Leaderboard
Language ModelsOpen weights
Qwen3.6-35B-A3B
Open-weights hybrid-MoE Qwen3.6 (35B total / 3B active), Apache-2.0.
Crosshair Index
68.0
#14 of 32 · Language Models
- Provider
- Alibaba Qwen
- Released
- 2026-04-16
- Parameters
- 35B
- Context
- 262.144K tokens
Token pricing
- Input
- $0.25 /1M
- Output
- $1.49 /1M
USD per 1M tokens · cache read = cached input (hit), cache write = caching surcharge · official list pricing (June 2026).
Industry skill web
Professional-domain strengths, composed from the benchmarks relevant to each field. Highlight an axis to see the benchmarks behind it.
Investment Banking
86
skill
Financial analysis over filings and credit agreements — valuation math, document QA, and the quantitative reasoning behind deals.
Scorecard
| Benchmark | Score | Source | Status |
|---|---|---|---|
| GPQA Diamond Reasoning | 86% | Alibaba — Qwen3.6-35B-A3B model cardvendor | unverified |
| Humanity's Last Exam Frontier | 21.4% | Alibaba — Qwen3.6-35B-A3B model cardvendor | unverified |
| SWE-bench Verified Agentic Coding | 73.4% | Alibaba — Qwen3.6-35B-A3B model cardvendor | unverified |
| LiveCodeBench Coding | 80.4% | Alibaba — Qwen3.6-35B-A3B model cardvendor | unverified |
| MMLU-Pro Knowledge | 85.2% | Alibaba — Qwen3.6-35B-A3B model cardvendor | unverified |
| LMArena Elo Human Preference | — | not evaluated | |
| AA Intelligence Index Composite | 43 | Artificial Analysis3rd-party | unverified |
| Corporate Finance Finance | — | not evaluated | |
| LegalBench Law | — | not evaluated | |
| TaxEval Tax & Accounting | — | not evaluated | |
| Medical Coding Medicine | — | not evaluated |