Advertise here
#520

Groundhog 1

Baseten Release: 2026-11-20 Tested on: 2026-11-22 00:13 baseten/groundhog-1::none
26B total (4B active)MoEOpen source

Summary

Groundhog 1 scores 2.5 on AI BENCHY and ranks #520. It has 10.0 reliability, a 21.7% pass rate, $0.002 total cost, and 671ms average response time.

What makes Groundhog 1 unique: It stands out most in Data parsing and extraction, where it ranks #1, while Coding is its weakest area at #13.

Model facts

Researched on 2026-11-22

Reported
Parameters
26B total (4B active)
Architecture
MoE
Availability
Open source
License
MIT AND Apache-2.0

Base Labs decision model fine-tuned from Gemma 4 26B A4B; Baseten reports 26B MoE with about 4B active. Weights are public: base under Apache-2.0, Baseten changes under MIT. Served as a typed decision endpoint with no reasoning controls; training data (6.71M decision examples) is not released. Released 2026-11-20.

Score

2.5

Consistency

5.2

Total Output Tokens

69

Total Input Tokens

54,825

Input Price

$0.035 / 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.

Tests Correct

Wrong Tests: 7

Attempt pass rate: 21.7%

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).

Response Time (avg)

671ms

Response Time (max): 1.04s

Response Time (total): 8.05s

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

Category Breakdown

Category Score Consistency Tests Correct
Agentic 0.0 0.0
Anti-AI Tricks 4.0 7.5
Coding 2.4 6.7
Combined 0.0 0.0
Data parsing and extraction 10.0 10.0
Domain specific 5.3 10.0
General Intelligence 0.0 0.0
Instructions following 1.5 5.0
Puzzle Solving 3.3 3.3
Tool Calling 0.0 0.0
Trivia 0.0 0.0

Compared models