AI21 Labs

Provider prefix
AI21
Benchmark Record namespace
025

Table may be scrolled horizontally on narrow displays.

Record No. Model Benchmark Metric Score Eval Date Source Model ID
BR-025JAMBA15LARGE-001 Jamba 1.5 Large Artificial Analysis Intelligence Index Overall 5.1 Unknown Primary source AI21-JAMBA15LARGE
BR-025JAMBA15LARGE-002 Jamba 1.5 Large GPQA Diamond Accuracy 42.7% Unknown Primary source AI21-JAMBA15LARGE
BR-025JAMBA15LARGE-003 Jamba 1.5 Large Humanity's Last Exam No tools Overall 4% Unknown Primary source AI21-JAMBA15LARGE
BR-025JAMBA15LARGE-004 Jamba 1.5 Large SciCode Overall 16.3% Unknown Primary source AI21-JAMBA15LARGE
BR-025JAMBA15MINI-001 Jamba 1.5 Mini Artificial Analysis Intelligence Index Overall 2.7 Unknown Primary source AI21-JAMBA15MINI
BR-025JAMBA15MINI-002 Jamba 1.5 Mini GPQA Diamond Accuracy 30.2% Unknown Primary source AI21-JAMBA15MINI
BR-025JAMBA15MINI-003 Jamba 1.5 Mini Humanity's Last Exam No tools Overall 5.1% Unknown Primary source AI21-JAMBA15MINI
BR-025JAMBA15MINI-004 Jamba 1.5 Mini SciCode Overall 8% Unknown Primary source AI21-JAMBA15MINI
BR-025JAMBA16LARGE-001 Jamba 1.6 Large Artificial Analysis Intelligence Index Overall 5 Unknown Primary source AI21-JAMBA16LARGE
BR-025JAMBA16LARGE-002 Jamba 1.6 Large GPQA Diamond Accuracy 38.7% Unknown Primary source AI21-JAMBA16LARGE
BR-025JAMBA16LARGE-003 Jamba 1.6 Large Humanity's Last Exam No tools Overall 4% Unknown Primary source AI21-JAMBA16LARGE
BR-025JAMBA16LARGE-004 Jamba 1.6 Large SciCode Overall 18.4% Unknown Primary source AI21-JAMBA16LARGE
BR-025JAMBA16MINI-001 Jamba 1.6 Mini Artificial Analysis Intelligence Index Overall 2.6 Unknown Primary source AI21-JAMBA16MINI
BR-025JAMBA16MINI-002 Jamba 1.6 Mini GPQA Diamond Accuracy 30% Unknown Primary source AI21-JAMBA16MINI
BR-025JAMBA16MINI-003 Jamba 1.6 Mini Humanity's Last Exam No tools Overall 4.6% Unknown Primary source AI21-JAMBA16MINI
BR-025JAMBA16MINI-004 Jamba 1.6 Mini SciCode Overall 10.1% Unknown Primary source AI21-JAMBA16MINI
BR-025JAMBA17LARGE-001 Jamba 1.7 Large Artificial Analysis Intelligence Index Overall 5.3 Unknown Primary source AI21-JAMBA17LARGE
BR-025JAMBA17LARGE-002 Jamba 1.7 Large GPQA Diamond Accuracy 39% Unknown Primary source AI21-JAMBA17LARGE
BR-025JAMBA17LARGE-003 Jamba 1.7 Large Humanity's Last Exam No tools Overall 3.8% Unknown Primary source AI21-JAMBA17LARGE
BR-025JAMBA17LARGE-004 Jamba 1.7 Large SciCode Overall 18.8% Unknown Primary source AI21-JAMBA17LARGE
BR-025JAMBA17LARGE-005 Jamba 1.7 Large tau2-bench Overall 13.5% Unknown Primary source AI21-JAMBA17LARGE
BR-025JAMBA17LARGE-006 Jamba 1.7 Large Terminal-Bench Hard Overall 2.3% Unknown Primary source AI21-JAMBA17LARGE
BR-025JAMBA17LARGE-007 Jamba 1.7 Large CritPt Overall 0% Unknown Primary source AI21-JAMBA17LARGE
BR-025JAMBA17LARGE-008 Jamba 1.7 Large AA-Omniscience Overall -55.5 Unknown Primary source AI21-JAMBA17LARGE
BR-025JAMBA17LARGE-009 Jamba 1.7 Large AA-Omniscience Accuracy 19.7% Unknown Primary source AI21-JAMBA17LARGE
BR-025JAMBA17LARGE-010 Jamba 1.7 Large IFBench Overall 35.2% Unknown Primary source AI21-JAMBA17LARGE
BR-025JAMBA17LARGE-011 Jamba 1.7 Large AA-LCR Overall 17.3% Unknown Primary source AI21-JAMBA17LARGE
BR-025JAMBA17MINI-001 Jamba 1.7 Mini Artificial Analysis Intelligence Index Overall 2.7 Unknown Primary source AI21-JAMBA17MINI
BR-025JAMBA17MINI-002 Jamba 1.7 Mini GPQA Diamond Accuracy 32.2% Unknown Primary source AI21-JAMBA17MINI
BR-025JAMBA17MINI-003 Jamba 1.7 Mini Humanity's Last Exam No tools Overall 4.5% Unknown Primary source AI21-JAMBA17MINI
BR-025JAMBA17MINI-004 Jamba 1.7 Mini SciCode Overall 9.3% Unknown Primary source AI21-JAMBA17MINI
BR-025JAMBA17MINI-005 Jamba 1.7 Mini tau2-bench Overall 12.6% Unknown Primary source AI21-JAMBA17MINI
BR-025JAMBA17MINI-006 Jamba 1.7 Mini Terminal-Bench Hard Overall 0% Unknown Primary source AI21-JAMBA17MINI
BR-025JAMBA17MINI-007 Jamba 1.7 Mini CritPt Overall 0% Unknown Primary source AI21-JAMBA17MINI
BR-025JAMBA17MINI-008 Jamba 1.7 Mini AA-Omniscience Overall -74.2 Unknown Primary source AI21-JAMBA17MINI
BR-025JAMBA17MINI-009 Jamba 1.7 Mini AA-Omniscience Accuracy 11.4% Unknown Primary source AI21-JAMBA17MINI
BR-025JAMBA17MINI-010 Jamba 1.7 Mini IFBench Overall 31.4% Unknown Primary source AI21-JAMBA17MINI
BR-025JAMBA17MINI-011 Jamba 1.7 Mini AA-LCR Overall 12.7% Unknown Primary source AI21-JAMBA17MINI
BR-025JAMBAREASONING3B-001 Jamba Reasoning 3B Artificial Analysis Intelligence Index Overall 4.1 Unknown Primary source AI21-JAMBAREASONING3B
BR-025JAMBAREASONING3B-002 Jamba Reasoning 3B GPQA Diamond Accuracy 33.3% Unknown Primary source AI21-JAMBAREASONING3B
BR-025JAMBAREASONING3B-003 Jamba Reasoning 3B Humanity's Last Exam No tools Overall 4.6% Unknown Primary source AI21-JAMBAREASONING3B
BR-025JAMBAREASONING3B-004 Jamba Reasoning 3B SciCode Overall 5.9% Unknown Primary source AI21-JAMBAREASONING3B
BR-025JAMBAREASONING3B-005 Jamba Reasoning 3B tau2-bench Overall 15.8% Unknown Primary source AI21-JAMBAREASONING3B
BR-025JAMBAREASONING3B-006 Jamba Reasoning 3B Terminal-Bench Hard Overall 0.8% Unknown Primary source AI21-JAMBAREASONING3B
BR-025JAMBAREASONING3B-007 Jamba Reasoning 3B CritPt Overall 0% Unknown Primary source AI21-JAMBAREASONING3B
BR-025JAMBAREASONING3B-008 Jamba Reasoning 3B AA-Omniscience Overall -73.7 Unknown Primary source AI21-JAMBAREASONING3B
BR-025JAMBAREASONING3B-009 Jamba Reasoning 3B AA-Omniscience Accuracy 6.6% Unknown Primary source AI21-JAMBAREASONING3B
BR-025JAMBAREASONING3B-010 Jamba Reasoning 3B IFBench Overall 52.4% Unknown Primary source AI21-JAMBAREASONING3B
BR-025JAMBAREASONING3B-011 Jamba Reasoning 3B AA-LCR Overall 7% Unknown Primary source AI21-JAMBAREASONING3B