Skip to content
Model Pareto

Nex-N2.5-Mini

Nex AGIOpen weightshuggingface.co ↗
Input
$0.025/M tok
Output
$0.10/M tok
Blended
$0.044/M tok · 3:1
Speed
~110tok/sest.
Context
262Ktokens
Cost per task
~$0.04/taskest.

Rankings

Self-hostingEstimated

How we estimate →

What it would cost to run these open weights yourself on rented GPUs, compared with the API price above.

Hardware
1× H200 141GB
FP8 weights
Throughput
~8,390 tok/s
many requests batched
Price
$0.046–0.38 /M tok
busy → light use
On your own machine
RTX 5090 32GB (int4, 300+ tok/s single-stream)
single consumer GPU or Mac
Assumptions (5)
  • FP8 weights (35B params, 3B active per token) + 25% KV-cache headroom ≈ 44 GB
  • 1× H200 141GB at $3.59–$7.91/GPU-hour on-demand (2026-09-24)
  • ~8,390 output tok/s aggregate at batch 256 (bandwidth-bound); MoE compute scales with active params
  • Blended 3:1 input:output; prefill ~155,846 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

~#14 of 21 (estimated)~72.1%
  1. #1Claude Opus 596.0%
  2. #2Claude Sonnet 585.2%
  3. #13Claude Haiku 4.573.3%
  4. ~#14Nex-N2.5-MiniEstimated72.1%
  5. #14Nemotron 3.5 Super VL71.1%
No published score — estimated from related benchmarks
~#39 of 102 (estimated)~11.6%
  1. #1Kimi K3.1 Pro67.2%
  2. #2Claude Sonnet 5.563.6%
  3. #36Kimi K312.6%
  4. ~#39Nex-N2.5-MiniEstimated11.6%
  5. #39Qwen3.8 2.4T A95B11.1%
No published score — estimated from related benchmarks
SciCodeEstimated
~#46 of 119 (estimated)~49.5%
  1. #1Claude Fable 5.267.7%
  2. #2Claude Opus 5.566.9%
  3. #45Inkling Small49.7%
  4. ~#46Nex-N2.5-MiniEstimated49.5%
  5. #46Beam 1.0 501B A23B49.2%
No published score — estimated from related benchmarks
~#22 of 26 (estimated)~38.0
  1. #1Claude Opus 5.561.7
  2. #2Claude Opus 559.7
  3. #21Qwen3.8 Max (0902)39.2
  4. ~#22Nex-N2.5-MiniEstimated38.0
  5. #22Claude Haiku 5.537.3
No published score — estimated from related benchmarks

Agents

Not comparable across labs (1)

Kept for reference, not counted in rankings: these use a lab-specific task set, answer key or scoring, so scores can't be compared fairly across labs. Only published scores are shown.