[mle]/DaBench
Leaderboard

Clover 35B A3B Preview

Clover-35B-A3B-Preview

Hostedcustom252 tok/sserved by DiffuSpace
Run recordCompareOpen weights
Overall score
30

42 of 153 test cases fully passed

Scores by task

Scores give partial credit. Passed counts fully correct answers only. Select a task to read its test cases.

  1. 20Agents1 of 21 passedp90 latency 1m 5s
  2. 43Structured Extraction9 of 21 passedp90 latency 44.1s
  3. 10Coding2 of 21 passedp90 latency 1m 22s
  4. 48Grounded Answers10 of 21 passedp90 latency 37.6s
  5. 53Instruction Following8 of 21 passedp90 latency 59.1s
  6. 19Business Logic4 of 21 passedp90 latency 57.0s
  7. 47Security & permissions8 of 21 passedp90 latency 49.2s
  8. 0Diagnosis & investigation0 of 6 passedp90 latency 1m 4s

Run it yourself

The API call the benchmark made, and the settings behind this score.

Deployment
Hosted
API
Custom endpoint
Serving provider
DiffuSpace
Precision
Provider default
Context window
Not recorded
Throughput
252 tok/s
Cost of a suite run
Not measured
Cost per case
Not measured
Time per case
35.1s
Measured
2026-10-30
Run this buildCustom 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.

One email when a new model lands on the board or in the showcase. Unsubscribe anytime.