Clover 35B A3B Preview
Clover-35B-A3B-Preview
starter@v1HostedCustom endpointserved by DiffuSpace2026-10-30 08:51 UTC30
42 of 153 test cases fully passed
266.8tok/s
Mean per test case, 252 tok/s over the run
8.4Ktokens
Answer plus reasoning
8Ktokens
95% of the output
2.7M
1.4M in, 1.3M out
1h 29m
35.1s per caseSum of request times
Not measured
No price recorded
Every test case
One square per test case. Select a square to read the answer.
20Agents1 of 21 passed
43Structured Extraction9 of 21 passed
10Coding2 of 21 passed
48Grounded Answers10 of 21 passed
53Instruction Following8 of 21 passed
19Business Logic4 of 21 passed
47Security & permissions8 of 21 passed
0Diagnosis & investigation0 of 6 passed
Speed and output per test case
One bar per test case. Hover a bar to see its numbers. Select it to read the answer.
Peak 464 tok/s
ReasoningAnswer
Test by test
Every answer with its reasoning and the checks it had to pass.
Reproduce this run
The prompts stay private so models can't train on them. The hashes pin the exact suite and config this run used.
Custom endpointHosted
curl "${OPENAI_BASE_URL:-https://api.openai.com/v1}/chat/completions" \
-H "Authorization: Bearer $OPENAI_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"Clover-35B-A3B-Preview","messages":[{"role":"user","content":"Hello"}]}'Set OPENAI_BASE_URL when the run used an endpoint other than OpenAI's.
Configuration
Where the suite ran, and the token budget each task got.
- Hosted
- Custom endpoint
- DiffuSpace
- Provider default
- Not recorded
- Not set
- v1.0.0
- 2026-10-30 08:51 UTC
| Task | Reasoning | Max output per call |
|---|---|---|
| Agents | 4.1K | 12.3K |
| Structured Extraction | 4.1K | 12.3K |
| Coding | 4.1K | 12.3K |
| Grounded Answers | 4.1K | 12.3K |
| Instruction Following | 4.1K | 12.3K |
| Business Logic | 4.1K | 12.3K |
| Security & permissions | 4.1K | 12.3K |
| Diagnosis & investigation | 4.1K | 12.3K |