#399 Cobuddy
medium
No endpoints found for baidu/cobuddy:free.
- Cost
- $0.000
- Time
- 0.1s
- Tokens
- 0 tok
Baidu
Release: 2026-05-06
Tested on: 2026-10-01 05:10
baidu/cobuddy::medium
~21B total (~3B active)MoEClosedEstimated Summary
Cobuddy scores 4.4 on AI BENCHY and ranks #399. It has 10.0 reliability, a 43.5% pass rate, $0.000 total cost, and 38.01s average response time.
What makes Cobuddy unique: It stands out most in Anti-AI Tricks, where it ranks #2, while Domain specific is its weakest area at #12. Its total benchmark cost is unusually low for its score range.
Model facts
Researched on 2026-08-12
- Parameters
- ~21B total (~3B active)
- Architecture
- MoE
- Availability
- Closed
- License
- -
Best estimate from public evidence; the vendor did not disclose every value. Estimate from positioning and related lightweight ERNIE models; no count is disclosed.
4.4
Consistency
7.3
10.0
$0.000
Total Output Tokens
118,380
Total Input Tokens
37,449
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: 43.5%
Benchmark coverage: 66/69 attempts (Target: 3 repeats per test)
Flaky tests
6
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 05:10 New test added | 4.4 | 10.0 | $0.000 | Current run | |
| 2026-05-22 00:23 Suite changed | 5.7 | 9.9 | $0.000 | Compare | |
| 2026-05-06 11:30 First recorded run | 6.0 | 9.9 | $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 05:10 · Current run | 66/69 attempts | 4.4 | 7.3 | 10.0 | 7/22 | 6 | 118,380 | 37,449 | $0.000 | 38.01s |
| 2026-05-22 00:23 · Suite changed | 60/60 attempts | 5.7 | 7.0 | 9.9 | 7/20 | 7 | 118,185 | 0 | $0.000 | 39.91s |
| Difference | — | -1.4 | +0.3 | +0.1 | 0 | -1 | +195 | +37449 | $0.000 | -1903ms |
Benchmark coverage differs: 66/69 attempts (Target: 3 repeats per test) versus 60/60 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
CobuddymediumFree AvailablevsGranite 4.2 8BnoneCobuddymediumFree AvailablevsMercury 2noneCobuddymediumFree AvailablevsTrinity Large PreviewdefaultFree AvailableCobuddymediumFree AvailablevsMiniMax M2.5mediumCobuddymediumFree AvailablevsKAT Coder AIR V2.5defaultCobuddymediumFree AvailablevsGLM 4.7 FlashmediumCobuddymediumFree AvailablevsNemotron 3 SupernoneFree AvailableCobuddymediumFree Availablevsgpt-oss-120bnoneCobuddymediumFree AvailablevsRing 2.6 1tdefaultCobuddymediumFree AvailablevsMercury 2.5none
Category Breakdown
| Category | Score | Consistency | Tests Correct |
|---|---|---|---|
| Agentic | 3.0 | 10.0 | |
| Anti-AI Tricks | 8.7 | 7.9 | |
| Coding | 3.7 | 6.7 | |
| Combined | 1.5 | 5.0 | |
| Data parsing and extraction | 6.3 | 5.8 | |
| Domain specific | 2.9 | 4.4 | |
| General Intelligence | 4.2 | 9.9 | |
| Instructions following | 9.8 | 10.0 | |
| Puzzle Solving | 3.6 | 7.2 | |
| Tool Calling | 10.0 | 10.0 | |
| Trivia | 3.0 | 10.0 |