#334 North Mini Code
medium- Cost
- $0.000
- Time
- 51.8s
- Tokens
- 12,460 tok
Cohere
Release: 2026-06-18
Tested on: 2026-10-01 03:03
cohere/north-mini-code::medium
30B total (3B active)MoEOpen source
(medium)
(default)
Summary
North Mini Code scores 5.4 on AI BENCHY and ranks #334. It has 8.9 reliability, a 42.0% pass rate, $0.000 total cost, and 140.39s average response time.
What makes North Mini Code unique: It stands out most in Anti-AI Tricks, where it ranks #2, while Domain specific is its weakest area at #14. Its total benchmark cost is unusually low for its score range. It uses unusually many reasoning tokens, which can help explain its slower or more expensive runs.
Model facts
Researched on 2026-08-12
- Parameters
- 30B total (3B active)
- Architecture
- MoE
- Availability
- Open source
- License
- Apache-2.0
5.4
Consistency
8.6
8.9
$0.000
Total Output Tokens
1,359,341
Total Input Tokens
166,347
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: 15
Attempt pass rate: 42.0%
Benchmark coverage: 61/69 attempts (Target: 3 repeats per test)
Flaky tests
4
Flaky tests had mixed outcomes across runs (at least one pass and one fail).
Hamster playing table tennis
Prompt: Create a detailed SVG illustration of a hamster playing table tennis.
Run history
| Tested on | Score | Reliability | Tests Correct | Total Cost | Compare |
|---|---|---|---|---|---|
| 2026-10-01 03:03 Re-test | 5.4 | 8.9 | $0.000 | Current run | |
| 2026-07-16 23:46 New test added | 5.9 | 8.6 | $0.000 | Compare | |
| 2026-06-18 09:44 Initial run | 5.8 | 8.5 | $0.000 | Compare |
This run used a different benchmark suite. Keep suite changes in mind when reading historical movement.
Run comparison
| Run | Benchmark coverage | Score | Consistency | Reliability | Tests Correct | Flaky tests | Total Output Tokens | Total Input Tokens | Total Cost | Response Time (avg) |
|---|---|---|---|---|---|---|---|---|---|---|
| 2026-10-01 03:03 · Current run | 61/69 attempts | 5.4 | 8.6 | 8.9 | 8/23 | 4 | 1,359,341 | 166,347 | $0.000 | 140.39s |
| 2026-07-16 23:46 · New test added | 58/66 attempts | 5.9 | 8.5 | 8.6 | 9/22 | 4 | 1,766,801 | 81,813 | $0.000 | 137.11s |
| Difference | — | -0.5 | +0.1 | +0.3 | -1 | 0 | -407460 | +84534 | $0.000 | +3285ms |
Benchmark coverage differs: 61/69 attempts (Target: 3 repeats per test) versus 58/66 attempts (Target: 3 repeats per test). Totals and repeat-sensitive metrics are not directly comparable.
These two runs used different benchmark suites, so the deltas reflect both model changes and suite changes.
Charts
Choose the first model, then click a second model to open a side-by-side page.
Top Models by Score
Score vs Total Cost
Response Time (avg)
Score vs Response Time (avg)
Total Output Tokens
Score vs Total Output Tokens
Quick Compare
North Mini CodemediumFree AvailablevsQwen3.8 27BnoneFree AvailableNorth Mini CodemediumFree AvailablevsHy4 previewlowNorth Mini CodemediumFree AvailablevsSeed-2.0-CodenoneNorth Mini CodemediumFree AvailablevsMiMo-V2.6-FlashnoneNorth Mini CodemediumFree AvailablevsGemma 4 26B A4BnoneFree AvailableNorth Mini CodemediumFree AvailablevsStep 3.5 FlashmediumNorth Mini CodemediumFree AvailablevsGPT-6 LunanoneNorth Mini CodemediumFree AvailablevsEmber-1noneNorth Mini CodemediumFree AvailablevsGemini 2.5 FlashnoneNorth Mini CodemediumFree AvailablevsGPT-5.6 Lunanone
Category Breakdown
| Category | Score | Consistency | Tests Correct |
|---|---|---|---|
| Agentic | 3.9 | 9.6 | |
| Anti-AI Tricks | 8.4 | 10.0 | |
| Coding | 4.5 | 4.9 | |
| Combined | 2.9 | 5.8 | |
| Data parsing and extraction | 10.0 | 10.0 | |
| Domain specific | 2.9 | 7.2 | |
| General Intelligence | 5.1 | 10.0 | |
| Instructions following | 9.8 | 10.0 | |
| Puzzle Solving | 3.3 | 10.0 | |
| Tool Calling | 10.0 | 10.0 | |
| Trivia | 3.0 | 10.0 |