Gemini 2.5 Pro vs Qwen3 235B A22B
Wins 5 of 6 areas
Coding · Reasoning · Facts · Long documents · Following instructions
Wins 1 of 6 areas
Agents
Gemini 2.5 Pro is the stronger all-rounder.Qwen3 235B A22B is cheaper and better at agents.
Scores updated · 40 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
- FactsGetting facts right instead of making them up31Gemini 2.5 Pro3 of 4 tests
- Long documentsFinding answers in very long texts20Gemini 2.5 Pro2 of 2 tests
- Following instructionsDoing exactly what it is asked20Gemini 2.5 Pro2 of 2 tests
- AgentsCarrying out multi-step tasks on its own01Qwen3 235B A22B1 of 1 test
Agents rests on a single test.
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 235B A22B costs 69% 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
- Fixes real GitHub issues in Python projectsSWE-bench Verified+28.8points ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+20.6points ahead
- Hard command-line tasks in a real terminalTerminal-Bench Hard+20.4points ahead
Where Qwen3 235B A22B pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+13.3points ahead
Every test, side by side
All 40 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingGemini 2.5 Pro
- SWE-bench VerifiedGemini 2.5 Pro by 28.863.234.4+28.8
- Terminal-Bench HardGemini 2.5 Pro by 20.426.56.1+20.4
- SciCodeGemini 2.5 Pro by 6.446.339.9+6.4
ReasoningGemini 2.5 Pro
- GPQA DiamondGemini 2.5 Pro by 13.683.670+13.6
- Humanity's Last ExamGemini 2.5 Pro by 71811+7
- CritPtGemini 2.5 Pro by 2.62.60+2.6
FactsGemini 2.5 Pro
- AA-Omniscience · AccuracyGemini 2.5 Pro by 20.63918.5+20.6
- SimpleQA VerifiedGemini 2.5 Pro by 15.65640.4+15.6
- AA-Omniscience · Non-hallucinationQwen3 235B A22B by 13.39.122.4+13.3
- Vectara HHEM hallucination ratelower is betterGemini 2.5 Pro by 2.379.3+2.3
Long documentsGemini 2.5 Pro
- AA-LCRGemini 2.5 Pro by 69690+69
- LongBench v2Gemini 2.5 Pro by 8.758.850.1+8.7
Following instructionsGemini 2.5 Pro
- Multi-ChallengeGemini 2.5 Pro by 12.453.641.2+12.4
- IFBenchGemini 2.5 Pro by 1048.738.7+10
Other results25 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.
- ZebraLogicGemini 2.5 Pro by 53.991.637.7+53.9
- HMMT 2025Gemini 2.5 Pro by 53.865.711.9+53.8
- OpenAI-MRCR (128k)Gemini 2.5 Pro by 49.176.827.7+49.1
- SimpleQAGemini 2.5 Pro by 37.650.813.2+37.6
- τ²-BenchGemini 2.5 Pro by 31.95422.1+31.9
- τ²-Bench Telecom (AA run)Gemini 2.5 Pro by 30.154.124+30.1
- Artificial Analysis Coding IndexGemini 2.5 Pro by 29.346.717.4+29.3
- AA-OmniscienceGemini 2.5 Pro by 28.4-16.4-44.7+28.4
- HMMT Feb. 2025Gemini 2.5 Pro by 18.380.862.5+18.3
- MMLU-ProGemini 2.5 Pro by 17.88668.2+17.8
- TAU-bench (airline)Gemini 2.5 Pro by 15.35034.7+15.3
- AA Agentic IndexQwen3 235B A22B by 14.93.518.4+14.9
- LiveCodeBench (24/8~25/5)Gemini 2.5 Pro by 11.277.165.9+11.2
- TAU-bench (retail)Gemini 2.5 Pro by 8.46758.6+8.4
- MATH-500 (EM)Gemini 2.5 Pro by 7.698.891.2+7.6
- AIME 2024Gemini 2.5 Pro by 6.39285.7+6.3
- AA IntelligenceGemini 2.5 Pro by 5.5159.5+5.5
- livecodebench_hardGemini 2.5 Pro by 5.459.454+5.4
- vectara_answer_rateGemini 2.5 Pro by 4.299.194.9+4.2
- LiveCodeBenchGemini 2.5 Pro by 3.574.270.7+3.5
- vectara_factual_consistencyGemini 2.5 Pro by 2.39390.7+2.3
- livecodebench_mediumGemini 2.5 Pro by 1.890.688.8+1.8
- AIME 2025Gemini 2.5 Pro by 1.58381.5+1.5
- livecodebench_easytie98.899.1tie
- vectara_avg_summary_lengthtie106.4105.6tie
Questions people ask
Which is better, Gemini 2.5 Pro or Qwen3 235B A22B?
Gemini 2.5 Pro wins five of the six areas where both have results: coding, reasoning, facts, long documents and following instructions. Qwen3 235B A22B wins agents, and costs 69% less.
Which is better for coding?
Gemini 2.5 Pro. It wins 3 of the 3 coding tests both models report; Qwen3 235B A22B wins none.
Which is cheaper?
Gemini 2.5 Pro costs $1.25 per million input tokens and $10.00 per million output tokens; Qwen3 235B A22B costs $0.70 and $2.80. That makes Qwen3 235B A22B about 69% cheaper for the same work.
How do you compare the two?
We use the 40 benchmark tests both models have published scores on. The verdict counts the 15 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 25 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.