Nex-N2-Pro
- Input
- —
- Output
- —
- Speed
- ~90tok/sest.
- Context
- 262Ktokens
Long-tail import from Artificial Analysis (2026-09-24); AA variant: Nex-N2-Pro (based on Qwen3.5-397B-A17B). Price = AA median host price.
Rankings
Coding
Verified#68 / 137rank by quality43.6±10.1quality / 1001/7 benchmarks measuredWriting & chat
Verified#58 / 162rank by quality58.7±9.5quality / 1001/5 benchmarks measuredHard reasoning
Verified#56 / 218rank by quality64.1±5.9quality / 1002/4 benchmarks measuredAgents
Verified#73 / 187rank by quality39.7±4.3quality / 1004/7 benchmarks measured
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
- 4× B200 180GB
- FP8 weights
- Throughput
- ~12,969 tok/s
- many requests batched
- Price
- $0.20–1.76 /M tok
- busy → light use
- On your own machine
- Mac Studio M5 Ultra 512GB (int4, ~99 tok/s single-stream)
- single consumer GPU or Mac
Assumptions (5)
- FP8 weights (397B params, 17B active per token) + 25% KV-cache headroom ≈ 496 GB
- 4× B200 180GB at $5.98–$14.24/GPU-hour on-demand (2026-09-24)
- ~12,969 output tok/s aggregate at batch 371 (bandwidth-bound); MoE compute scales with active params
- Blended 3:1 input:output; prefill ~250,147 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
~#14 of 21 (estimated)~73.1%
- #1Claude Opus 596.0%
- #2Claude Sonnet 585.2%
- #13Claude Haiku 4.573.3%
- ~#14Nex-N2-ProEstimated73.1%
- #14Nemotron 3.5 Super VL71.1%
No published score — estimated from related benchmarks
SWE-bench Pro (Public)Estimated
~#20 of 24 (estimated)~53.0%
- #1Claude Fable 5.293.0%
- #2Claude Opus 5.589.9%
- #18Gemini 3.5 Flash-Lite54.2%
- ~#20Nex-N2-ProEstimated53.0%
- #20Nemotron 3.5 Super VL51.8%
No published score — estimated from related benchmarks
DeepSWE v1.1Estimated
~#38 of 46 (estimated)~45.2%
- #1Gemini 4 Argon78.8%
- #2DeepSeek V4.1 Flash 101777.0%
- #37Qwen3.8 Max (0902)51.0%
- ~#38Nex-N2-ProEstimated45.2%
- #38Ripple-65B Preview44.3%
No published score — estimated from related benchmarks
Terminal-Bench 4.0Estimated
~#36 of 102 (estimated)~13.9%
- #1Kimi K3.1 Pro67.2%
- #2Claude Sonnet 5.563.6%
- #34DeepSeek V4 Pro (0813)14.1%
- ~#36Nex-N2-ProEstimated13.9%
- #36GPT-5.5 Instant (June 2026)12.6%
No published score — estimated from related benchmarks
LiveCodeBenchEstimated
~#15 of 28 (estimated)~70.0%
- #1Qwen3.8-Omni-Flash92.6%
- #2Qwen3.8 Flash-Next91.9%
- #14Maple-Preview75.1%
- ~#15Nex-N2-ProEstimated70.0%
- #15Mistral Small 464.0%
No published score — estimated from related benchmarks
SciCodeVerified
#68 of 11843.3%
- #1Claude Fable 5.267.7%
- #2Claude Opus 5.566.9%
- #66Step 3.7 Flash43.9%
- #68Nex-N2-Pro43.3%
- #69K2 Horizon 375B A23B42.9%
artificialanalysis.ai · 2026-09-24
AA Coding Agent IndexEstimated
~#23 of 26 (estimated)~34.6
- #1Claude Opus 5.561.7
- #2Claude Opus 559.7
- #22Claude Haiku 5.537.3
- ~#23Nex-N2-ProEstimated34.6
- #23Gemini 3.8 Flash33.3
No published score — estimated from related benchmarks
Writing & chat
IFBenchVerified
#47 of 13966.2%
- #1MiniMax-M382.9%
- #2Qwen3.8 2.4T A95B82.8%
- #46HyperNova 60B 260566.5%
- #47Nex-N2-Pro66.2%
- #47Nova 2.0 Omni66.2%
artificialanalysis.ai · 2026-09-24
LMArena Text, Non-English (Elo)Estimated
~#36 of 57 (estimated)~1413 Elo
- #1Gemini 4 ArgonFew votes1512
- #2Claude Opus 5.51497
- #35Muse GlimmerFew votes1418
- ~#36Nex-N2-ProEstimated1413
- #36MiMo-V2.51411
No published score — estimated from related benchmarks
LMArena Text (Elo)Estimated
~#36 of 57 (estimated)~1428 Elo
- #1Gemini 4 Argon1525
- #2Claude Opus 5.51507
- #35MiMo-V2.51434
- ~#36Nex-N2-ProEstimated1428
- #36Mistral Medium 3.51426
No published score — estimated from related benchmarks
EQ-Bench Creative Writing v3 (Elo)Estimated
~#13 of 26 (estimated)~1816 Elo
- #1GPT-6 Astra2173
- #2Claude Fable 5.12162
- #12Qwen3.8 2.4T A95B1843
- ~#13Nex-N2-ProEstimated1816
- #13Muse Glimmer1798
No published score — estimated from related benchmarks
Hard reasoning
GPQA DiamondVerified
#39 of 19289.2%
- #1GPT-6 Astra96.1%
- #2Gemini 3.8 Flash95.3%
- #38Qwen3.5 397B A17B89.3%
- #39Nex-N2-Pro89.2%
- #40Solar Pro 489.1%
artificialanalysis.ai · 2026-09-24
AIME (latest)Estimated
~#8 of 34 (estimated)~94.2%
- #1GLM-5.3 NVFP499.5%
- #2Beam 1.0 501B A23B97.7%
- #7Nova 2.0 Lite94.3%
- ~#8Nex-N2-ProEstimated94.2%
- #8gpt-oss-120b93.4%
No published score — estimated from related benchmarks
AA Intelligence IndexEstimated
~#39 of 103 (estimated)~29.9
- #1Gemini 4 Carbon59.4
- #2Claude Opus 5.557.6
- #38K2 Horizon 375B A23B30.5
- ~#39Nex-N2-ProEstimated29.9
- #39Gemini 3.1 Pro29.7
No published score — estimated from related benchmarks
Agents
τ²-bench (Telecom)Verified
#28 of 11981.6%
- #1Step 3.7 Flash98.5%
- #2DeepSeek-V4-Pro-0813-nvfp4-DSpark98.3%
- #26Nemotron 3 Ultra83.3%
- #28Nex-N2-Pro81.6%
- #28Qwen3.5 2B81.6%
artificialanalysis.ai · 2026-09-24
OSWorld-VerifiedEstimated
~#11 of 15 (estimated)~67.1%
- #1Kimi K384.8%
- #2Qwen3.8 27B84.3%
- #10Nex-N2.5-Mini71.2%
- ~#11Nex-N2-ProEstimated67.1%
- #11Muse Glimmer65.9%
No published score — estimated from related benchmarks
OSWorld 2.0Estimated
~last of 5 (estimated)below measured range (<47.5%)
No published score — estimated from related benchmarks
BrowseCompEstimated
~#19 of 22 (estimated)~66.5%
- #1Atria Dawn Preview92.5%
- #2GPT-6 Astra91.5%
- #18Nemotron 3.5 Bolt 74B-A9B70.0%
- ~#19Nex-N2-ProEstimated66.5%
- #19Mistral Medium 3.548.6%
No published score — estimated from related benchmarks
AutomationBench-AAVerified
#43 of 8417.6%
- #1Claude Fable 5.276.4%
- #2Muse Wonder Full71.3%
- #41MiMo-V2.518.4%
- #43Nex-N2-Pro17.6%
- #44Qwen3.7 Plus17.4%
artificialanalysis.ai · 2026-09-24