Nace AI
Release: 2026-10-12
Tested on: 2026-10-12 12:39
nace-ai/drex-v1.5::none
8.95BDenseWeights available Summary
Drex v1.5 scores 2.4 on AI BENCHY and ranks #399. It has 10.0 reliability, a 17.4% pass rate, $0.002 total cost, and 986ms average response time.
What makes Drex v1.5 unique: It stands out most in Coding, where it ranks #2, while Puzzle Solving is its weakest area at #9.
Model facts
Researched on 2026-10-12
- Parameters
- 8.95B
- Architecture
- Dense
- Availability
- Weights available
- License
- Nace.AI Open RAIL-M
The official model card reports about 9B (8.95B) parameters with a Qwen3.5 dense backbone, post-trained from XiaomiMiMo/MiMo-V2.6-Distill-Qwen-9B, and a pointer head. Exact checkpoint weights, the head and inference code are publicly downloadable without gating. Weights use the custom Nace.AI Open RAIL-M license; bundled Kev code is Apache-2.0. Scores predefined options without sampling output tokens. The OpenRouter DeepInfra route declares no reasoning effort controls.
2.4
Consistency
5.2
10.0
$0.002
Total Output Tokens
27,468
Total Input Tokens
42,804
Input Price
$0.040 / 1M
Output Price
$0.000 / 1M
Cache Read Price
N/A
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.
Wrong Tests: 8
Attempt pass rate: 17.4%
Benchmark coverage: 36/69 attempts. Choices supplied by adapters. Supports 12/23 tests. Other tests are unsupported, not failed. Score uses the full suite.
Flaky tests
0
Flaky tests had mixed outcomes across runs (at least one pass and one fail).
Charts
Choose the first model, then click a second model to open a side-by-side page.
Score vs Total Cost
Response Time (avg)
Score vs Response Time (avg)
Total Output Tokens
Score vs Total Output Tokens
Quick Compare
Drex v1.5defaultvsDecider V1.1 27BdefaultDrex v1.5defaultvsGPT-6 Luna DecisionsdefaultDrex v1.5defaultvsJev 1.13defaultDrex v1.5defaultvsKev 4BdefaultDrex v1.5defaultvsCommand A+lowDrex v1.5defaultvsClef OmnidefaultDrex v1.5defaultvsCommand A+noneDrex v1.5defaultvsD1defaultDrex v1.5defaultvsCommand A+highDrex v1.5defaultvsGemini 3 Flash Previewhigh
Category Breakdown
| Category | Score | Consistency | Tests Correct |
|---|---|---|---|
| Agentic | 0.0 | 0.0 | |
| Anti-AI Tricks | 4.0 | 7.5 | |
| Coding | 4.5 | 6.7 | |
| Combined | 0.0 | 0.0 | |
| Data parsing and extraction | 6.5 | 10.0 | |
| Domain specific | 5.3 | 10.0 | |
| General Intelligence | 0.0 | 0.0 | |
| Instructions following | 1.5 | 5.0 | |
| Puzzle Solving | 1.0 | 3.3 | |
| Tool Calling | 0.0 | 0.0 | |
| Trivia | 0.0 | 0.0 |