MAI-Thinking-1 vs Qwen3.5 35B A3B
Wins 3 of 5 areas
Coding · Math · Long documents
Wins 1 of 5 areas
Following instructions
MAI-Thinking-1 is the stronger all-rounder.Qwen3.5 35B A3B is better at following instructions.
Scores updated · 13 tests both models report · How we compare
Where each one wins
Tests won in each of the five areas where both have results. Each piece is one test, so a longer bar means more evidence; grey means the two scored within a point of each other.
- CodingWriting and fixing software30MAI-Thinking-13 of 3 tests
- MathCompetition and research-level math20MAI-Thinking-12 of 2 tests
- Long documentsFinding answers in very long texts10MAI-Thinking-11 of 1 test
- Following instructionsDoing exactly what it is asked02Qwen3.5 35B A3B2 of 2 tests
- ReasoningHard problems that need careful thinking00Even0 each · 1 tie
Reasoning and long documents rest on a single test each.
What it costs
Prices per million tokens, roughly 750,000 words. The bars show the cost of a million tokens read plus a million written.
The biggest differences
The tests each model wins by the widest margin, up to three each. Scores are out of 100.
Where MAI-Thinking-1 pulls ahead
- Recent programming contest problemsLiveCodeBench v6+13.1points ahead
- Long, multi-file coding tasks in real codebasesSWE-bench Pro+8.2points ahead
- Fixes real GitHub issues in Python projectsSWE-bench Verified+4.3points ahead
Where Qwen3.5 35B A3B pulls ahead
- Keeps track of context across a multi-turn chatMulti-Challenge+7points ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+3.5points ahead
Every test, side by side
All 13 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingMAI-Thinking-1
- LiveCodeBench v6MAI-Thinking-1 by 13.187.774.6+13.1
- SWE-bench ProMAI-Thinking-1 by 8.252.844.6+8.2
- SWE-bench VerifiedMAI-Thinking-1 by 4.373.569.2+4.3
MathMAI-Thinking-1
- HMMT Feb. 2026MAI-Thinking-1 by 3.184.981.8+3.1
- AIME 2026MAI-Thinking-1 by 1.294.593.3+1.2
Following instructionsQwen3.5 35B A3B
- Multi-ChallengeQwen3.5 35B A3B by 75360+7
- IFBenchQwen3.5 35B A3B by 3.56972.5+3.5
Other results4 tests, not counted
Tests outside the eight areas. They are not counted above: several are summary scores built from other tests, or the same test under another name.
- HumanEvalMAI-Thinking-1 by 17.784.266.5+17.7
- MMLUMAI-Thinking-1 by 6.587.681.1+6.5
- Terminal-Bench 2.0MAI-Thinking-1 by 5.54640.5+5.5
- MMLU-Protie8585.3tie
Questions people ask
Which is better, MAI-Thinking-1 or Qwen3.5 35B A3B?
MAI-Thinking-1 wins three of the five areas where both have results: coding, math and long documents. Qwen3.5 35B A3B wins following instructions. They are level on reasoning.
Which is better for coding?
MAI-Thinking-1. It wins 3 of the 3 coding tests both models report; Qwen3.5 35B A3B wins none.
How do you compare the two?
We use the 13 benchmark tests both models have published scores on. The verdict counts the 9 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 4 are listed but not counted, because several are summary scores or repeat a test. Each score is the one shown on the model's own page.