Benchmark Almanac

Qwen3.5-35B-A3B-Base

Qwen3.5-35B-A3B-Base places in the top three on 2 benchmarks.

Qwen Released February 24th, 2026 The lab's model card Compare with others
9
Benchmarks with a score
0
Ranked first, out of five or more models
2
In the top three
Qwen Feb 2026

Qwen3.5-35B-A3B-Base

Open weights Mid-size

No Epoch Capabilities Index score yet
  • Angry Tweets 56.1% #46 /149
  • QIMMA 59% #11 /44
  • FoSent 64.9% #28 /147

How does it do against its rivals?

Qwen3.5-35B-A3B-Base beats Gemma 4 E2B on 7 of the 8 benchmarks they share. Gemma 4 31B IT does best against it, ahead on 8 of 8.

  1. Gemma 4 E2B 7 ahead, 1 behind Compare
  2. Gemma 4 E4B 7 ahead, 1 behind Compare
  3. Gemma 4 26B A4B 4 ahead, 4 behind Compare
  4. Gemma 4 31B IT 0 ahead, 8 behind Compare

Sources: Official leaderboards, Epoch AI (CC BY 4.0) and labs’ model cards

Where it ranks

Its best score on each benchmark, and where that ranks among every model with a score there. We rank each model once, at its best setting.

Knowledge and language

BenchmarkScoreRankSource
Uncheatable Eval 6.52 #2 of 33 Official leaderboard
NorEval 62.6 #2 of 19 Official leaderboard
Open Hebrew LLM Leaderboard 69.2 #10 of 88 Official leaderboard
HeQ 82.1% #11 of 88 Official leaderboard
FoSent 64.9% #28 of 147 Official leaderboard
QIMMA 59% #11 of 44 Official leaderboard
Angry Tweets 56.1% #46 of 149 Official leaderboard
EuroEval ERRNews 28.0 #48 of 76 Official leaderboard

Safety and security

BenchmarkScoreRankSource
nocot-bench (NCRI) 64.5 #127 of 201 Official leaderboard

Who measured it?

Independent runs cover all 9 of its benchmarks.

  • An independent run only 9
Official leaderboards scored it on 9.

Sources: Official leaderboards, Epoch AI (CC BY 4.0) and labs’ model cards