[mle]/DaBench
Leaderboard

GPT-6 Luna

openai/gpt-6-luna

Hostedopenai90 tok/sopenrouterserved by OpenAI1.1M context
Run recordCompare
Overall score
61

95 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. 56Agents8 of 21 passedp90 latency 2m 31s
  2. 95Structured Extraction20 of 21 passedp90 latency 23.4s
  3. 73Coding14 of 21 passedp90 latency 5m 12s
  4. 67Grounded Answers14 of 21 passedp90 latency 30.3s
  5. 84Instruction Following17 of 21 passedp90 latency 48.3s
  6. 37Business Logic8 of 21 passedp90 latency 2m 18s
  7. 62Security & permissions13 of 21 passedp90 latency 38.3s
  8. 17Diagnosis & investigation1 of 6 passedp90 latency 1m 29s

What it built

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

See everything it built

Run it yourself

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

Deployment
Hosted
API
OpenRouter
Serving provider
OpenAI
Precision
Provider default
Context window
1.1M
Throughput
90 tok/s
Cost of a suite run
$0.10
Cost per case
$0.00067
Time per case
49.1s
Measured
2026-10-04
Run this buildOpenRouterHosted
curl https://openrouter.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"openai/gpt-6-luna","provider":{"order":["openai/flex"],"allow_fallbacks":false},"service_tier":"flex","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.

LeaderboardCompare GPT-6 Luna with another model