← All benchmarks
Tau2 (average over 3)
Customer-service style tasks where the model uses tools and follows policies over a conversation with a simulated user.
- 1Gemma 4 31B · Google76.9%
How each maker reported it
- Gemma 4 31B Benchmark results
Instruction-tuned models, as published in Google's model card. OmniDocBench is edit distance (lower is better). Audio benchmarks are omitted because 31B has no audio input.
Only each model's own maker's number is shown; scores a maker reports for rival models are left out.