Gemini 2.5 Pro vs Qwen3 32B
Wins 5 of 6 areas
Coding · Agents · Reasoning · Long documents · Following instructions
Wins 1 of 6 areas
Facts
Gemini 2.5 Pro is the stronger all-rounder.Qwen3 32B is cheaper and better at facts.
Scores updated · 26 tests both models report · How we compare
Where each one wins
Tests won in each of the six 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 software30Gemini 2.5 Pro3 of 3 tests
- ReasoningHard problems that need careful thinking30Gemini 2.5 Pro3 of 3 tests
- AgentsCarrying out multi-step tasks on its own10Gemini 2.5 Pro1 of 3 tests · 2 ties
- Long documentsFinding answers in very long texts10Gemini 2.5 Pro1 of 1 test
- Following instructionsDoing exactly what it is asked10Gemini 2.5 Pro1 of 1 test
- FactsGetting facts right instead of making them up12Qwen3 32B2 of 3 tests
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.
Qwen3 32B costs 93% less for the same work.
The biggest differences
The tests each model wins by the widest margin, up to three each. Scores are out of 100.
Where Gemini 2.5 Pro pulls ahead
- Hard command-line tasks in a real terminalTerminal-Bench Hard+23.5points ahead
- Command-line tasks in a real terminalTerminal-Bench 2.1+23.3points ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+21.7points ahead
Where Qwen3 32B pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+8.8points 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.
CodingGemini 2.5 Pro
- Terminal-Bench HardGemini 2.5 Pro by 23.526.53+23.5
- Terminal-Bench 2.1Gemini 2.5 Pro by 23.328.55.2+23.3
- SciCodeGemini 2.5 Pro by 10.346.336+10.3
AgentsGemini 2.5 Pro
- τ-Bench V3 · BankingGemini 2.5 Pro by 4.39.75.4+4.3
- GDPValtie00tie
- Terminal-Bench 4.0tie00tie
ReasoningGemini 2.5 Pro
- GPQA DiamondGemini 2.5 Pro by 16.883.666.8+16.8
- Humanity's Last ExamGemini 2.5 Pro by 10.6187.4+10.6
- CritPtGemini 2.5 Pro by 2.32.60.3+2.3
FactsQwen3 32B
- AA-Omniscience · AccuracyGemini 2.5 Pro by 21.73917.4+21.7
- AA-Omniscience · Non-hallucinationQwen3 32B by 8.89.117.9+8.8
- Vectara HHEM hallucination ratelower is betterQwen3 32B by 1.175.9+1.1
Following instructionsGemini 2.5 Pro
- IFBenchGemini 2.5 Pro by 12.448.736.3+12.4
Other results12 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.
- Aider-PolyglotGemini 2.5 Pro by 36.576.540+36.5
- AA-OmniscienceGemini 2.5 Pro by 34.1-16.4-50.4+34.1
- Artificial Analysis Coding IndexGemini 2.5 Pro by 31.446.715.3+31.4
- τ²-Bench Telecom (AA run)Gemini 2.5 Pro by 24.354.129.8+24.3
- AIME 2024Gemini 2.5 Pro by 10.69281.4+10.6
- AIME 2025Gemini 2.5 Pro by 10.18372.9+10.1
- LiveCodeBenchGemini 2.5 Pro by 8.574.265.7+8.5
- AA IntelligenceGemini 2.5 Pro by 6.4158.6+6.4
- MMLU-ProGemini 2.5 Pro by 4.28681.8+4.2
- vectara_factual_consistencyQwen3 32B by 1.19394.1+1.1
- vectara_avg_summary_lengthtie106.4115.8tie
- vectara_answer_ratetie99.199.9tie
Questions people ask
Which is better, Gemini 2.5 Pro or Qwen3 32B?
Gemini 2.5 Pro wins five of the six areas where both have results: coding, agents, reasoning, long documents and following instructions. Qwen3 32B wins facts, and costs 93% less.
Which is better for coding?
Gemini 2.5 Pro. It wins 3 of the 3 coding tests both models report; Qwen3 32B wins none.
Which is cheaper?
Gemini 2.5 Pro costs $1.25 per million input tokens and $10.00 per million output tokens; Qwen3 32B costs $0.16 and $0.64. That makes Qwen3 32B about 93% cheaper for the same work.
How do you compare the two?
We use the 26 benchmark tests both models have published scores on. The verdict counts the 14 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 12 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.