Nano GPT logo
NanoGPT
Provider logo

Gemma 4 31B

google/gemma-4-31b-it
BackTry Model
Provider logo

Gemma 4 31B

google/gemma-4-31b-it
BackTry Model

Google's Gemma 4 31B instruction-tuned model for heavier reasoning, coding, agentic workflows, and long-context multimodal understanding. This route keeps tokenizer thinking disabled for faster direct answers.

Added Apr 2, 2026

Model weights

Context Window

262.1K

Max Output

131.1K

Input Price (Auto)

$0.100/1M

Output Price (Auto)

$0.34/1M

Cache Read (Auto)

$0.100/1M

Capabilities

Benchmarks

Performance metrics and benchmarks

Sourced from Artificial Analysis.

Intelligence Index

29.7

Better than 68% of models compared

Coding Index

43.4

Better than 55% of models compared

Agentic Index

14.4

Better than 40% of models compared

Reasoning

GPQA Diamond

Graduate-level scientific reasoning

85.7%

Better than 83% of models compared

HLE

Humanity's Last Exam

23.6%

Better than 79% of models compared

IFBench

Instruction-following benchmark

75.6%

Better than 93% of models compared

T²-Bench Telecom

Conversational AI agents in dual-control scenarios

59.9%

Better than 57% of models compared

AA-LCR

Long context reasoning evaluation

68.3%

Better than 76% of models compared

GDPval-AA

Economically valuable tasks

15.5%

CritPt

Research-level physics reasoning

1.4%

Coding

SciCode

Python programming for scientific computing

43.4%

Better than 80% of models compared

Terminal-Bench Hard

Agentic coding and terminal use

36.4%

Better than 83% of models compared

Knowledge

AA-Omniscience Accuracy

Proportion of correctly answered questions

20.0%

AA-Omniscience Hallucination Rate

Rate of incorrect answers among non-correct responses

85.0%

Last updated Aug 16, 2026

Artificial Analysis

Providers

Choose explicit providers for this model. Auto routing remains available as the default option.

Loading provider options…

Compare Gemma 4 31B with similar models from the same provider or model family.

Gemma 4 31B Thinking

google/gemma-4-31b-it:thinking

Google's Gemma 4 31B instruction-tuned model with thinking explicitly enabled, exposing reasoning traces for complex multimodal and coding workflows.

Gemma 4 26B A4B Uncensored

google/gemma-4-26b-a4b-uncensored

Gemma 4 26B A4B Uncensored is an FP8 open-weight multimodal mixture-of-experts model LoRA-tuned for fewer refusals across chat, coding, tool use, and long-context work.

Gemma 4 26B A4B

google/gemma-4-26b-a4b-it

Google's Gemma 4 26B A4B instruction-tuned model built for scalable reasoning, coding, long-context, and multimodal workflows. This route is tuned for faster direct answers while preserving multimodal and structured output support.

Gemma 4 26B A4B Thinking

google/gemma-4-26b-a4b-it:thinking

Google's Gemma 4 26B A4B instruction-tuned model with structured reasoning for more deliberate coding, multimodal analysis, and long-context problem solving.

Gemma 4 31B MeroMero v2

Gemma-4-31B-MeroMero-v2

Gemma 4 31B MeroMero v2 is a LoRA finetune for emotive dialogue, relationship scenes, creative writing, and multimodal roleplay.

Gemma 4 31B IT TEE

TEE/gemma-4-31b-it

Gemma 4 31B Instruct is a 30.7B dense model with a long context window, multilingual performance, function calling, and configurable reasoning. Running inside a TEE (Trusted Execution Environment), with provider attestation support.