Baseten
Release: 2026-10-24
Tested on: 2026-10-24 15:07
baseten/mammoth-1::none
27BDenseOpen source Summary
Mammoth 1 scores 2.2 on AI BENCHY and ranks #442. It has 8.9 reliability, a 18.8% pass rate, $0.000 total cost, and 1.80s average response time.
What makes Mammoth 1 unique: It stands out most in Coding, where it ranks #1, while Data parsing and extraction is its weakest area at #13. Its total benchmark cost is unusually low for its score range.
Model facts
Researched on 2026-10-24
- Parameters
- 27B
- Architecture
- Dense
- Availability
- Open source
- License
- MIT
Official MIT weights and pinned serving implementation are published. Base Labs identifies a 27B Qwen3.5-27B fine-tune with block-bidirectional full-attention layers and a frozen vision encoder. Dense here means no mixture of experts; the hybrid recurrent/attention backbone is preserved. The exact OpenRouter route accepts text states and returns typed decisions, with no free-form generation or reasoning controls. BaseTen publishes no prompt training and no retention. The current free promotional route is $0/$0; the vendor free week ends October 27 at 23:59 Pacific. Decision output is evaluated with compatible adapted general tests and the five dedicated decision tests. Free-form showcases do not apply.
2.2
Consistency
4.2
8.9
$0.000
Total Output Tokens
54
Total Input Tokens
45,468
Input Price
$0.000 / 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: 9
Attempt pass rate: 18.8%
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
3
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
Mammoth 1defaultFree AvailablevsJev 1.14defaultMammoth 1defaultFree AvailablevsClassify-1defaultMammoth 1defaultFree AvailablevsKev 4BdefaultMammoth 1defaultFree AvailablevsClef OmnidefaultMammoth 1defaultFree AvailablevsGPT-6 Luna DecisionsdefaultMammoth 1defaultFree AvailablevsDecider Flash V1.2defaultMammoth 1defaultFree AvailablevsDrex v1.5defaultMammoth 1defaultFree AvailablevsD1defaultMammoth 1defaultFree AvailablevsDecider V1.1 27BdefaultMammoth 1defaultFree AvailablevsGemini 3 Flash Previewhigh
Category Breakdown
| Category | Score | Consistency | Tests Correct |
|---|---|---|---|
| Agentic | 0.0 | 0.0 | |
| Anti-AI Tricks | 4.0 | 7.5 | |
| Coding | 4.9 | 6.7 | |
| Combined | 0.0 | 0.0 | |
| Data parsing and extraction | 3.7 | 1.7 | |
| Domain specific | 5.3 | 10.0 | |
| General Intelligence | 0.0 | 0.0 | |
| Instructions following | 1.5 | 5.0 | |
| Puzzle Solving | 1.6 | 1.0 | |
| Tool Calling | 0.0 | 0.0 | |
| Trivia | 0.0 | 0.0 |