A cross-benchmark capability estimate. Index points, not a percentage; intervals show uncertainty.
100140
gemma-2-27b
Gemma 2 27B · 95% interval 115.8–124.1
Model performance
Radar task score: four tests, equal weight. An experimental summary of these tasks, not a universal intelligence rating.
gemma-2-27b
Radar task score
/ 100
1/4 core tests · not enough evidence
1 benchmark results for this configuration
Scientific reasoning
GPQA Diamond · 25%
Expert-written science questions; strict multiple-choice scoring. Chance accuracy is 25%.
050100%
gemma-2-27b36.5*%Approx. 95% interval: 31.8–41.2% · Older result
Novel problem solving
Mystery Game Puzzles · 25%
Best-next-move puzzles in an undisclosed game variant. A narrow reasoning test, not general intelligence.
050100%
gemma-2-27bNot available
Advanced mathematics
FrontierMath Tiers 1-3 · 25%
Private v2 mathematics problems with Python tools. Earlier versions and Tier 4 are excluded.
050100%
gemma-2-27bNot available
Factual answers
SimpleQA Verified · 25%
Correct factual answers under a guessing prompt, graded by a model. Not a hallucination or abstention score.
050100%
gemma-2-27bNot available
Bars show reported task scores. Whiskers are approximate 95% intervals where standard errors are available. Different reasoning budgets are not equal-cost tests. Missing results are never zero.
Run it locally
Inference · memory estimate
gemma-2-27b
101.4 GiB checkpoint tensor payload · 27.23 B stored tensor elements · F32
Stored tensors can include buffers and repeated shared weights. A verified unique parameter count is unavailable. Checkpoint size is not the memory required to run the model.