Timeline of SpaceXAI

grok-4-20-0309 scores 96.49% on τ²-bench

grok-4-20-0309 scores 73.18% on MMMU-Pro

grok-4-20-0309 scores 82.93% on IFBench

grok-4-20-0309 scores 32.39% on Humanity's Last Exam

grok-4-20-0309 scores 88.48% on GPQA

grok-4-20-0309 scores 25.22 on Artificial Analysis Intelligence Index

grok-build-0-1-06-16 scores 52.06% on Terminal-Bench

grok-build-0-1-06-16 scores 76.53% on MMMU-Pro

grok-build-0-1-06-16 scores 38.28% on Humanity's Last Exam

grok-build-0-1-06-16 scores 89.49% on GPQA

grok-build-0-1-06-16 scores 27.17 on Artificial Analysis Intelligence Index

grok-4-1-fast-reasoning scores 24.24% on Terminal-Bench

grok-4-1-fast-reasoning scores 93.27% on τ²-bench

grok-4-1-fast-reasoning scores 63.29% on MMMU-Pro

grok-4-1-fast-reasoning scores 52.72% on IFBench

grok-4-1-fast-reasoning scores 19.32% on Humanity's Last Exam

grok-4-1-fast-reasoning scores 85.25% on GPQA

grok-4-1-fast-reasoning scores 20.37 on Artificial Analysis Intelligence Index

grok-3 scores 11.36% on Terminal-Bench

grok-3 scores 48.83% on τ²-bench

grok-3 scores 46.94% on IFBench

grok-3 scores 4.12% on Humanity's Last Exam

grok-3 scores 69.29% on GPQA

grok-3 scores 12.11 on Artificial Analysis Intelligence Index

grok-4-6-medium scores 84.27% on Terminal-Bench

grok-4-6-medium scores 13.13% on Terminal-Bench

grok-4-6-medium scores 55.9% on SciCode

grok-4-6-medium scores 42.12% on Humanity's Last Exam

grok-4-6-medium scores 93.54% on GPQA

grok-4-6-medium scores 43.01 on Artificial Analysis Intelligence Index

grok-4-fast scores 12.12% on Terminal-Bench

grok-4-fast scores 63.74% on τ²-bench

grok-4-fast scores 48.09% on MMMU-Pro

grok-4-fast scores 37.69% on IFBench

grok-4-fast scores 4.54% on Humanity's Last Exam

grok-4-fast scores 60.61% on GPQA

grok-4-fast scores 11.06 on Artificial Analysis Intelligence Index

grok-4-1-fast scores 14.39% on Terminal-Bench

grok-4-1-fast scores 63.74% on τ²-bench

grok-4-1-fast scores 48.44% on MMMU-Pro

grok-4-1-fast scores 36.46% on IFBench

grok-4-1-fast scores 5.1% on Humanity's Last Exam

grok-4-1-fast scores 63.74% on GPQA

grok-4-1-fast scores 11.28 on Artificial Analysis Intelligence Index

grok-4-20-0309-non-reasoning scores 21.97% on Terminal-Bench

grok-4-20-0309-non-reasoning scores 69.59% on τ²-bench

grok-4-20-0309-non-reasoning scores 64.05% on MMMU-Pro

grok-4-20-0309-non-reasoning scores 47.82% on IFBench

grok-4-20-0309-non-reasoning scores 24.51% on Humanity's Last Exam

grok-4-20-0309-non-reasoning scores 78.48% on GPQA

grok-4-20-0309-non-reasoning scores 14.61 on Artificial Analysis Intelligence Index

grok-4-fast-reasoning scores 18.94% on Terminal-Bench

grok-4-fast-reasoning scores 65.79% on τ²-bench

grok-4-fast-reasoning scores 61.79% on MMMU-Pro

grok-4-fast-reasoning scores 50.54% on IFBench

grok-4-fast-reasoning scores 19.09% on Humanity's Last Exam

grok-4-fast-reasoning scores 84.75% on GPQA

grok-4-fast-reasoning scores 17.94 on Artificial Analysis Intelligence Index

grok-4-3-medium scores 30.3% on Terminal-Bench

grok-4-3-medium scores 91.23% on τ²-bench

grok-4-3-medium scores 75.84% on MMMU-Pro

grok-4-3-medium scores 83.33% on IFBench

grok-4-3-medium scores 29.98% on Humanity's Last Exam

grok-4-3-medium scores 88.99% on GPQA

grok-4-3-medium scores 24.78 on Artificial Analysis Intelligence Index

grok-4 scores 37.88% on Terminal-Bench

grok-4 scores 74.85% on τ²-bench

grok-4 scores 68.84% on MMMU-Pro

grok-4 scores 53.67% on IFBench

grok-4 scores 26.69% on Humanity's Last Exam

grok-4 scores 87.68% on GPQA

grok-4 scores 22.49 on Artificial Analysis Intelligence Index

grok-4-3-non-reasoning scores 18.94% on Terminal-Bench

grok-4-3-non-reasoning scores 34.08% on Terminal-Bench

grok-4-3-non-reasoning scores 0% on Terminal-Bench

grok-4-3-non-reasoning scores 65.79% on τ²-bench

grok-4-3-non-reasoning scores 64.8% on MMMU-Pro

grok-4-3-non-reasoning scores 47.62% on IFBench

grok-4-3-non-reasoning scores 39.35% on SciCode

grok-4-3-non-reasoning scores 6.77% on Humanity's Last Exam

grok-4-3-non-reasoning scores 65.76% on GPQA

grok-4-3-non-reasoning scores 14.54 on Artificial Analysis Intelligence Index

grok-beta scores 4.45% on Humanity's Last Exam

grok-beta scores 47.07% on GPQA

grok-beta scores 6.89 on Artificial Analysis Intelligence Index

grok-4-6-low scores 75.28% on Terminal-Bench

grok-4-6-low scores 3.03% on Terminal-Bench

grok-4-6-low scores 49.42% on SciCode

grok-4-6-low scores 27.62% on Humanity's Last Exam

grok-4-6-low scores 87.88% on GPQA

grok-4-6-low scores 35.41 on Artificial Analysis Intelligence Index

grok-4-6-xhigh scores 88.01% on Terminal-Bench

grok-4-6-xhigh scores 17.17% on Terminal-Bench

grok-4-6-xhigh scores 53.01% on SciCode

grok-4-6-xhigh scores 44.07% on Humanity's Last Exam

grok-4-6-xhigh scores 93.54% on GPQA

grok-4-6-xhigh scores 44.27 on Artificial Analysis Intelligence Index

grok-3-reasoning scores 10.36 on Artificial Analysis Intelligence Index

grok-4-3-low scores 26.52% on Terminal-Bench

grok-4-3-low scores 88.89% on τ²-bench

grok-4-3-low scores 72.77% on MMMU-Pro

grok-4-3-low scores 80.95% on IFBench

grok-4-3-low scores 18.35% on Humanity's Last Exam

grok-4-3-low scores 84.34% on GPQA

grok-4-3-low scores 24.3 on Artificial Analysis Intelligence Index

grok-3-mini-reasoning scores 17.42% on Terminal-Bench

grok-3-mini-reasoning scores 90.35% on τ²-bench

grok-3-mini-reasoning scores 45.85% on IFBench

grok-3-mini-reasoning scores 11.01% on Humanity's Last Exam

grok-3-mini-reasoning scores 79.09% on GPQA

grok-3-mini-reasoning scores 14.62 on Artificial Analysis Intelligence Index