[mle]/DaBench
Leaderboard

Qwen3.8 Flash Next

qwen/qwen3.8-flash

Hostedqwen68 tok/sopenrouterserved by Alibaba1M context
Run recordCompareOpen weights
Overall score
42

68 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. 52Agents9 of 21 passedp90 latency 3m 35s
  2. 50Structured Extraction12 of 21 passedp90 latency 1m 3s
  3. 52Coding7 of 21 passedp90 latency 2m 22s
  4. 51Grounded Answers12 of 21 passedp90 latency 1m 12s
  5. 62Instruction Following12 of 21 passedp90 latency 3m 4s
  6. 25Business Logic7 of 21 passedp90 latency 1m 26s
  7. 45Security & permissions9 of 21 passedp90 latency 2m 20s
  8. 0Diagnosis & investigation0 of 6 passedp90 latency 2m 13s

Run it yourself

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

Deployment
Hosted
API
OpenRouter
Serving provider
Alibaba
Precision
Provider default
Context window
1M
Throughput
68 tok/s
Cost of a suite run
$0.46
Cost per case
$0.003
Time per case
1m 15s
Measured
2026-10-22
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/qwen3.8-flash","provider":{"order":["alibaba"],"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.