode
Claude Opus 5 scores 54.87% on Humanity's Last Exam
Claude Opus 5 scores 50.7 on Artificial Analysis Intelligence Index
claude-sonnet-5-high scores 5.05% on Terminal-Bench
claude-sonnet-5-high scores 54.28% on SciCode
claude-sonnet-5-high scores 35.73% on Humanity's Last Exam
claude-sonnet-5-high scores 32.03 on Artificial Analysis Intelligence Index
Claude Haiku 4.5 scores 27.27% on Terminal-Bench
Claude Haiku 4.5 scores 32.46% on τ²-bench
Claude Haiku 4.5 scores 55.14% on MMMU-Pro
Claude Haiku 4.5 scores 42.04% on IFBench
Claude Haiku 4.5 scores 4.22% on Humanity's Last Exam
Claude Haiku 4.5 scores 64.65% on GPQA
Claude Haiku 4.5 scores 15.41 on Artificial Analysis Intelligence Index
claude-4-1-opus-thinking scores 34.34% on Terminal-Bench
claude-4-1-opus-thinking scores 71.37% on τ²-bench
claude-4-1-opus-thinking scores 67.92% on MMMU-Pro
claude-4-1-opus-thinking scores 55.44% on IFBench
claude-4-1-opus-thinking scores 12.47% on Humanity's Last Exam
claude-4-1-opus-thinking scores 80.9% on GPQA
claude-4-1-opus-thinking scores 22.85 on Artificial Analysis Intelligence Index
Claude Fable 5 scores 62.88% on Terminal-Bench
Claude Fable 5 scores 84.64% on Terminal-Bench
Claude Fable 5 scores 42.42% on Terminal-Bench
Claude Fable 5 scores 98.54% on τ²-bench
Claude Fable 5 scores 63.47% on IFBench
Claude Fable 5 scores 55.47% on Humanity's Last Exam
Claude Fable 5 scores 49.7 on Artificial Analysis Intelligence Index
Claude Sonnet 4 scores 27.27% on Terminal-Bench
Claude Sonnet 4 scores 52.34% on τ²-bench
Showing up to 400 events. Narrow by year or category, or use the changes feed for cursor-paged history. Times are UTC.