[mle]/DaBench
Leaderboard

Mistral Large 4

mistralai/mistral-large-4-0

Hostedmistralai56 tok/sopenrouterserved by Mistral512K context
Run recordCompare
Overall score
28

43 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. 11Agents1 of 21 passedp90 latency 48.5s
  2. 15Structured Extraction4 of 21 passedp90 latency 6.14s
  3. 33Coding5 of 21 passedp90 latency 4m 8s
  4. 38Grounded Answers8 of 21 passedp90 latency 4m 20s
  5. 69Instruction Following13 of 21 passedp90 latency 5m 35s
  6. 24Business Logic5 of 21 passedp90 latency 3m 59s
  7. 33Security & permissions7 of 21 passedp90 latency 3m 21s
  8. 0Diagnosis & investigation0 of 6 passedp90 latency 3m 27s

What it built

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

Run it yourself

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

Deployment
Hosted
API
OpenRouter
Serving provider
Mistral
Precision
Provider default
Context window
512K
Throughput
56 tok/s
Cost of a suite run
$2.67
Cost per case
$0.017
Time per case
1m 56s
Measured
2026-10-06
Run this buildOpenRouterHosted
curl https://openrouter.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"mistralai/mistral-large-4-0","provider":{"order":["mistral"],"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.

LeaderboardCompare Mistral Large 4 with another model