NexReleased Jun 8, 2026
Open weights

nex-n2-pro

Strongest in Computer Use (#43 of 186) and Academic Reasoning (#82 of 228); weakest in Reliability (#105 of 188). Three of seven dimensions are estimated, because no results are published yet.

Composite IQ ?
109
#94 of 186 ranked models · ahead of 50%
China (Other)'s #5 model, behind Ling 3.1 Flash (120)
Effective cost
$2.97/1M
$0.50 in · $2.50 out
Speed
99tok/s
27s typical response
Context
262Ktokens
262,144 tokens in
Evidence
4of 7 dims
12 of 39 benchmarks

IQ profile

Seven dimensions, averaged equally into Composite IQ
Compare shape with
100 avg human130160● Abstract86#148 · est.● Math103#125 · est.● Academic125#82● Coding100#130 · est.● Computer Use122#43● Reliability111#105● Knowledge Work114#68
MeasuredEstimated95% range
#1 in dimensionTop-10 median

IQ dimensions

Ranks are among models scored in each dimension. Ranges are model-based estimates, not calibrated confidence intervals.

DimensionIQPosition · 70–160RankEvidencevs Top 10
86estimated
#148 / 226
0/5
-46.5
103estimated
#125 / 186
0/5
-46.5
125measured
#82 / 228
4/6
-10
100estimated
#130 / 187
0/6
-51
122measured
#43 / 186
1/5
-24.5
111measured
#105 / 188
3/6
-24.5
114measured
#68 / 186
4/6
-18
nex-n2-pro95% range (model-based, uncalibrated)Top-10 median#1 in dimension100 = average human

Benchmark results

12 of 39 Composite IQ benchmarks have a published result for nex-n2-pro. Benchmarks without a result stay listed so gaps are visible.

Abstract Reasoning IQ 86 · estimatedNo published results0/5
No published results yet for Abstract Reasoning. The 86 shown is estimated from nex-n2-pro's other dimensions and will be replaced as results come in. How estimates work
ARC-AGI-3ARC-AGI-2ARC-AGI-1Chess PuzzlesMystery Game Puzzles
Mathematical Reasoning IQ 103 · estimatedNo published results0/5
No published results yet for Mathematical Reasoning. The 103 shown is estimated from nex-n2-pro's other dimensions and will be replaced as results come in. How estimates work
FrontierMath Tier 4FrontierMath Tier 1-3ProofBench 1.1MathArenaAIME
Academic Reasoning IQ 125 · measuredBest: #55 of 147 on GPQA Diamond4/6
BenchmarkScorePercentileRankLeader · source
GPQA Diamond
Artificial Analysis v5.0.1 · Nov 13
89.2%
#55 / 147
Leader gpt-6-astra · 96.1%
Artificial Analysis v5.0.1 · Nov 13
Humanity's Last Exam
Artificial Analysis v4.3.2 · Oct 27
33.7%
#73 / 167
Leader opus-5.5 · 61.4%
Artificial Analysis v4.3.2 · Oct 27
CritPt
Artificial Analysis v4.3.2 · Oct 27
8.6%
#70 / 159
Leader Muse Wonder Full · 32.9%
Artificial Analysis v4.3.2 · Oct 27
SciCode
Artificial Analysis v4.3.2 · Oct 27
43.3%
#98 / 167
Leader opus-5.5 · 66.9%
Artificial Analysis v4.3.2 · Oct 27
Not yet reported
MMLU-ProMMMU-Pro
Programmatic Reasoning IQ 100 · estimatedNo published results0/6
No published results yet for Programmatic Reasoning. The 100 shown is estimated from nex-n2-pro's other dimensions and will be replaced as results come in. How estimates work
LiveCodeBenchIOI V2Terminal-Bench 4.0ProgramBenchSWE-rebenchMirrorCode
Computer Use IQ 122 · measuredBest: #16 of 45 on BrowseComp1/5
BenchmarkScorePercentileRankLeader · source
BrowseComp
LLM Stats BrowseComp · Sep 22
83.7%
#16 / 45
Leader Kimi K3.1 Pro · 92.1%
LLM Stats BrowseComp · Sep 22
Not yet reported
OSWorld-VerifiedMCP AtlasArena.ai Agent ArenaAgents' Last Exam
Reliability IQ 111 · measuredBest: #33 of 154 on AA Long Context Reasoning v1.13/6
BenchmarkScorePercentileRankLeader · source
AA Long Context Reasoning v1.1
Artificial Analysis v4.3.2 · Oct 27
81.7%
#33 / 154
Leader kimi-k3 · 88.7%
Artificial Analysis v4.3.2 · Oct 27
IFBench
Artificial Analysis v5.0.1 · Nov 13
66.2%
#59 / 96
Leader minimax-m3 · 82.9%
Artificial Analysis v5.0.1 · Nov 13
AA Omniscience
Artificial Analysis v4.3.2 · Oct 27
-27.0
#120 / 158
Leader opus-5.5 · 46.4
Artificial Analysis v4.3.2 · Oct 27
Not yet reported
SimpleQA VerifiedBullshitBench v2FACTS Grounding
Knowledge Work IQ 114 · measuredBest: #53 of 111 on GDP.pdf4/6
BenchmarkScorePercentileRankLeader · source
GDP.pdf
Artificial Analysis v5.0.1 · Nov 13
12.6%
#53 / 111
Leader Muse Wonder Full · 32.6%
Artificial Analysis v5.0.1 · Nov 13
GDPval-AA v2.1 normalized score
Artificial Analysis v4.3.2 · Oct 23
30.2%
#62 / 124
Leader opus-5.5 · 68.3%
Artificial Analysis v4.3.2 · Oct 23
AA-Briefcase v1.1 Elo
Artificial Analysis v5.0.1 · Nov 13
940
#61 / 116
Leader sonnet-5.5 · 1,816
Artificial Analysis v5.0.1 · Nov 13
AutomationBench-AA
Artificial Analysis v5.0.1 · Nov 13
17.6%
#65 / 112
Leader Gemini 4 Carbon · 77.8%
Artificial Analysis v5.0.1 · Nov 13
Not yet reported
AA-AnalystAgentEnterpriseOps-Gym-AA

Release & availability

Release details on record for this model.

Released
Developer
Nex
Weights
Open weightsDownloadable and self-hostable
Context
262,144 tokens
API price
$0.50 in · $2.50 outper 1M tokens · full pricing

About this score

How much of nex-n2-pro's IQ is measured, and how the rest is estimated.

12/ 39benchmark results
4/ 7dimensions measured
3estimated
0/5Abstract
0/5Math
4/6Academic
0/6Coding
1/5Computer Use
3/6Reliability
4/6Knowledge Work
Bar height = share of benchmarks with resultsEstimatedNo score
Measured results are shown as published

Every score in the benchmark tables comes from its source unchanged. Composite IQ averages all seven dimensions equally.

Estimates fill the gaps

Abstract Reasoning, Mathematical Reasoning and Programmatic Reasoning have no published results yet, so their IQ is estimated from nex-n2-pro's other dimensions.

A missing result is not a zero

Benchmark versions and evaluation harnesses can differ between sources, so small gaps between models may not be meaningful.

Read the scoring methodology →

Compare nex-n2-pro

Side-by-side pages for the models it is most often weighed against.

nex-n2-proComparison model
Browse all comparisons →

Frequently asked questions

Quick answers about nex-n2-pro, drawn from the same data as the rest of this page.

How AI IQ scores models →Get this data from the API →
What is the IQ of nex-n2-pro?
nex-n2-pro has an estimated IQ of 109, which ranks #94 out of 186 public models on the AI IQ leaderboard. The score combines seven equally weighted reasoning dimensions using measured benchmark results and conservative estimates for missing coverage.
What is nex-n2-pro best at?
Among the dimensions with published benchmark results, nex-n2-pro ranks highest in Computer Use (IQ 122, #43 of 186) and Academic Reasoning (IQ 125, #82 of 228). Its lowest-ranked measured dimension is Reliability (IQ 111, #105 of 188).
What is the EQ of nex-n2-pro?
nex-n2-pro doesn't have an EQ score yet. EQ (emotional reasoning) is calculated from EQ-Bench 4 and AttuneBench, and neither has published a result for nex-n2-pro. AI IQ doesn't estimate EQ from other benchmarks, so the score appears once one of those results is published.
Which benchmarks has nex-n2-pro been tested on?
nex-n2-pro has published results on 12 of the 39 benchmarks behind AI IQ's Composite IQ, including AA Long Context Reasoning v1.1, BrowseComp, GPQA Diamond, Humanity's Last Exam and CritPt.
How much does nex-n2-pro cost?
nex-n2-pro costs $0.50 per million input tokens and $2.50 per million output tokens. Adjusted for how many tokens it actually consumes on real tasks, its effective cost works out to $2.97 per million input-plus-output tokens.
Is nex-n2-pro open source?
Yes — nex-n2-pro is an open-weights model: its trained weights are published, so it can be downloaded and self-hosted.
Who developed nex-n2-pro?
nex-n2-pro was developed by Nex, based in China.
When was nex-n2-pro released?
nex-n2-pro was publicly released on June 8, 2026.
How large is the context window of nex-n2-pro?
nex-n2-pro supports a context window of 262,144 tokens — the amount of text it can consider in a single request.
How fast is nex-n2-pro?
In independent measurements, nex-n2-pro generates about 99 tokens per second, with a typical response time of about 27 seconds.