ModelsCompareBest forBenchmarksStatusPricingAPI
Compare / head-to-head

Gemini 3.1 Pro PreviewvsGLM-5.2

Gemini 3.1 Pro Preview leads 5 of 7 shared benchmarks. GLM-5.2 is 2.4x cheaper per token. Gemini 3.1 Pro Preview has the larger context window (1.0M tokens).

Benchmarks from cited public sources; pricing from official pages; status from official provider feeds.

Shared benchmarks
5 – 2
Gemini 3.1 Pro Preview leads
Cheaper per token
GLM-5.2
2.4x cheaper, input + output
Larger context
Gemini 3.1 Pro Preview
1.0M tokens
Provider uptime (30d)
100% · —
Google · Z.ai
Gemini 3.1 Pro Preview
Google · released 2026-02-19
textvisionaudio
Context
1.0M
Max out
66K
Input /1M
$2
Output /1M
$12
Cached /1M
$0.2
Scores
10 · 8 core
GLM-5.2
Z.ai · released 2026-06-24
text
Context
1M
Max out
131K
Input /1M
$1.4
Output /1M
$4.4
Cached /1M
$0.26
Scores
26 · 9 core
Quality

Benchmark matrix

BenchmarkGemini 3.1 Pro PreviewGLM-5.2ΔEdge
Reported by both · 7
GPQA Diamond94.3% 91.9% epoch+2.4 ptGemini 3.1 Pro Preview
AIME 202698.3% matharena90% matharena+8.3 ptGemini 3.1 Pro Preview
FrontierMath Tier 4 v2 (Epoch AI run)26.8% epoch29.3% epoch-2.5 ptGLM-5.2
FrontierMath Tiers 1-3 v2 (Epoch AI run)59.6% epoch59.2% epoch+0.4 ptGemini 3.1 Pro Preview
OTIS Mock AIME 2024-2025 (Epoch AI run)95.6% epoch86.4% epoch+9.2 ptGemini 3.1 Pro Preview
SimpleQA Verified73.5% epoch34.2% epoch+39.3 ptGemini 3.1 Pro Preview
SWE-Bench Pro54.2% 62.1% -7.9 ptGLM-5.2
Only Gemini 3.1 Pro Preview reports · 2
LMArena Elo1480.1 not reported
ARC-AGI-277.1% not reported
Only GLM-5.2 reports · 18
Agents' Last Exam (ALE-CLI)not reported23.8%
AutomationBench v1.0.6not reported26.2%
CyberGymnot reported77.2%
DeepSWE v1.1not reported46.2%
ExploitBenchnot reported24.4%
ExploitGym 2hnot reported29
ExploitGym 6hnot reported39
FrontierSWEnot reported67.5%
GDPval-AA v2not reported1508
HLE (with tools)not reported54.7%
NL2Reponot reported48.9%
PostTrainBenchnot reported31.7%
ProgramBench (Almost Solved)not reported9.5%
SWE-bench Verified (Epoch AI run)not reported78.7% epoch
SWE-Marathon v1.1not reported19.4%
Terminal-Bench 2.1not reported81%
Terminal-Bench 3.0not reported4.6%
Toolathlon Verifiednot reported59.9%
Scores tagged "epoch" or "matharena" are independent runs, used only where the lab has not published its own; ⚠ marks rows MathArena flags as released after the competition. Higher is better on every row. Δ is Gemini 3.1 Pro Preview minus GLM-5.2 in the benchmark's own unit. "Not reported" means the lab has not published that figure; it is not a zero. ↗ opens the source.
Specs & pricing

Side by side

SpecGemini 3.1 Pro PreviewGLM-5.2Edge
Context window1.0M tokens1M tokensGemini 3.1 Pro Preview
Max output66K tokens131K tokensGLM-5.2
Input price / 1M$2 $1.4 GLM-5.2
Output price / 1M$12 $4.4 GLM-5.2
Cached input / 1M$0.2 $0.26 Gemini 3.1 Pro Preview
Input + output / 1M
Lower is cheaper. List prices; batch, tool and regional fees excluded.
$14$5.8GLM-5.2
Modalitiestext · vision · audiotextGemini 3.1 Pro Preview
Released2026-02-192026-06-24
Cited benchmark scores1026
Reliability

Provider status

All providers
More matchups

Gemini 3.1 Pro Preview vs …

More matchups

GLM-5.2 vs …

Built by Respan
Which one wins on your data?

Public benchmarks are a starting point. Run Gemini 3.1 Pro Preview and GLM-5.2 on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.