Nex-AGILanguage modelOpen weights
Nex-N2.5-Max
Nex-N2.5-Max has no overall index value yet because there are too few independent benchmark results.
0out of 100same as last month
Summary
Nex-N2.5-Max marks Nex-AGI’s first complete post-training effort at trillion-parameter scale, according to the company. Its foundation is a text-only MoE model with 1.6 trillion parameters. Unlike Mini and Pro, Max does not accept visual input.
Nex-AGI publishes the weights under Apache 2.0. The release does not list a dedicated hosted Max endpoint.
All benchmark results
Every published result with its source, test setup and comparison models.
Show all 8 published benchmark results
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
- 86.1
- Score
- 86.1
- 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.
SWE-Pro (Show measurement, test conditions, and source)
- Source value
- 65.7
- Score
- 65.7
- 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.
DeepSWE (Show measurement, test conditions, and source)
- Source value
- 65.6
- Score
- 65.6
- 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.
Automation (Show measurement, test conditions, and source)
- Source value
- 50.2
- Score
- 50.2
- 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.
Toolathlon (Show measurement, test conditions, and source)
- Source value
- 74.7
- Score
- 74.7
- 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.
GDPval (Show measurement, test conditions, and source)
- Source value
- 1713
- Score
- 1713
- 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.
JobBench (Show measurement, test conditions, and source)
- Source value
- 53.6
- Score
- 53.6
- 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.
BrowseComp (Show measurement, test conditions, and source)
- Source value
- 92.6
- Score
- 92.6
- 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.
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
As of November 2026 · Source: gradually.ai popularity index
Over time
Weekly values from October 18, 2026 to November 5, 2026
Nex-N2.5-MaxAgnes 3.0 FlashAion 3.5Aion 3.5 MiniEmber-1
All specifications
Architecture
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
API
Frequently asked questions about Nex-N2.5-Max
Can I run Nex-N2.5-Max locally?
Yes, the weights are open. With 1.6T parameters it needs a lot of memory, more a server than a laptop.
Stated by Nex-AGI
- Open weights
- yes
- License
- Apache 2.0
- Parameters
- 1.6T
- 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.