Qwen3.5 122B A10B vs Qwen3.7 Plus Preview
Wins 1 of 7 areas
Long documents
Wins 5 of 7 areas
Coding · Agents · Reasoning · Images and charts · Following instructions
Qwen3.7 Plus Preview is the stronger all-rounder.Qwen3.5 122B A10B is better at long documents.
Scores updated · 50 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 software07Qwen3.7 Plus Preview7 of 7 tests
- ReasoningHard problems that need careful thinking03Qwen3.7 Plus Preview3 of 3 tests
- Images and chartsUnderstanding pictures, charts and video03Qwen3.7 Plus Preview3 of 3 tests
- AgentsCarrying out multi-step tasks on its own13Qwen3.7 Plus Preview3 of 4 tests
- Following instructionsDoing exactly what it is asked01Qwen3.7 Plus Preview1 of 1 test
- Long documentsFinding answers in very long texts10Qwen3.5 122B A10B1 of 1 test
- FactsGetting facts right instead of making them up11Even1 each
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.
Qwen3.7 Plus Preview costs 44% less for the same work.
The biggest differences
The three tests each model wins by the widest margin. Scores are out of 100.
Where Qwen3.7 Plus Preview pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+59.4points ahead
- Hard command-line tasks in a real terminalTerminal-Bench Hard+15.9points ahead
- Completes tasks by operating a computer desktopOSWorld-Verified+15.3points ahead
Where Qwen3.5 122B A10B pulls ahead
- Reasons across sets of long documentsAA-LCR+3.3points ahead
- Real work tasks from 44 professionsGDPVal+2.3points ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+1.9points ahead
Every test, side by side
All 50 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingQwen3.7 Plus Preview
- Terminal-Bench HardQwen3.7 Plus Preview by 15.931.147+15.9
- SWE-bench MultilingualQwen3.7 Plus Preview by 13.86275.8+13.8
- Terminal-Bench 2.1Qwen3.7 Plus Preview by 13.447.661+13.4
- SWE-bench ProQwen3.7 Plus Preview by 12.744.957.6+12.7
- LiveCodeBench v6Qwen3.7 Plus Preview by 10.778.989.6+10.7
- SciCodeQwen3.7 Plus Preview by 6.439.746.1+6.4
- SWE-bench VerifiedQwen3.7 Plus Preview by 5.77277.7+5.7
AgentsQwen3.7 Plus Preview
- OSWorld-VerifiedQwen3.7 Plus Preview by 15.35873.3+15.3
- GDPValQwen3.5 122B A10B by 2.315.713.4+2.3
- τ-Bench V3 · BankingQwen3.7 Plus Preview by 2.215.317.5+2.2
- Terminal-Bench 4.0Qwen3.7 Plus Preview by 101+1
ReasoningQwen3.7 Plus Preview
- Humanity's Last ExamQwen3.7 Plus Preview by 10.425.235.6+10.4
- CritPtQwen3.7 Plus Preview by 8.50.69.1+8.5
- GPQA DiamondQwen3.7 Plus Preview by 4.385.790+4.3
FactsEven
- AA-Omniscience · Non-hallucinationQwen3.7 Plus Preview by 59.412.972.3+59.4
- AA-Omniscience · AccuracyQwen3.5 122B A10B by 1.924.422.5+1.9
Images and chartsQwen3.7 Plus Preview
- CharXiv (RQ)Qwen3.7 Plus Preview by 8.777.285.9+8.7
- MMMU-ProQwen3.7 Plus Preview by 5.57580.5+5.5
- LMArena · VisionQwen3.7 Plus Preview by 33 rating points12441277+33 rating
Following instructionsQwen3.7 Plus Preview
- IFBenchQwen3.7 Plus Preview by 2.375.778+2.3
Other results29 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-OmniscienceQwen3.7 Plus Preview by 42.6-41.51.1+42.6
- DeepPlanningQwen3.7 Plus Preview by 38.224.162.3+38.2
- BabyVisionQwen3.7 Plus Preview by 30.240.270.4+30.2
- Terminal-Bench 2.0Qwen3.7 Plus Preview by 20.949.470.3+20.9
- SimpleVQAQwen3.7 Plus Preview by 2061.781.7+20
- VITA-BenchQwen3.7 Plus Preview by 1233.645.6+12
- Artificial Analysis Coding IndexQwen3.7 Plus Preview by 10.245.755.9+10.2
- AA Agentic IndexQwen3.7 Plus Preview by 10.19.619.7+10.1
- AA IntelligenceQwen3.7 Plus Preview by 9.615.625.2+9.6
- GDP (Surge AI)Qwen3.7 Plus Preview by 8.83.412.2+8.8
- ScreenSpot-Pro (No tools)Qwen3.7 Plus Preview by 8.670.479+8.6
- ERQAQwen3.7 Plus Preview by 7.86269.8+7.8
- HLE-DiamondQwen3.7 Plus Preview by 6.67.313.9+6.6
- WMT24++Qwen3.7 Plus Preview by 6.378.384.6+6.3
- SuperGPQAQwen3.7 Plus Preview by 4.367.171.4+4.3
- MATH-VisionQwen3.7 Plus Preview by 4.186.290.3+4.1
- VideoMMMUQwen3.7 Plus Preview by 3.48285.4+3.4
- MMLU-ProXQwen3.7 Plus Preview by 3.282.285.4+3.2
- MMMLUQwen3.7 Plus Preview by 2.386.789+2.3
- LVBenchQwen3.7 Plus Preview by 1.874.476.2+1.8
- MMLU-ProQwen3.7 Plus Preview by 1.886.788.5+1.8
- RealWorldQAQwen3.7 Plus Preview by 1.885.186.9+1.8
- OmniDocBench 1.5Qwen3.7 Plus Preview by 1.689.891.4+1.6
- IFEvalQwen3.7 Plus Preview by 1.293.494.6+1.2
- BFCLv4tie72.272.9tie
- τ²-Bench Telecom (AA run)tie93.693tie
- MMLU-Reduxtie9494.5tie
- Includetie82.883tie
- MLVUtie87.387.4tie
Questions people ask
Which is better, Qwen3.5 122B A10B or Qwen3.7 Plus Preview?
Qwen3.7 Plus Preview wins five of the seven areas where both have results: coding, agents, reasoning, images and charts and following instructions. Qwen3.5 122B A10B wins long documents. They are level on facts.
Which is better for coding?
Qwen3.7 Plus Preview. It wins 7 of the 7 coding tests both models report; Qwen3.5 122B A10B wins none.
Which is cheaper?
Qwen3.5 122B A10B costs $0.40 per million input tokens and $3.20 per million output tokens; Qwen3.7 Plus Preview costs $0.40 and $1.60. That makes Qwen3.7 Plus Preview about 44% cheaper for the same work.
How do you compare the two?
We use the 50 benchmark tests both models have published scores on. The verdict counts the 21 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 29 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.