Claude Opus 4.6 vs Qwen3.5 122B A10B
Wins 6 of 7 areas
Coding · Agents · Reasoning · Facts · Images and charts · Long documents
Wins 1 of 7 areas
Following instructions
Claude Opus 4.6 is the stronger all-rounder.Qwen3.5 122B A10B is cheaper and better at following instructions.
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 software70Claude Opus 4.67 of 7 tests
- AgentsCarrying out multi-step tasks on its own30Claude Opus 4.63 of 3 tests
- ReasoningHard problems that need careful thinking30Claude Opus 4.63 of 3 tests
- FactsGetting facts right instead of making them up21Claude Opus 4.62 of 3 tests
- Images and chartsUnderstanding pictures, charts and video10Claude Opus 4.61 of 3 tests · 2 ties
- Long documentsFinding answers in very long texts10Claude Opus 4.61 of 1 test
- Following instructionsDoing exactly what it is asked02Qwen3.5 122B A10B2 of 2 tests
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 88% 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 Claude Opus 4.6 pulls ahead
- Real work tasks from 44 professionsGDPVal+40.2points ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+24.3points ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+22.6points ahead
Where Qwen3.5 122B A10B pulls ahead
- Keeps track of context across a multi-turn chatMulti-Challenge+24.3points ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+22.6points 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.
CodingClaude Opus 4.6
- LMArena · WebDevClaude Opus 4.6 by 187 rating points15471360+187 rating
- SWE-bench MultilingualClaude Opus 4.6 by 15.877.862+15.8
- Terminal-Bench HardClaude Opus 4.6 by 15.146.231.1+15.1
- SciCodeClaude Opus 4.6 by 12.251.939.7+12.2
- LiveCodeBench v6Claude Opus 4.6 by 9.988.878.9+9.9
- SWE-bench VerifiedClaude Opus 4.6 by 8.880.872+8.8
- SWE-bench ProClaude Opus 4.6 by 8.553.444.9+8.5
AgentsClaude Opus 4.6
- GDPValClaude Opus 4.6 by 40.255.915.7+40.2
- BrowseCompClaude Opus 4.6 by 20.28463.8+20.2
- OSWorld-VerifiedClaude Opus 4.6 by 14.772.758+14.7
ReasoningClaude Opus 4.6
- Humanity's Last ExamClaude Opus 4.6 by 14.739.925.2+14.7
- CritPtClaude Opus 4.6 by 1212.60.6+12
- GPQA DiamondClaude Opus 4.6 by 3.989.685.7+3.9
FactsClaude Opus 4.6
- AA-Omniscience · Non-hallucinationClaude Opus 4.6 by 24.337.212.9+24.3
- AA-Omniscience · AccuracyClaude Opus 4.6 by 22.64724.4+22.6
- Vectara HHEM hallucination ratelower is betterQwen3.5 122B A10B by 112.211.2+1
Images and chartsClaude Opus 4.6
- LMArena · VisionClaude Opus 4.6 by 71 rating points13161245+71 rating
- MMMU-Protie75.475tie
- CharXiv (RQ)tie77.477.2tie
Following instructionsQwen3.5 122B A10B
- Multi-ChallengeQwen3.5 122B A10B by 24.337.161.5+24.3
- IFBenchQwen3.5 122B A10B by 22.653.175.7+22.6
Other results17 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 Agentic IndexClaude Opus 4.6 by 5867.69.6+58
- AA-OmniscienceClaude Opus 4.6 by 55.213.7-41.5+55.2
- BabyVisionQwen3.5 122B A10B by 25.414.840.2+25.4
- ERQAQwen3.5 122B A10B by 21.240.862+21.2
- MATH-VisionQwen3.5 122B A10B by 20.765.586.2+20.7
- AA IntelligenceClaude Opus 4.6 by 16.331.915.6+16.3
- Terminal-Bench 2.0Claude Opus 4.6 by 1665.449.4+16
- ScreenSpot-Pro (No tools)Qwen3.5 122B A10B by 12.757.770.4+12.7
- LVBenchQwen3.5 122B A10B by 11.46374.4+11.4
- RealWorldQAQwen3.5 122B A10B by 11.273.985.1+11.2
- vectara_avg_summary_lengthClaude Opus 4.6 by 51.2 rating points137.686.4+51.2 rating
- MMMLUClaude Opus 4.6 by 4.491.186.7+4.4
- Artificial Analysis Coding IndexClaude Opus 4.6 by 2.448.145.7+2.4
- MMLU-ProClaude Opus 4.6 by 2.489.186.7+2.4
- τ²-Bench Telecom (AA run)Qwen3.5 122B A10B by 1.592.193.6+1.5
- vectara_factual_consistencyQwen3.5 122B A10B by 187.888.8+1
- vectara_answer_ratetie99.899.8tie
Questions people ask
Which is better, Claude Opus 4.6 or Qwen3.5 122B A10B?
Claude Opus 4.6 wins six of the seven areas where both have results: coding, agents, reasoning, facts, images and charts and long documents. Qwen3.5 122B A10B wins following instructions, and costs 88% less.
Which is better for coding?
Claude Opus 4.6. It wins 7 of the 7 coding tests both models report; Qwen3.5 122B A10B wins none.
Which is cheaper?
Claude Opus 4.6 costs $5.00 per million input tokens and $25.00 per million output tokens; Qwen3.5 122B A10B costs $0.40 and $3.20. That makes Qwen3.5 122B A10B about 88% 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 22 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 17 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.