Advertise here
#207

Nex-N2.6

NEX AGI Release: 2026-11-12 Tested on: 2026-11-12 23:21 nex-agi/nex-n2.6::high
321B total (~18B active)MoEOpen sourceEstimated
(high) (medium)

Summary

Nex-N2.6 scores 7.2 on AI BENCHY and ranks #207. It has 9.2 reliability, a 75.4% pass rate, $0.177 total cost, and 49.19s average response time.

What makes Nex-N2.6 unique: It stands out most in Coding, where it ranks #1, while Data parsing and extraction is its weakest area at #16.

Model facts

Researched on 2026-11-12

Estimated
Parameters
321B total (~18B active)
Architecture
MoE
Availability
Open source
License
Apache-2.0

Best estimate from public evidence; the vendor did not disclose every value. The Hugging Face card reports a GLM-5.3-Flash base and 321B parameters with Apache-2.0 FP8 weights. Active parameters and MoE architecture are estimated from the base model card (18B active). The card does not confirm that the OpenRouter fp8 endpoint serves this exact export.

Parameter source 1 Parameter source 2 Availability source

Score

7.2

Consistency

6.9

Reliability

9.2

Total Cost (Current Price)

$0.177

Total Output Tokens

346,067

Total Input Tokens

320,969

Input Price

$0.120 / 1M

Output Price

$0.400 / 1M

Cache Read Price

$0.024 / 1M

Cache Write Price

N/A

Cache prices apply to input tokens. Reads reuse cached prompts; writes store them and can cost extra. Output tokens use the output price.

Tests Correct

Wrong Tests: 11

Attempt pass rate: 75.4%

Flaky tests

9

Flaky tests had mixed outcomes across runs (at least one pass and one fail).

Response Time (avg)

49.19s

Response Time (max): 324.64s

Response Time (total): 1131.29s

Wrong answer: 6 Did not follow instructions: 2 Extra formatting: 1 Invalid tool call: 1 No answer: 1

Hamster playing table tennis

Prompt: Create a detailed SVG illustration of a hamster playing table tennis.

#207 Nex-N2.6

high
Cost
$0.005
Time
108.9s
Tokens
11,855 tok

Charts

Choose the first model, then click a second model to open a side-by-side page.

Total Output Tokens

Score vs Total Output Tokens

Quick Compare

Nex-N2.6highvsQwen3.5-27BnoneNex-N2.6highvsQwen3.5 Plus 2026-02-15mediumNex-N2.6highvsGemini 3.5 Flash LitemediumNex-N2.6highvsQwen3.8 27BmediumFree AvailableNex-N2.6highvsQwen3.6 PlusmediumNex-N2.6highvsGemini 3.8 FlashlowNex-N2.6highvsLongCat 2.0highNex-N2.6highvsClaude Opus 4.8lowNex-N2.6highvsGemini 2.5 FlashmediumNex-N2.6highvsQwen3.7 Flashhigh

Category Breakdown

Category Score Consistency Tests Correct
Agentic 6.1 3.1
Anti-AI Tricks 8.7 7.9
Coding 10.0 10.0
Combined 6.9 5.9
Data parsing and extraction 4.6 1.7
Domain specific 3.5 4.4
General Intelligence 6.5 3.4
Instructions following 9.9 10.0
Puzzle Solving 8.7 7.7
Tool Calling 10.0 10.0
Trivia 3.0 10.0

Compared models