[mle]/DaBench
Leaderboard

Qwen3.6 35B A3B

qwen/qwen3.6-35b-a3b

Hostedqwen156 tok/sopenrouterserved by AkashMLFP8256K context
Run recordCompareOpen weights
Overall score
26

37 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. 24Agents4 of 21 passedp90 latency 3m 28s
  2. 43Structured Extraction9 of 21 passedp90 latency 1m 35s
  3. 3Coding0 of 21 passedp90 latency 1m 24s
  4. 33Grounded Answers7 of 21 passedp90 latency 1m 20s
  5. 32Instruction Following4 of 21 passedp90 latency 2m 28s
  6. 29Business Logic6 of 21 passedp90 latency 1m 6s
  7. 46Security & permissions7 of 21 passedp90 latency 1m 6s
  8. 0Diagnosis & investigation0 of 6 passedp90 latency 1m 40s

Run it yourself

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

Deployment
Hosted
API
OpenRouter
Serving provider
AkashML
Precision
FP8
Context window
256K
Throughput
156 tok/s
Cost of a suite run
$1.47
Cost per case
$0.0096
Time per case
1m 5s
Measured
2026-10-30
Run this buildOpenRouterHosted
curl https://openrouter.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"qwen/qwen3.6-35b-a3b","provider":{"order":["akashml/fp8"],"allow_fallbacks":false},"service_tier":"default","messages":[{"role":"user","content":"Hello"}]}'

The request the benchmark sent, pinned to the provider that served it.

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