Gemini 3.1 Pro vs GLM-5.2

Verdict

Gemini 3.1 Pro leads 9–5 across 14 shared benchmarks.

Gemini 3.1 Pro 9 · GLM-5.2 5 · higher isn't always better — see caveats.

Per-benchmark head-to-head

Gemini 3.1 ProGLM-5.2

33.5
APEX-Agents
35.6
98
ARC-AGI
77
77.1
ARC-AGI-2
22.78
55
Chess Puzzles
21
17.71
CritPt
20.86
26.83
FrontierMath-Tier-4-v2-Private
29.27
59.65
FrontierMath-Tiers-1-3-v2-Private
59.21
0.85
GBAEval
0.02
92.13
GPQA diamond
89.14
95.6
OTIS Mock AIME 2024-2025
86.38
21.59
PostTrainBench
34.29
77.3
SimpleQA Verified
38.1
75.62
SWE-Bench verified
78.7
72.1
WeirdML
70.12

A higher number is not always a better model. Each score is task performance under a disclosed harness, and some of these benchmarks are saturated or scored under mixed harnesses. Follow any benchmark to its integrity grade before reading a win as decisive.

Follow the record

Per-benchmark head-to-head

Follow the record

These models

Gemini 3.1 Pro vs …

GLM-5.2 vs …

Per-benchmark head-to-head

Follow the record

These models

Gemini 3.1 Pro vs …

GLM-5.2 vs …