GPT-5 vs Qwen3.5 122B A10B
Wins 5 of 7 areas
Coding · Agents · Reasoning · Facts · Long documents
Wins 0 of 7 areas
—
GPT-5 is the stronger all-rounder.Qwen3.5 122B A10B is cheaper.
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 software53GPT-55 of 8 tests
- ReasoningHard problems that need careful thinking20GPT-52 of 3 tests · 1 tie
- AgentsCarrying out multi-step tasks on its own21GPT-52 of 3 tests
- FactsGetting facts right instead of making them up21GPT-52 of 3 tests
- Long documentsFinding answers in very long texts10GPT-51 of 1 test
- Images and chartsUnderstanding pictures, charts and video11Even1 each · 2 ties
- Following instructionsDoing exactly what it is asked11Even1 each
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 68% less for the same work.
The biggest differences
The three tests each model wins by the widest margin. Scores are out of 100.
Where GPT-5 pulls ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+15.9points ahead
- Recent programming contest problemsLiveCodeBench v6+8.1points ahead
- Keeps track of context across a multi-turn chatMulti-Challenge+8.1points ahead
Where Qwen3.5 122B A10B pulls ahead
- Command-line tasks in a real terminalTerminal-Bench 2.1+12.4points ahead
- Finds hard-to-locate facts by browsing the webBrowseComp+8.9points ahead
- Fixes real GitHub issues in many programming languagesSWE-bench Multilingual+6.7points 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.
CodingGPT-5
- Terminal-Bench 2.1Qwen3.5 122B A10B by 12.435.247.6+12.4
- LiveCodeBench v6GPT-5 by 8.18778.9+8.1
- SWE-bench MultilingualQwen3.5 122B A10B by 6.755.362+6.7
- LMArena · WebDevGPT-5 by 57 rating points14171360+57 rating
- SciCodeGPT-5 by 3.242.939.7+3.2
- SWE-bench ProQwen3.5 122B A10B by 3.141.844.9+3.1
- SWE-bench VerifiedGPT-5 by 2.974.972+2.9
- Terminal-Bench HardGPT-5 by 1.532.631.1+1.5
AgentsGPT-5
- BrowseCompQwen3.5 122B A10B by 8.954.963.8+8.9
- τ-Bench V3 · BankingGPT-5 by 6.822.115.3+6.8
- GDPValGPT-5 by 5.220.915.7+5.2
ReasoningGPT-5
- CritPtGPT-5 by 5.15.70.6+5.1
- Humanity's Last ExamGPT-5 by 3.328.525.2+3.3
- GPQA Diamondtie85.485.7tie
FactsGPT-5
- AA-Omniscience · AccuracyGPT-5 by 15.940.324.4+15.9
- AA-Omniscience · Non-hallucinationGPT-5 by 4.917.812.9+4.9
- Vectara HHEM hallucination ratelower is betterQwen3.5 122B A10B by 3.915.111.2+3.9
Images and chartsEven
- CharXiv (RQ)GPT-5 by 3.981.177.2+3.9
- LMArena · VisionQwen3.5 122B A10B by 37 rating points12081245+37 rating
- MMMU-Protie74.275tie
- MMMUtie84.283.9tie
Following instructionsEven
- Multi-ChallengeGPT-5 by 8.169.661.5+8.1
- IFBenchQwen3.5 122B A10B by 2.673.175.7+2.6
Other results15 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-OmniscienceGPT-5 by 32.8-8.7-41.5+32.8
- AA Agentic IndexGPT-5 by 16.926.59.6+16.9
- Terminal-Bench 2.0Qwen3.5 122B A10B by 14.235.249.4+14.2
- τ²-Bench Telecom (AA run)Qwen3.5 122B A10B by 8.884.893.6+8.8
- Artificial Analysis Coding IndexQwen3.5 122B A10B by 7.937.845.7+7.9
- vectara_avg_summary_lengthGPT-5 by 76.3 rating points162.786.4+76.3 rating
- AA IntelligenceGPT-5 by 7.42315.6+7.4
- BrowseComp-ZHQwen3.5 122B A10B by 6.96369.9+6.9
- vectara_factual_consistencyQwen3.5 122B A10B by 3.984.988.8+3.9
- ERQAGPT-5 by 3.765.762+3.7
- HMMT 2025GPT-5 by 393.390.3+3
- VideoMMMUGPT-5 by 2.684.682+2.6
- MMLU-ReduxGPT-5 by 1.395.394+1.3
- MMLU-Protie87.186.7tie
- vectara_answer_ratetie99.999.8tie
Questions people ask
Which is better, GPT-5 or Qwen3.5 122B A10B?
GPT-5 wins five of the seven areas where both have results: coding, agents, reasoning, facts and long documents. Qwen3.5 122B A10B wins none, but costs 68% less. They are level on images and charts and following instructions.
Which is better for coding?
GPT-5. It wins 5 of the 8 coding tests both models report; Qwen3.5 122B A10B wins 3.
Which is cheaper?
GPT-5 costs $1.25 per million input tokens and $10.00 per million output tokens; Qwen3.5 122B A10B costs $0.40 and $3.20. That makes Qwen3.5 122B A10B about 68% 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 24 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 15 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.