Qwen 3.5 Flash (hosted 35B-A3B)
Qwen 3.5 Flash (hosted 35B-A3B) is an API-only (closed weights) language model from Qwen, released February 25, 2026. The context window is 1M tokens. On the Epoch Capabilities Index it scores 143.8, rank 104 of 256 rated models. API price: $0.1 input / $0.4 output per million tokens.
Check it against your own PC →
Lab
Qwen
Released
February 25, 2026
Weights
API-only (closed weights)
Parameters
–
Context
1M
Price / M tokens
$0.1 / $0.4 in / out
Epoch ECI
143.8 #104
Strengths by category
ModelTape's 0–100 fit on Epoch AI benchmark results.
| Category | Score | Based on |
|---|---|---|
| Reasoning | 12.0 | Chess Puzzles, Mystery Game Puzzles |
| Math | 32.2 | OTIS Mock AIME 2024-2025, FrontierMath-Tier-4-2025-07-01-Private, FrontierMath-Tiers-1-3-v2-Private |
| Knowledge | 62.3 | GPQA diamond, SimpleQA Verified |
Benchmark results
| Benchmark (Epoch AI) | Score |
|---|---|
| OTIS Mock AIME | 84.4% |
| GPQA Diamond | 79.6% |
| SimpleQA Verified | 20.3% |
| FrontierMath (Tiers 1–3) | 19.2% |
| Mystery Game Puzzles | 11.9% |
| Chess Puzzles | 9.5% |
| FrontierMath-Tier-4-2025-07-01-Private | 0.0% |
Links
Models with a similar score
MiniMax-M3 · Claude Sonnet 4.5 · o3-pro · Qwen 3.5 Plus (hosted 397B-A17B) · o3 · Nemotron 3 Ultra · Grok 4 · DeepSeek-V4-Flash
More from Qwen
Qwen3.8 Omni Flash · Qwen3.8 Max (0902) · Qwen3.8 Flash · Qwen3.8 Flash Next · Qwen 3.8 27B · Qwen3.8-2.4T-A95B · Qwen 3.8 Max · Qwen3.7 Flash