Qwen3.5 122B A10B vs Qwen3.5 2B
Wins 6 of 7 areas
Coding · Agents · Reasoning · Images and charts · Long documents · Following instructions
Wins 0 of 7 areas
—
Qwen3.5 122B A10B is the stronger all-rounder.
Scores updated · 37 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.
- Images and chartsUnderstanding pictures, charts and video40Qwen3.5 122B A10B4 of 4 tests
- CodingWriting and fixing software30Qwen3.5 122B A10B3 of 3 tests
- ReasoningHard problems that need careful thinking20Qwen3.5 122B A10B2 of 3 tests · 1 tie
- AgentsCarrying out multi-step tasks on its own20Qwen3.5 122B A10B2 of 2 tests
- Long documentsFinding answers in very long texts20Qwen3.5 122B A10B2 of 2 tests
- Following instructionsDoing exactly what it is asked20Qwen3.5 122B A10B2 of 2 tests
- FactsGetting facts right instead of making them up11Even1 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 tests each model wins by the widest margin, up to three each. Scores are out of 100.
Where Qwen3.5 122B A10B pulls ahead
- Reasons across sets of long documentsAA-LCR+55.3points ahead
- Command-line tasks in a real terminalTerminal-Bench 2.1+44.6points ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+44.2points ahead
Where Qwen3.5 2B pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+12.9points ahead
Every test, side by side
All 37 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingQwen3.5 122B A10B
- Terminal-Bench 2.1Qwen3.5 122B A10B by 44.647.63+44.6
- SciCodeQwen3.5 122B A10B by 36.939.72.8+36.9
- Terminal-Bench HardQwen3.5 122B A10B by 27.331.13.8+27.3
AgentsQwen3.5 122B A10B
- GDPValQwen3.5 122B A10B by 15.715.70+15.7
- τ-Bench V3 · BankingQwen3.5 122B A10B by 12.815.32.5+12.8
ReasoningQwen3.5 122B A10B
- GPQA DiamondQwen3.5 122B A10B by 40.185.745.6+40.1
- Humanity's Last ExamQwen3.5 122B A10B by 22.625.22.6+22.6
- CritPttie0.60tie
FactsEven
- AA-Omniscience · AccuracyQwen3.5 122B A10B by 16.324.48.1+16.3
- AA-Omniscience · Non-hallucinationQwen3.5 2B by 12.912.925.8+12.9
Images and chartsQwen3.5 122B A10B
Long documentsQwen3.5 122B A10B
- AA-LCRQwen3.5 122B A10B by 55.376.321+55.3
- LongBench v2Qwen3.5 122B A10B by 21.560.238.7+21.5
Following instructionsQwen3.5 122B A10B
- IFBenchQwen3.5 122B A10B by 44.275.731.5+44.2
- Multi-ChallengeQwen3.5 122B A10B by 27.861.533.7+27.8
Other results19 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 122B A10B by 42.845.72.9+42.8
- BFCLv4Qwen3.5 122B A10B by 38.372.233.9+38.3
- WMT24++Qwen3.5 122B A10B by 32.578.345.8+32.5
- t2-benchQwen3.5 122B A10B by 30.779.548.8+30.7
- MMLU-ProXQwen3.5 122B A10B by 29.982.252.3+29.9
- SuperGPQAQwen3.5 122B A10B by 29.667.137.5+29.6
- IncludeQwen3.5 122B A10B by 27.482.855.4+27.4
- SimpleVQAQwen3.5 122B A10B by 26.561.735.2+26.5
- τ²-Bench Telecom (AA run)Qwen3.5 122B A10B by 24.693.669+24.6
- MMMLUQwen3.5 122B A10B by 23.686.763.1+23.6
- OCRBench v2_enQwen3.5 122B A10B by 20.668.347.7+20.6
- MMLU-ProQwen3.5 122B A10B by 20.286.766.5+20.2
- RealWorldQAQwen3.5 122B A10B by 2085.165.1+20
- IFEvalQwen3.5 122B A10B by 19.893.473.6+19.8
- AA-OmniscienceQwen3.5 122B A10B by 18.7-41.5-60.2+18.7
- C-EvalQwen3.5 122B A10B by 18.791.973.2+18.7
- HallusionBenchQwen3.5 122B A10B by 18.367.649.3+18.3
- MMLU-ReduxQwen3.5 122B A10B by 14.49479.6+14.4
- AA IntelligenceQwen3.5 122B A10B by 8.715.66.9+8.7
Questions people ask
Which is better, Qwen3.5 122B A10B or Qwen3.5 2B?
Qwen3.5 122B A10B wins six of the seven areas where both have results: coding, agents, reasoning, images and charts, long documents and following instructions. Qwen3.5 2B wins none. They are level on facts.
Which is better for coding?
Qwen3.5 122B A10B. It wins 3 of the 3 coding tests both models report; Qwen3.5 2B wins none.
How do you compare the two?
We use the 37 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 19 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.