Skip to content
Model Pareto

GLM-5.3 NVFP4

NVIDIAOpen weightsNVFP4quantized from GLM-5.3huggingface.co ↗
Compare with nearest rivalsCompare with…
Input
—
Output
—
Speed
~140tok/sest.
Context
1Mtokens

Rankings

Self-hostingEstimated

How we estimate →

What it would cost to run these open weights yourself on rented GPUs. No API sells this model, so this is its price on the chart.

Hardware
8× H200 141GB
NVFP4 weights
Throughput
~16,000 tok/s
many requests batched
Price
$0.25–2.08 /M tok
busy → light use
On your own machine
Too large
needs data-center GPUs
Assumptions (5)
  • NVFP4 weights (744B params, 40B active per token) + 40% KV-cache headroom ≈ 586 GB
  • 8× H200 141GB at $3.59–$7.91/GPU-hour on-demand (2026-09-24)
  • ~16,000 output tok/s aggregate at batch 575 (bandwidth-bound); MoE compute scales with active params
  • Blended 3:1 input:output; prefill ~93,508 tok/s
  • Low = 75% utilization at the low GPU price; high = 20% at the high price

Benchmark scores

~ italic, dashed = no published score yet, estimated from related benchmarks.

Coding

SWE-bench VerifiedEstimated
~#2 of 14 (estimated)~88.0%
  1. #1Claude Opus 596.0%
  2. ~#2GLM-5.3 NVFP4Estimated88.0%
  3. #2Claude Sonnet 585.2%
No published score — estimated from related benchmarks
SWE-bench Pro (Public)Estimated
~#5 of 19 (estimated)~71.4%
  1. #1Claude Opus 5.589.9%
  2. #2Claude Sonnet 5.581.3%
  3. #4Claude Opus 579.2%
  4. ~#5GLM-5.3 NVFP4Estimated71.4%
  5. #5Intern-S2-397B68.5%
No published score — estimated from related benchmarks
DeepSWE v1.1Estimated
~#20 of 32 (estimated)~63.4%
  1. #1GPT-6.1 Sol75.2%
  2. #2DeepSeek V4.1 Flash74.2%
  3. #19GPT-6 Luna63.7%
  4. ~#20GLM-5.3 NVFP4Estimated63.4%
  5. #20GLM-5.3 Flash63.4%
No published score — estimated from related benchmarks
Terminal-Bench 4.0Estimated
~#15 of 85 (estimated)~27.3%
  1. #1Claude Sonnet 5.563.6%
  2. #2Claude Opus 5.559.6%
  3. #14GLM-5.3 Flash32.8%
  4. ~#15GLM-5.3 NVFP4Estimated27.3%
  5. #15DeepSeek V4.1 Flash26.8%
No published score — estimated from related benchmarks
AA Coding Agent IndexEstimated
~#6 of 15 (estimated)~56.5
  1. #1Claude Opus 5.566.0
  2. #2Claude Fable 5.162.2
  3. #5GPT-6 Sol56.7
  4. ~#6GLM-5.3 NVFP4Estimated56.5
  5. #6Grok 4.756.3
No published score — estimated from related benchmarks

Writing & chat

MMMLUEstimated
~#3 of 5 (estimated)~87.7%
  1. #1Gemini 3.1 Pro92.6%
  2. #2Gemma 4 31B88.4%
  3. ~#3GLM-5.3 NVFP4Estimated87.7%
  4. #3Claude Haiku 4.583.0%
No published score — estimated from related benchmarks
LMArena Text, Non-English (Elo)Estimated
~#20 of 54 (estimated)~1446 Elo
  1. #1Claude Opus 5.51501
  2. #2Claude Fable 5.1Few votes1496
  3. #18Grok 4.61447
  4. ~#20GLM-5.3 NVFP4Estimated1446
  5. #20Gemini 3.5 Flash-Lite1445
No published score — estimated from related benchmarks
LMArena Text (Elo)Estimated
~#18 of 54 (estimated)~1458 Elo
  1. #1Claude Opus 5.51509
  2. #2Claude Fable 5.11501
  3. #17Claude Sonnet 51461
  4. ~#18GLM-5.3 NVFP4Estimated1458
  5. #18GPT-6 Sol1457
No published score — estimated from related benchmarks
EQ-Bench Creative Writing v3 (Elo)Estimated
~#9 of 26 (estimated)~1988 Elo
  1. #1GPT-6 Astra2173
  2. #2Claude Fable 5.12162
  3. #8Grok 4.72007
  4. ~#9GLM-5.3 NVFP4Estimated1988
  5. #9Muse Spark 1.31906
No published score — estimated from related benchmarks

Hard reasoning

Humanity's Last ExamEstimated
~#44 of 182 (estimated)~29.7%
  1. #1Claude Opus 5.561.4%
  2. #2Claude Fable 5.159.1%
  3. #43Inkling31.9%
  4. ~#44GLM-5.3 NVFP4Estimated29.7%
  5. #44A.X-K229.6%
No published score — estimated from related benchmarks
AA Intelligence IndexEstimated
~#27 of 78 (estimated)~33.1
  1. #1Claude Opus 5.557.6
  2. #2Claude Sonnet 5.556.0
  3. #26Qwen3.8 27B33.7
  4. ~#27GLM-5.3 NVFP4Estimated33.1
  5. #27K2 Horizon 375B A23B30.5
No published score — estimated from related benchmarks