Gemini 3.1 Pro vs Qwen3.5 122B A10B
Wins 7 of 7 areas
Coding · Agents · Reasoning · Facts · Images and charts · Long documents · Following instructions
Wins 0 of 7 areas
—
Gemini 3.1 Pro is the stronger all-rounder.Qwen3.5 122B A10B is cheaper.
Both rank among the ten best models we track in images and charts.
Scores updated · 48 tests both models report · How we compare
Where each one wins
Tests won in each of the seven 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 software80Gemini 3.1 Pro8 of 8 tests
- Images and chartsUnderstanding pictures, charts and video40Gemini 3.1 Pro4 of 4 tests
- AgentsCarrying out multi-step tasks on its own41Gemini 3.1 Pro4 of 5 tests
- ReasoningHard problems that need careful thinking30Gemini 3.1 Pro3 of 3 tests
- FactsGetting facts right instead of making them up20Gemini 3.1 Pro2 of 3 tests · 1 tie
- Following instructionsDoing exactly what it is asked20Gemini 3.1 Pro2 of 2 tests
- Long documentsFinding answers in very long texts10Gemini 3.1 Pro1 of 1 test
Long documents 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.
Qwen3.5 122B A10B costs 74% 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 3.1 Pro pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+36.2points ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+30.5points ahead
- Command-line tasks in a real terminalTerminal-Bench 2.1+26.2points ahead
Where Qwen3.5 122B A10B pulls ahead
- Real work tasks from 44 professionsGDPVal+1.1points ahead
Every test, side by side
All 48 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingGemini 3.1 Pro
- Terminal-Bench 2.1Gemini 3.1 Pro by 26.273.847.6+26.2
- Terminal-Bench HardGemini 3.1 Pro by 22.753.831.1+22.7
- SciCodeGemini 3.1 Pro by 1958.739.7+19
- SWE-bench MultilingualGemini 3.1 Pro by 14.976.962+14.9
- LiveCodeBench v6Gemini 3.1 Pro by 12.891.778.9+12.8
- SWE-bench ProGemini 3.1 Pro by 9.354.244.9+9.3
- LMArena · WebDevGemini 3.1 Pro by 87 rating points14471360+87 rating
- SWE-bench VerifiedGemini 3.1 Pro by 8.680.672+8.6
AgentsGemini 3.1 Pro
- BrowseCompGemini 3.1 Pro by 22.185.963.8+22.1
- OSWorld-VerifiedGemini 3.1 Pro by 18.276.258+18.2
- τ-Bench V3 · BankingGemini 3.1 Pro by 6.121.415.3+6.1
- Terminal-Bench 4.0Gemini 3.1 Pro by 440+4
- GDPValQwen3.5 122B A10B by 1.114.615.7+1.1
ReasoningGemini 3.1 Pro
- Humanity's Last ExamGemini 3.1 Pro by 21.84725.2+21.8
- CritPtGemini 3.1 Pro by 17.117.70.6+17.1
- GPQA DiamondGemini 3.1 Pro by 8.494.185.7+8.4
FactsGemini 3.1 Pro
- AA-Omniscience · Non-hallucinationGemini 3.1 Pro by 36.249.112.9+36.2
- AA-Omniscience · AccuracyGemini 3.1 Pro by 30.554.924.4+30.5
- Vectara HHEM hallucination ratelower is bettertie10.411.2tie
Images and chartsGemini 3.1 Pro
- MMMU-ProGemini 3.1 Pro by 7.482.475+7.4
- CharXiv (RQ)Gemini 3.1 Pro by 6.183.377.2+6.1
- LMArena · VisionGemini 3.1 Pro by 51 rating points12961245+51 rating
- MathVistaGemini 3.1 Pro by 2.890.287.4+2.8
Following instructionsGemini 3.1 Pro
- Multi-ChallengeGemini 3.1 Pro by 9.971.461.5+9.9
- IFBenchGemini 3.1 Pro by 1.477.175.7+1.4
Other results22 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.
- AA-OmniscienceGemini 3.1 Pro by 73.431.9-41.5+73.4
- Artificial Analysis Coding IndexGemini 3.1 Pro by 23.168.845.7+23.1
- t2-benchGemini 3.1 Pro by 19.899.379.5+19.8
- Terminal-Bench 2.0Gemini 3.1 Pro by 19.168.549.4+19.1
- BabyVisionGemini 3.1 Pro by 14.254.440.2+14.2
- AA IntelligenceGemini 3.1 Pro by 14.129.715.6+14.1
- DynaMathQwen3.5 122B A10B by 13.872.185.9+13.8
- GDPval-AA v2Gemini 3.1 Pro by 101 rating points962861+101 rating
- ERQAGemini 3.1 Pro by 8.870.862+8.8
- LVBenchQwen3.5 122B A10B by 8.266.274.4+8.2
- SimpleVQAGemini 3.1 Pro by 8.269.961.7+8.2
- MMMLUGemini 3.1 Pro by 5.992.686.7+5.9
- MMLU-ProGemini 3.1 Pro by 4.39186.7+4.3
- MATH-VisionGemini 3.1 Pro by 3.689.886.2+3.6
- τ³-Bench BankingGemini 3.1 Pro by 2.316.514.2+2.3
- vectara_avg_summary_lengthGemini 3.1 Pro by 21.3 rating points107.786.4+21.3 rating
- τ²-Bench Telecom (AA run)Gemini 3.1 Pro by 295.693.6+2
- vectara_factual_consistencytie89.688.8tie
- AA Agentic Indextie10.39.6tie
- vectara_answer_ratetie99.499.8tie
- EmbSpatial-Benchtie84.283.9tie
- RealWorldQAtie85.485.1tie
Questions people ask
Which is better, Gemini 3.1 Pro or Qwen3.5 122B A10B?
Gemini 3.1 Pro wins all seven areas where both have results: coding, agents, reasoning, facts, images and charts, long documents and following instructions. Qwen3.5 122B A10B wins none, but costs 74% less.
Which is better for coding?
Gemini 3.1 Pro. It wins 8 of the 8 coding tests both models report; Qwen3.5 122B A10B wins none.
Which is cheaper?
Gemini 3.1 Pro costs $2.00 per million input tokens and $12.00 per million output tokens; Qwen3.5 122B A10B costs $0.40 and $3.20. That makes Qwen3.5 122B A10B about 74% cheaper for the same work.
How do you compare the two?
We use the 48 benchmark tests both models have published scores on. The verdict counts the 26 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 22 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.