Claude Sonnet 4 vs Qwen3.5 122B A10B
Wins 0 of 7 areas
—
Wins 6 of 7 areas
Coding · Agents · Reasoning · Images and charts · Long documents · Following instructions
Qwen3.5 122B A10B is the stronger all-rounder.
Scores updated · 39 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 software04Qwen3.5 122B A10B4 of 7 tests · 3 ties
- Images and chartsUnderstanding pictures, charts and video03Qwen3.5 122B A10B3 of 3 tests
- AgentsCarrying out multi-step tasks on its own13Qwen3.5 122B A10B3 of 4 tests
- ReasoningHard problems that need careful thinking02Qwen3.5 122B A10B2 of 3 tests · 1 tie
- Following instructionsDoing exactly what it is asked02Qwen3.5 122B A10B2 of 2 tests
- Long documentsFinding answers in very long texts01Qwen3.5 122B A10B1 of 1 test
- FactsGetting facts right instead of making them up11Even1 each · 1 tie
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 80% 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 Qwen3.5 122B A10B pulls ahead
- Finds hard-to-locate facts by browsing the webBrowseComp+51.6points ahead
- Recent programming contest problemsLiveCodeBench v6+30.4points ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+21points ahead
Where Claude Sonnet 4 pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+58points ahead
- Customer-service tasks in a simulated bankτ-Bench V3 · Banking+1.4points ahead
Every test, side by side
All 39 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingQwen3.5 122B A10B
- LiveCodeBench v6Qwen3.5 122B A10B by 30.448.578.9+30.4
- Terminal-Bench 2.1Qwen3.5 122B A10B by 11.336.347.6+11.3
- SWE-bench MultilingualQwen3.5 122B A10B by 5.156.962+5.1
- SWE-bench ProQwen3.5 122B A10B by 2.242.744.9+2.2
- SWE-bench Verifiedtie72.772tie
- SciCodetie4039.7tie
- Terminal-Bench Hardtie31.131.1tie
AgentsQwen3.5 122B A10B
- BrowseCompQwen3.5 122B A10B by 51.612.263.8+51.6
- OSWorld-VerifiedQwen3.5 122B A10B by 15.842.258+15.8
- GDPValQwen3.5 122B A10B by 6.19.615.7+6.1
- τ-Bench V3 · BankingClaude Sonnet 4 by 1.416.715.3+1.4
ReasoningQwen3.5 122B A10B
- Humanity's Last ExamQwen3.5 122B A10B by 14.510.725.2+14.5
- GPQA DiamondQwen3.5 122B A10B by 877.785.7+8
- CritPttie0.30.6tie
FactsEven
- AA-Omniscience · Non-hallucinationClaude Sonnet 4 by 5870.912.9+58
- AA-Omniscience · AccuracyQwen3.5 122B A10B by 1.722.724.4+1.7
- Vectara HHEM hallucination ratelower is bettertie10.311.2tie
Images and chartsQwen3.5 122B A10B
- MMMU-ProQwen3.5 122B A10B by 13.261.875+13.2
- MMMUQwen3.5 122B A10B by 9.574.483.9+9.5
- LMArena · VisionQwen3.5 122B A10B by 54 rating points11911245+54 rating
Following instructionsQwen3.5 122B A10B
- IFBenchQwen3.5 122B A10B by 2154.775.7+21
- Multi-ChallengeQwen3.5 122B A10B by 4.457.161.5+4.4
Other results16 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.
- HMMT 2025Qwen3.5 122B A10B by 74.415.990.3+74.4
- AA-OmniscienceClaude Sonnet 4 by 41.70.2-41.5+41.7
- BrowseComp-ZHQwen3.5 122B A10B by 40.829.169.9+40.8
- τ²-Bench Telecom (AA run)Qwen3.5 122B A10B by 2964.693.6+29
- OJBenchQwen3.5 122B A10B by 24.215.339.5+24.2
- SuperGPQAQwen3.5 122B A10B by 11.455.767.1+11.4
- Artificial Analysis Coding IndexQwen3.5 122B A10B by 8.137.645.7+8.1
- AA Agentic IndexClaude Sonnet 4 by 817.69.6+8
- vectara_avg_summary_lengthClaude Sonnet 4 by 59.4 rating points145.886.4+59.4 rating
- IFEvalQwen3.5 122B A10B by 5.887.693.4+5.8
- AA IntelligenceClaude Sonnet 4 by 3.318.915.6+3.3
- MMLU-ProQwen3.5 122B A10B by 383.786.7+3
- vectara_answer_rateQwen3.5 122B A10B by 1.298.699.8+1.2
- vectara_factual_consistencytie89.788.8tie
- MMLU-Reduxtie93.694tie
- MMMLUtie86.586.7tie
Questions people ask
Which is better, Claude Sonnet 4 or Qwen3.5 122B A10B?
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. Claude Sonnet 4 wins none. They are level on facts.
Which is better for coding?
Qwen3.5 122B A10B. It wins 4 of the 7 coding tests both models report; Claude Sonnet 4 wins none, and 3 are ties.
Which is cheaper?
Claude Sonnet 4 costs $3.00 per million input tokens and $15.00 per million output tokens; Qwen3.5 122B A10B costs $0.40 and $3.20. That makes Qwen3.5 122B A10B about 80% cheaper for the same work.
How do you compare the two?
We use the 39 benchmark tests both models have published scores on. The verdict counts the 23 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 16 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.