Qwen3.6 35B A3B
qwen/qwen3.6-35b-a3b
starter@v1HostedOpenRouterserved by AkashMLFP8256K context2026-10-30 18:52 UTC26
37 of 153 test cases fully passed
159.9tok/s
Mean per test case, 156 tok/s over the run
9.7Ktokens
Answer plus reasoning
9.3Ktokens
96% of the output
2.9M
1.4M in, 1.5M out
2h 45m
1m 5s per caseSum of request times
$1.47
$0.0096 per caseAt the provider's list price
Every test case
One square per test case. Select a square to read the answer.
24Agents4 of 21 passed
43Structured Extraction9 of 21 passed
3Coding0 of 21 passed
33Grounded Answers7 of 21 passed
32Instruction Following4 of 21 passed
29Business Logic6 of 21 passed
46Security & permissions7 of 21 passed
0Diagnosis & investigation0 of 6 passed
Speed and output per test case
One bar per test case. Hover a bar to see its numbers. Select it to read the answer.
Peak 229 tok/s
ReasoningAnswer
Test by test
Every answer with its reasoning and the checks it had to pass.
Reproduce this run
The prompts stay private so models can't train on them. The hashes pin the exact suite and config this run used.
OpenRouterHosted
curl https://openrouter.ai/api/v1/chat/completions \
-H "Authorization: Bearer $OPENROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"qwen/qwen3.6-35b-a3b","provider":{"order":["akashml/fp8"],"allow_fallbacks":false},"service_tier":"default","messages":[{"role":"user","content":"Hello"}]}'The request the benchmark sent, pinned to the provider that served it.
Configuration
Where the suite ran, and the token budget each task got.
- Hosted
- OpenRouter
- AkashML
- FP8
- 256K
- Not set
- v1.0.0
- 2026-10-30 18:52 UTC
{
"provider": {
"order": [
"akashml/fp8"
],
"allow_fallbacks": false
},
"service_tier": "default"
}| Task | Reasoning | Max output per call |
|---|---|---|
| Agents | 4.1K | 12.3K |
| Structured Extraction | 4.1K | 12.3K |
| Coding | 4.1K | 12.3K |
| Grounded Answers | 4.1K | 12.3K |
| Instruction Following | 4.1K | 12.3K |
| Business Logic | 4.1K | 12.3K |
| Security & permissions | 4.1K | 12.3K |
| Diagnosis & investigation | 4.1K | 12.3K |