ModelsCompareBest forBenchmarksStatusPricingAPI
Compare / head-to-head

GLM-5.3-FlashvsNVIDIA Nemotron 3 Super 120B-A12B

GLM-5.3-Flash leads 1 of 1 shared benchmark. Both offer a 1M-token context window.

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

Shared benchmarks
1 – 0
GLM-5.3-Flash leads
Cheaper per token
list price, input + output
Larger context
Tie
both 1M tokens
Provider uptime (30d)
— · 100%
Z.ai · NVIDIA
GLM-5.3-Flash
Z.ai · released 2026-09-16
textvision
Context
1M
Max out
131K
Input /1M
$0.15
Output /1M
$0.5
Cached /1M
$0.03
Scores
19 · 6 core
NVIDIA Nemotron 3 Super 120B-A12B
NVIDIA · released 2026-03-11
text
Context
1M
Max out
Input /1M
Output /1M
Cached /1M
Scores
10 · 8 core
Quality

Benchmark matrix

BenchmarkGLM-5.3-FlashNVIDIA Nemotron 3 Super 120B-A12BΔEdge
Reported by both · 1
LMArena Elo1471.9 1377.9 +94GLM-5.3-Flash
Only GLM-5.3-Flash reports · 18
GPQA Diamond90.2% epochnot reported
Agents' Last Exam (ALE-CLI)26.3% not reported
AutomationBench v1.0.648.8% not reported
BabyVision53.4% not reported
Chartography (with tools)78% not reported
CharXiv Reasoning (with tools)89.4% not reported
DeepSWE v1.163.4% not reported
FrontierMath Tier 4 v2 (Epoch AI run)17.1% epochnot reported
FrontierMath Tiers 1-3 v2 (Epoch AI run)55.8% epochnot reported
GDPval-AA v21773 not reported
HLE (with tools)55.3% not reported
MMVU80.5% not reported
MVBench77.8% not reported
NL2Repo56.3% not reported
OfficeQA Pro62.4% not reported
OTIS Mock AIME 2024-2025 (Epoch AI run)93.9% epochnot reported
Terminal-Bench 2.184.3% not reported
Toolathlon Verified78.4% not reported
Only NVIDIA Nemotron 3 Super 120B-A12B reports · 9
SWE-bench Verifiednot reported60.47%
MMLU-Pronot reported83.73%
AIME 2025not reported90.21%
Humanity's Last Exam (no tools)not reported18.26%
GPQA (no tools)not reported79.23%
GPQA (with tools)not reported82.7%
Humanity's Last Exam (with tools)not reported22.82%
LiveCodeBenchnot reported81.19%
Terminal-Bench Core 2.0not reported31%
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 GLM-5.3-Flash minus NVIDIA Nemotron 3 Super 120B-A12B 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

SpecGLM-5.3-FlashNVIDIA Nemotron 3 Super 120B-A12BEdge
Context window1M tokens1M tokensTie
Max output131K tokens
Input price / 1M$0.15
Output price / 1M$0.5
Cached input / 1M$0.03
Input + output / 1M
Lower is cheaper. List prices; batch, tool and regional fees excluded.
$0.65
Modalitiestext · visiontextGLM-5.3-Flash
Released2026-09-162026-03-11
Cited benchmark scores1910
Reliability

Provider status

All providers
More matchups

GLM-5.3-Flash vs …

Built by Respan
Which one wins on your data?

Public benchmarks are a starting point. Run GLM-5.3-Flash and NVIDIA Nemotron 3 Super 120B-A12B on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.