Qwen3.8 27B

qwen3-8-27b

openai1 build benchmarkedbest build openai45 tok/s
best build

Scores at a glance

overall48
Tool Calling6516/27
Structured Output4813/27
RAG / Retrieval QA5916/27
Context Recall9417/18
Coding72/27
Reasoning & Math329/28
Instruction Following257/28
Classification3811/29
Summarization6217/27
0255075100

0–100 per task · n/m = cases passed (scores credit partial passes) · overall = mean across tasks

best build
config
deployment

openai

quantization
harness
openai
context
memory
throughput
45 tok/s
cost / run
$0
provider
openai
run
2026-08-17
run this buildopenaihosted
curl https://openrouter.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"qwen3-8-27b","messages":[{"role":"user","content":"Hello"}]}'

Hosted API — not self-hostable. This is the call the benchmark made; try it live in the Playground.

record
per-test results

Full run record

Per-test scores, full transcripts, and the reproduce recipe.

open the run record →