Skip to main content

Nex-AGILanguage modelOpen weights

Nex-N2.5-mini

Nex-N2.5-mini has no overall index value yet because there are too few independent benchmark results.

PopularityRank 670 of 875

0out of 100same as last month

Summary

Nex-N2.5-mini uses visual feedback to work through longer computer and browser tasks. Nex-AGI trains this compact multimodal variant on a broader set of environments and tasks than the previous Nex-N2 series.

Mini is available through OpenRouter alongside Pro. Nex-AGI also publishes local weights under Apache 2.0.

See for yourself: one prompt, one attempt

SVG short test

One SVG task with the same fixed settings for every model, without hidden thinking.

Nex-N2.5-mini

Nex-N2.5-mini: SVG short test

Prompt

Return only one standalone SVG of a pelican riding a bicycle. Use viewBox="0 0 800 600", simple shapes, two clearly visible wheels and a recognizable pelican with a long beak. At most 30 SVG elements and 1800 characters. No Markdown, explanations, comments, scripts, animation, CSS or external resources.

Oct 14, 2026 · $0.0001

Test details
Test run
Oct 14, 2026
Provider
nex-agi/bf16
API model
nex-agi/nex-n2.5-mini
Output
867 tokens
Reasoning
API reports 0 reasoning tokens
Cost of the attempt
$0.0001
Test round
43b8c5c46830
Earlier tests

The response reached the token limit. No complete recording is available.

Pelican on a bicycle

Prompt

Generate an SVG of a pelican riding a bicycle

Oct 5, 2026 · 35 s · $0.0008

Not yet visually reviewed. A successful recording does not confirm correct physics or full compliance with the prompt.

Test details
Run date
Oct 5, 2026
API provider
openrouter
Requested API model
nex-agi/nex-n2.5-mini
Reasoning setting
high
Token limit including reasoning
8,192 tokens
Output tokens
8,192 tokens
Cost of the attempt
$0.0008
Response time
34.8 s
API model reported in response
nex-agi/nex-n2.5-mini
Pinned endpoint
Nex AGI | nex-agi/nex-n2.5-mini-20260908
Temperature
Provider default
Test protocol
community-visual-tests-v1
Technical checks
Failed
Task origin: Simon Willison

All benchmark results

Every published result with its source, test setup and comparison models.

Show all 16 published benchmark results

Page 1 of 2

Measurements without matching peer values

These measurements have no matching peer values under the same test conditions. Their original values and sources remain available here.

TerminalBench 2.1 (Show measurement, test conditions, and source)
Source value
73.4
Score
73.4
Metric
TerminalBench 2.1 reported score
Unit
No unit provided
Category
source-specific
Direction
Higher is better
Source type
vendor-reported
Evaluator
Provider model card
Status
active
Retrieved at
2026-10-04
Methodology
Vendor-reported result. Vendor table. Sampling temperature 0.7, top_p 0.95 and top_k 40; coding uses NexAU, computer-use tasks use NexCUA, and WebTest is oracle-mode defect detection.
Context
Source-specific observation; it is not a shared comparison cohort. The source table does not state a unit or scale for this numeric score.
Source Provider model card
SWE-Pro (Show measurement, test conditions, and source)
Source value
43.8
Score
43.8
Metric
SWE-Pro reported score
Unit
No unit provided
Category
source-specific
Direction
Higher is better
Source type
vendor-reported
Evaluator
Provider model card
Status
active
Retrieved at
2026-10-04
Methodology
Vendor-reported result. Vendor table. Sampling temperature 0.7, top_p 0.95 and top_k 40; coding uses NexAU, computer-use tasks use NexCUA, and WebTest is oracle-mode defect detection.
Context
Source-specific observation; it is not a shared comparison cohort. The source table does not state a unit or scale for this numeric score.
Source Provider model card
DeepSWE (Show measurement, test conditions, and source)
Source value
36.1
Score
36.1
Metric
DeepSWE reported score
Unit
No unit provided
Category
source-specific
Direction
Higher is better
Source type
vendor-reported
Evaluator
Provider model card
Status
active
Retrieved at
2026-10-04
Methodology
Vendor-reported result. Vendor table. Sampling temperature 0.7, top_p 0.95 and top_k 40; coding uses NexAU, computer-use tasks use NexCUA, and WebTest is oracle-mode defect detection.
Context
Source-specific observation; it is not a shared comparison cohort. The source table does not state a unit or scale for this numeric score.
Source Provider model card
Automation (Show measurement, test conditions, and source)
Source value
32.3
Score
32.3
Metric
Automation reported score
Unit
No unit provided
Category
source-specific
Direction
Higher is better
Source type
vendor-reported
Evaluator
Provider model card
Status
active
Retrieved at
2026-10-04
Methodology
Vendor-reported result. Vendor table. Sampling temperature 0.7, top_p 0.95 and top_k 40; coding uses NexAU, computer-use tasks use NexCUA, and WebTest is oracle-mode defect detection.
Context
Source-specific observation; it is not a shared comparison cohort. The source table does not state a unit or scale for this numeric score.
Source Provider model card
Toolathlon (Show measurement, test conditions, and source)
Source value
54.6
Score
54.6
Metric
Toolathlon reported score
Unit
No unit provided
Category
source-specific
Direction
Higher is better
Source type
vendor-reported
Evaluator
Provider model card
Status
active
Retrieved at
2026-10-04
Methodology
Vendor-reported result. Vendor table. Sampling temperature 0.7, top_p 0.95 and top_k 40; coding uses NexAU, computer-use tasks use NexCUA, and WebTest is oracle-mode defect detection.
Context
Source-specific observation; it is not a shared comparison cohort. The source table does not state a unit or scale for this numeric score.
Source Provider model card
GDPval (Show measurement, test conditions, and source)
Source value
1446
Score
1446
Metric
GDPval reported score
Unit
No unit provided
Category
source-specific
Direction
Higher is better
Source type
vendor-reported
Evaluator
Provider model card
Status
active
Retrieved at
2026-10-04
Methodology
Vendor-reported result. Vendor table. Sampling temperature 0.7, top_p 0.95 and top_k 40; coding uses NexAU, computer-use tasks use NexCUA, and WebTest is oracle-mode defect detection.
Context
Source-specific observation; it is not a shared comparison cohort. The source table does not state a unit or scale for this numeric score.
Source Provider model card
JobBench (Show measurement, test conditions, and source)
Source value
28.5
Score
28.5
Metric
JobBench reported score
Unit
No unit provided
Category
source-specific
Direction
Higher is better
Source type
vendor-reported
Evaluator
Provider model card
Status
active
Retrieved at
2026-10-04
Methodology
Vendor-reported result. Vendor table. Sampling temperature 0.7, top_p 0.95 and top_k 40; coding uses NexAU, computer-use tasks use NexCUA, and WebTest is oracle-mode defect detection.
Context
Source-specific observation; it is not a shared comparison cohort. The source table does not state a unit or scale for this numeric score.
Source Provider model card
BrowseComp (Show measurement, test conditions, and source)
Source value
83.4
Score
83.4
Metric
BrowseComp reported score
Unit
No unit provided
Category
source-specific
Direction
Higher is better
Source type
vendor-reported
Evaluator
Provider model card
Status
active
Retrieved at
2026-10-04
Methodology
Vendor-reported result. Vendor table. Sampling temperature 0.7, top_p 0.95 and top_k 40; coding uses NexAU, computer-use tasks use NexCUA, and WebTest is oracle-mode defect detection.
Context
Source-specific observation; it is not a shared comparison cohort. The source table does not state a unit or scale for this numeric score.
Source Provider model card
OSWorld Verified (Show measurement, test conditions, and source)
Source value
71.2
Score
71.2
Metric
OSWorld Verified reported score
Unit
No unit provided
Category
source-specific
Direction
Higher is better
Source type
vendor-reported
Evaluator
Provider model card
Status
active
Retrieved at
2026-10-04
Methodology
Vendor-reported result. Vendor table. Sampling temperature 0.7, top_p 0.95 and top_k 40; coding uses NexAU, computer-use tasks use NexCUA, and WebTest is oracle-mode defect detection.
Context
Source-specific observation; it is not a shared comparison cohort. The source table does not state a unit or scale for this numeric score.
Source Provider model card
OSWorld 2 (Show measurement, test conditions, and source)
Source value
30.5
Score
30.5
Metric
OSWorld 2 reported score
Unit
No unit provided
Category
source-specific
Direction
Higher is better
Source type
vendor-reported
Evaluator
Provider model card
Status
active
Retrieved at
2026-10-04
Methodology
Vendor-reported result. Vendor table. Sampling temperature 0.7, top_p 0.95 and top_k 40; coding uses NexAU, computer-use tasks use NexCUA, and WebTest is oracle-mode defect detection.
Context
Source-specific observation; it is not a shared comparison cohort. The source table does not state a unit or scale for this numeric score.
Source Provider model card
WebTest (Show measurement, test conditions, and source)
Source value
48.6
Score
48.6
Metric
WebTest reported score
Unit
No unit provided
Category
source-specific
Direction
Higher is better
Source type
vendor-reported
Evaluator
Provider model card
Status
active
Retrieved at
2026-10-04
Methodology
Vendor-reported result. Vendor table. Sampling temperature 0.7, top_p 0.95 and top_k 40; coding uses NexAU, computer-use tasks use NexCUA, and WebTest is oracle-mode defect detection.
Context
Source-specific observation; it is not a shared comparison cohort. The source table does not state a unit or scale for this numeric score.
Source Provider model card
WebArena (Show measurement, test conditions, and source)
Source value
63.4
Score
63.4
Metric
WebArena reported score
Unit
No unit provided
Category
source-specific
Direction
Higher is better
Source type
vendor-reported
Evaluator
Provider model card
Status
active
Retrieved at
2026-10-04
Methodology
Vendor-reported result. Vendor table. Sampling temperature 0.7, top_p 0.95 and top_k 40; coding uses NexAU, computer-use tasks use NexCUA, and WebTest is oracle-mode defect detection.
Context
Source-specific observation; it is not a shared comparison cohort. The source table does not state a unit or scale for this numeric score.
Source Provider model card

Page 1 of 2

Popularity compared

How often the model is searched for, used and mentioned, compared with every model of its category.

Popularity index

The 100 most popular models of this category, 0 to 100, higher is more popular

20 of 101 models

Gemini 4 Argon92
GPT-6 Astra78
Claude Haiku 5.577
Qwen3.5 4B76
GPT-573
GPT-6 Sol72
Qwen3.5 0.8B72
Qwen3.5 2B71
Qwen 3.8 27B70
Claude Opus 5.570
DeepSeek V4.1 Flash 101768
Qwen 3.8 Max 090268
Kimi K368
DeepSeek-V4-Flash65
GPT-5.6 Terra64
Claude Sonnet 563
DiffusionGemma 26B A4B IT63
Claude Opus 562
Qwen 3.8 Flash62
Nex-N2.5-mini0

As of November 2026 · Source: gradually.ai popularity index

Over time

Weekly values from October 18, 2026 to November 5, 2026

Nex-N2.5-miniAgnes 3.0 FlashAion 3.5Aion 3.5 MiniEmber-1

All specifications

Input and output

Input
Text and visual inputs
Source: Input

Watermarking and provenance

AI watermarking refers to invisible signals embedded in the output. Visible marks and provenance metadata are listed separately. Unknown means there is insufficient evidence for that particular field.

AI watermarking
Unknown
no source
Watermarking technique
Not known
no source

Licence and access

Access
Open weights and OpenRouter
Source: Access
License
Apache 2.0
Source: License

API

Model ID
nex-agi/Nex-N2.5-mini
Source: Model ID

Frequently asked questions about Nex-N2.5-mini

Can I run Nex-N2.5-mini locally?

Yes, the weights are open.

Stated by Nex-AGI

Open weights
yes
License
Apache 2.0
Parameters
n/a
active per token
n/a

Sources and data date

Show all 9 sources

Benchmark sources at a glance

Which independent evaluators tested this model. This is coverage, not a quality ranking.

No active result from the reviewed external evaluators can currently be attributed to this model. Other source evidence remains available below.

Without vendor claims and historical or disputed results; those stay labelled in the single values.

TypeEvidence and data date
Research statusResearch date October 4, 2026. 1 source URLs checked. This documents the inspected sources, not an exhaustive inventory of every publication.
Additional sourceNex-N2.5-mini model card (retrieved October 3, 2026; October 4, 2026) · Nex-N2.5-mini model card · Editorial description reviewed October 4, 2026
Additional sourceNex-N2.5-Pro model card (retrieved October 3, 2026) · Nex-N2.5-Pro model card · Editorial description reviewed October 4, 2026
Additional sourceNex-N2.5-Max model card (retrieved October 3, 2026) · Nex-N2.5-Max model card · Editorial description reviewed October 4, 2026
Additional sourceOpenRouter: Popularity index (derived), CC BY 4.0
Additional sourceVercel AI Gateway: Popularity index (derived), CC BY 4.0
Additional sourceOllama: cumulative downloads for the popularity index
Additional sourceReplicate: cumulative runs for the popularity index
Additional sourceGoogle Trending Now: limited feed selection for Germany and the US
Additional sourceCreative Commons Attribution 4.0