EXAONE 4.5 33B vs Qwen3.5 35B A3B
Wins 0 of 8 areas
—
Wins 5 of 8 areas
Coding · Reasoning · Images and charts · Long documents · Following instructions
Qwen3.5 35B A3B is the stronger all-rounder.
Scores updated · 26 tests both models report · How we compare
Where each one wins
Tests won in each of the eight areas we test. Each piece is one test, so a longer bar means more evidence; grey means the two scored within a point of each other.
- Images and chartsUnderstanding pictures, charts and video04Qwen3.5 35B A3B4 of 4 tests
- CodingWriting and fixing software13Qwen3.5 35B A3B3 of 4 tests
- ReasoningHard problems that need careful thinking02Qwen3.5 35B A3B2 of 3 tests · 1 tie
- Long documentsFinding answers in very long texts01Qwen3.5 35B A3B1 of 1 test
- Following instructionsDoing exactly what it is asked01Qwen3.5 35B A3B1 of 1 test
- AgentsCarrying out multi-step tasks on its own11Even1 each
- FactsGetting facts right instead of making them up11Even1 each
- MathCompetition and research-level math00Even0 each · 1 tie
Math, long documents and following instructions 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 three tests each model wins by the widest margin. Scores are out of 100.
Where Qwen3.5 35B A3B pulls ahead
- Command-line tasks in a real terminalTerminal-Bench 2.1+19.5points ahead
- Reasons across sets of long documentsAA-LCR+17.3points ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+14.5points ahead
Where EXAONE 4.5 33B pulls ahead
- Recent programming contest problemsLiveCodeBench v6+6.8points ahead
- Customer-service tasks in a simulated bankτ-Bench V3 · Banking+6.2points ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+5.5points ahead
Every test, side by side
All 26 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingQwen3.5 35B A3B
- Terminal-Bench 2.1Qwen3.5 35B A3B by 19.521.340.8+19.5
- SciCodeQwen3.5 35B A3B by 9.72837.7+9.7
- LiveCodeBench v6EXAONE 4.5 33B by 6.881.474.6+6.8
- Terminal-Bench HardQwen3.5 35B A3B by 620.526.5+6
AgentsEven
- τ-Bench V3 · BankingEXAONE 4.5 33B by 6.211.14.9+6.2
- GDPValQwen3.5 35B A3B by 5.605.6+5.6
ReasoningQwen3.5 35B A3B
- Humanity's Last ExamQwen3.5 35B A3B by 8.112.921+8.1
- GPQA DiamondQwen3.5 35B A3B by 5.179.484.5+5.1
- CritPttie0.30.9tie
FactsEven
- AA-Omniscience · Non-hallucinationEXAONE 4.5 33B by 5.520.114.6+5.5
- AA-Omniscience · AccuracyQwen3.5 35B A3B by 3.916.220.1+3.9
Images and chartsQwen3.5 35B A3B
Following instructionsQwen3.5 35B A3B
- IFBenchQwen3.5 35B A3B by 14.55872.5+14.5
Other results8 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.
- Artificial Analysis Coding IndexQwen3.5 35B A3B by 13.423.637+13.4
- τ²-Bench Telecom (AA run)Qwen3.5 35B A3B by 11.178.189.2+11.1
- AA IntelligenceQwen3.5 35B A3B by 6.113.219.3+6.1
- AI2DQwen3.5 35B A3B by 3.68992.6+3.6
- AA-OmniscienceQwen3.5 35B A3B by 2.6-50.7-48.1+2.6
- IFEvalQwen3.5 35B A3B by 2.389.691.9+2.3
- AA Agentic IndexQwen3.5 35B A3B by 2.19.711.8+2.1
- MMLU-ProQwen3.5 35B A3B by 283.385.3+2
Questions people ask
Which is better, EXAONE 4.5 33B or Qwen3.5 35B A3B?
Qwen3.5 35B A3B wins five of the eight areas we test: coding, reasoning, images and charts, long documents and following instructions. EXAONE 4.5 33B wins none. They are level on agents, facts and math.
Which is better for coding?
Qwen3.5 35B A3B. It wins 3 of the 4 coding tests both models report; EXAONE 4.5 33B wins 1.
How do you compare the two?
We use the 26 benchmark tests both models have published scores on. The verdict counts the 18 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 8 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.