MBZUAI Institute of Foundation Models
Updated 2 h ago · first seen 11 Sept 2026
company_01M29A5B63YS0NP7EFFK0H3Y28
Specification
No structured attributes yet.
Each value shows its source, tier and observation time. Conflicting claims are kept side by side and flagged — never averaged. How AI Atlas records facts →
Provenance
Attributed facts
0
Source tiers
—
Freshest observation
—
Conflicts
None
Papers 0
No papers linked yet.
Repositories 0
No repositories linked yet.
| Model | Params | Context | Openness | Released | Status | Quality |
|---|---|---|---|---|---|---|
| k2-v2-medium | — | 512K | open-weights | — | active | 44 |
| k2-v2-low | — | 512K | open-weights | — | active | 44 |
| k2-horizon-375b-a23b | — | 524.3K | open-weights | — | active | 44 |
| k2-v2 | — | 512K | open-weights | — | active | 44 |
| k2-think-v2 | — | 262.1K | open-weights | — | active | 44 |
No relations recorded.
No repositories linked yet.
As of
Rewind the record: see this entity's attributes exactly as AI Atlas knew them on a given day.
Claim history
No claims recorded yet
New model: k2-think-v2 (MBZUAI Institute of Foundation Models)
artificial_analysisNew model: k2-v2 (MBZUAI Institute of Foundation Models)
artificial_analysisNew model: k2-horizon-375b-a23b (MBZUAI Institute of Foundation Models)
artificial_analysisNew model: k2-v2-low (MBZUAI Institute of Foundation Models)
artificial_analysisNew model: k2-v2-medium (MBZUAI Institute of Foundation Models)
artificial_analysisNew company: MBZUAI Institute of Foundation Models
artificial_analysisk2-think-v2 scores 6.82% on Terminal-Bench
artificial_analysisk2-think-v2 scores 14.98% on Terminal-Bench
artificial_analysisk2-think-v2 scores 25.44% on τ²-bench
artificial_analysisk2-think-v2 scores 62.79% on IFBench
artificial_analysisk2-think-v2 scores 10.1% on Humanity's Last Exam
artificial_analysisk2-think-v2 scores 71.31% on GPQA
artificial_analysisk2-think-v2 scores 11.5 on Artificial Analysis Intelligence Index
artificial_analysisk2-v2 scores 9.85% on Terminal-Bench
artificial_analysisk2-v2 scores 27.78% on τ²-bench
artificial_analysisk2-v2 scores 60.14% on IFBench
artificial_analysisk2-v2 scores 10.52% on Humanity's Last Exam
artificial_analysisk2-v2 scores 68.08% on GPQA
artificial_analysisk2-v2 scores 9.87 on Artificial Analysis Intelligence Index
artificial_analysisk2-horizon-375b-a23b scores 71.91% on Terminal-Bench
artificial_analysisk2-horizon-375b-a23b scores 42.94% on SciCode
artificial_analysisk2-horizon-375b-a23b scores 31.97% on Humanity's Last Exam
artificial_analysisk2-horizon-375b-a23b scores 87.27% on GPQA
artificial_analysisk2-horizon-375b-a23b scores 30.7 on Artificial Analysis Intelligence Index
artificial_analysisk2-v2-low scores 4.55% on Terminal-Bench
artificial_analysisk2-v2-low scores 20.76% on τ²-bench
artificial_analysisk2-v2-low scores 40.95% on IFBench
artificial_analysisk2-v2-low scores 3.61% on Humanity's Last Exam
artificial_analysisk2-v2-low scores 54.14% on GPQA
artificial_analysisk2-v2-low scores 7.31 on Artificial Analysis Intelligence Index
artificial_analysis
No documents recorded