DataLearner logo

Gemma 4 31BvsGLM-5

Across 5 shared benchmarks, GLM-5 leads overall: Gemma 4 31B wins 0, GLM-5 wins 5, with 0 ties and an average score difference of -9.83.

DeepMind
Gemma 4 31B

DeepMind · 2026-04-02 · Chat model

智谱AI
GLM-5

智谱AI · 2026-02-11 · Chat model

Gemma 4 31B0 wins(0%)(100%)5 winsGLM-5

Benchmark scores

Grouped by capability, sorted by largest gap within each. 5 shared benchmarks.

General Knowledge

GLM-5 3/3
BenchmarkGemma 4 31BGLM-5Diff
HLE26.5097 / 172Thinking (With Tools + Internet)50.4025 / 172-23.90
LiveBench61.6262 / 115Normal (No Tools)68.8543 / 115Normal (No Tools)-7.23
GPQA Diamond84.3058 / 187Thinking (No Tools)8648 / 187Thinking (No Tools)-1.70

Agent Level Benchmark

GLM-5 1/1
BenchmarkGemma 4 31BGLM-5Diff
τ²-Bench76.9020 / 43Thinking (With Tools)89.704 / 43-12.80

Math and Reasoning

GLM-5 1/1
BenchmarkGemma 4 31BGLM-5Diff
AIME 202689.2015 / 18Thinking (No Tools)92.709 / 18Thinking (No Tools)-3.50

Specs

FieldGemma 4 31BGLM-5
PublisherDeepMind智谱AI
Release date2026-04-022026-02-11
Model typeChat modelChat model
ArchitectureDenseMoE
Parameters30.7B744B
Context length256K200K
Max output32K128K

API pricing

Prices use DataLearner records when available; missing fields are not inferred.

ItemGemma 4 31BGLM-5
Text inputNot public$1 / 1M tokens
Text outputNot public$3.2 / 1M tokens
Cache writeNot public$0.2 / 1M tokens

One or both models have incomplete public pricing.

Summary

  • GLM-5leads in:General Knowledge (3/3), Agent Level Benchmark (1/1), Math and Reasoning (1/1)

On average across the 5 shared benchmarks, GLM-5 scores 9.83 higher.

Largest single-benchmark gap: HLE — Gemma 4 31B 26.50 vs GLM-5 50.40 (-23.90).

Page generated from structured model, pricing and benchmark records. No real-time LLM is used to write the prose.