Skip to content
Model Pareto

HyperNova 60B 2605

Multiverse ComputingOpen weightsartificialanalysis.ai ↗
Input
—
Output
—
Speed
~100tok/sest.
Context
131Ktokens

Long-tail import from Artificial Analysis (2026-09-24); AA variant: HyperNova 60B 2605 (high, based on gpt-oss-120b). Price = AA median host price.

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× B200 180GB
FP8 weights
Throughput
~9,539 tok/s
many requests batched
Price
$0.066–0.59 /M tok
busy → light use
On your own machine
Mac Studio M5 Max 128GB (int4, ~180 tok/s single-stream)
single consumer GPU or Mac
Assumptions (5)
  • FP8 weights (60B params, 4.8B active per token) + 25% KV-cache headroom ≈ 75 GB
  • 1× B200 180GB at $5.98–$14.24/GPU-hour on-demand (2026-09-24)
  • ~9,539 output tok/s aggregate at batch 256 (bandwidth-bound); MoE compute scales with active params
  • Blended 3:1 input:output; prefill ~221,484 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.

Writing & chat

Hard reasoning

Agents

~#12 of 15 (estimated)~59.5%
  1. #1Kimi K384.8%
  2. #2Qwen3.8 27B84.3%
  3. #11Muse Glimmer65.9%
  4. ~#12HyperNova 60B 2605Estimated59.5%
  5. #12Nemotron 3.5 Super VL NVFP452.3%
No published score — estimated from related benchmarks
OSWorld 2.0Estimated
~last of 5 (estimated)below measured range (<47.5%)
  1. #1GLM-5.3 Flash59.1%
  2. #2Kimi K358.3%
  3. #4GPT-5.547.5%
  4. ~#5HyperNova 60B 2605Estimated<47.5%
No published score — estimated from related benchmarks