[mle]/DaBench
Leaderboard

Flint

recursive/flint-v1.0:free

Hostedrecursive149 tok/sopenrouterserved by RecursiveBF16256K context
Run recordCompareOpen weights
Overall score
21

33 of 153 test cases fully passed

What it built

What it wrote for showcase prompts, running live in your browser.

Scores by task

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

  1. 14Agents2 of 21 passedp90 latency 1m 31s
  2. 29Structured Extraction6 of 21 passedp90 latency 1m 36s
  3. 14Coding3 of 21 passedp90 latency 1m 30s
  4. 29Grounded Answers6 of 21 passedp90 latency 1m 20s
  5. 35Instruction Following7 of 21 passedp90 latency 3m 48s
  6. 10Business Logic2 of 21 passedp90 latency 1m 32s
  7. 35Security & permissions7 of 21 passedp90 latency 1m 20s
  8. 0Diagnosis & investigation0 of 6 passedp90 latency 2m 4s

Run it yourself

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

Deployment
Hosted
API
OpenRouter
Serving provider
Recursive
Precision
BF16
Context window
256K
Throughput
149 tok/s
Cost of a suite run
Not measured
Cost per case
Not measured
Time per case
1m 17s
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":"recursive/flint-v1.0:free","provider":{"order":["recursive/bf16"],"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.