Google: functiongemma-270m-it
7 benchmarks
Leaderboard position
#1087
Overall rank (of 1121 models)
-579
Elo rating
7
Benchmarks
Top 97.0%
Percentile
In Google (of 72 models)
Above: AI21: jamba-1.6-mini #1086
Below: LiquidAI: lfm-2-8b-a1b #1088
Benchmark highlights
Best benchmark
WinoGrande
53.1176
Worst benchmark
WikiText-2 (-ppl)
-109.8192
Nearest competitor from another company
The model from another company with the most similar benchmark scores.
appeared as nearest in 1 of 7 benchmarks
1/7
14.3%
1/7
14.3%
1/7
14.3%
1/7
14.3%
1/7
14.3%
1/7
14.3%
| Model | Votes | % of benchmarks |
|---|---|---|
| raincandy-u: rain-100m | 1 | 14.3% |
| Technology Innovation Institute: Falcon H1 Tiny 90M Instruct | 1 | 14.3% |
| Sapbot: Grok 4 Distill SmolLM2 135M | 1 | 14.3% |
| Qwen: qwen2.5-math-1.5b-instruct | 1 | 14.3% |
| NVIDIA Corporation: locateanything-3b | 1 | 14.3% |
| Mistral AI: devstral-small-2505 | 1 | 14.3% |
| pleias: baguettotron | 1 | 14.3% |
Benchmarks
Predicted scores
Estimated from 25 similar models and the global Elo rating. These are projections, not measured results.