Skip to content
Model Pareto

Maple-Preview

DeepGroveOpen weightsnative ternaryhuggingface.co ↗
Input
—
Output
—
Speed
~120tok/sest.
Context
131Ktokens

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
1× H200 141GB
native ternary weights
Throughput
~16,365 tok/s
many requests batched
Price
$0.023–0.19 /M tok
busy → light use
On your own machine
RTX 5090 32GB (native ternary, 300+ tok/s single-stream)
single consumer GPU or Mac
Assumptions (5)
  • NATIVE TERNARY weights (20.2B params, 1.49B active per token) + 25% KV-cache headroom ≈ 5 GB
  • 1× H200 141GB at $3.59–$7.91/GPU-hour on-demand (2026-09-24)
  • ~16,365 output tok/s aggregate at batch 256 (bandwidth-bound); MoE compute scales with active params
  • Blended 3:1 input:output; prefill ~313,784 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

~#4 of 21 (estimated)~80.6%
  1. #1Claude Opus 596.0%
  2. #2Claude Sonnet 585.2%
  3. #3Beam 1.0 501B A23B81.6%
  4. ~#4Maple-PreviewEstimated80.6%
  5. #4Gemini 3.1 Pro80.6%
No published score — estimated from related benchmarks
~#8 of 24 (estimated)~66.1%
  1. #1Claude Fable 5.293.0%
  2. #2Claude Opus 5.589.9%
  3. #7Beam 1.0 501B A23B66.1%
  4. ~#8Maple-PreviewEstimated66.1%
  5. #8Hy4 preview65.7%
No published score — estimated from related benchmarks
DeepSWE v1.1Estimated
~#43 of 46 (estimated)~33.6%
  1. #1Gemini 4 Argon78.8%
  2. #2DeepSeek V4.1 Flash 101777.0%
  3. #42Nex-N2.5-Mini36.1%
  4. ~#43Maple-PreviewEstimated33.6%
  5. #43Hy328.0%
No published score — estimated from related benchmarks
~#24 of 102 (estimated)~31.6%
  1. #1Kimi K3.1 Pro67.2%
  2. #2Claude Sonnet 5.563.6%
  3. #22GLM-5.3 Flash32.8%
  4. ~#24Maple-PreviewEstimated31.6%
  5. #24DeepSeek V4.1 Flash26.8%
No published score — estimated from related benchmarks
SciCodeEstimated
~#36 of 119 (estimated)~53.1%
  1. #1Claude Fable 5.267.7%
  2. #2Claude Opus 5.566.9%
  3. #35MiniMax-M3.1-Flash53.4%
  4. ~#36Maple-PreviewEstimated53.1%
  5. #36Grok 4.653.0%
No published score — estimated from related benchmarks
~#11 of 26 (estimated)~51.0
  1. #1Claude Opus 5.561.7
  2. #2Claude Opus 559.7
  3. #10Muse Wonder52.0
  4. ~#11Maple-PreviewEstimated51.0
  5. #11GLM-5.348.9
No published score — estimated from related benchmarks

Hard reasoning