GPT-5.4 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
GPT-5.4 is the stronger all-rounder.Qwen3.5 122B A10B is cheaper and better at following instructions.
Scores updated · 34 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 software60GPT-5.46 of 6 tests
- AgentsCarrying out multi-step tasks on its own40GPT-5.44 of 4 tests
- ReasoningHard problems that need careful thinking30GPT-5.43 of 3 tests
- Images and chartsUnderstanding pictures, charts and video30GPT-5.43 of 3 tests
- FactsGetting facts right instead of making them up21GPT-5.42 of 3 tests
- Long documentsFinding answers in very long texts10GPT-5.41 of 1 test
- Following instructionsDoing exactly what it is asked01Qwen3.5 122B A10B1 of 1 test
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.
Qwen3.5 122B A10B costs 79% 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 GPT-5.4 pulls ahead
- Command-line tasks in a real terminalTerminal-Bench 2.1+30.7points ahead
- Hard command-line tasks in a real terminalTerminal-Bench Hard+26.5points ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+26.5points ahead
Where Qwen3.5 122B A10B pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+4.6points ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+1.8points ahead
Every test, side by side
All 34 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingGPT-5.4
- Terminal-Bench 2.1GPT-5.4 by 30.778.347.6+30.7
- Terminal-Bench HardGPT-5.4 by 26.557.631.1+26.5
- SciCodeGPT-5.4 by 16.956.639.7+16.9
- SWE-bench ProGPT-5.4 by 12.857.744.9+12.8
- LMArena · WebDevGPT-5.4 by 103 rating points14631360+103 rating
- SWE-bench MultilingualGPT-5.4 by 9.771.762+9.7
AgentsGPT-5.4
- τ-Bench V3 · BankingGPT-5.4 by 24.339.615.3+24.3
- GDPValGPT-5.4 by 21.637.315.7+21.6
- BrowseCompGPT-5.4 by 18.982.763.8+18.9
- OSWorld-VerifiedGPT-5.4 by 177558+17
ReasoningGPT-5.4
- CritPtGPT-5.4 by 22.823.40.6+22.8
- Humanity's Last ExamGPT-5.4 by 18.543.725.2+18.5
- GPQA DiamondGPT-5.4 by 6.39285.7+6.3
FactsGPT-5.4
- AA-Omniscience · AccuracyGPT-5.4 by 26.550.924.4+26.5
- AA-Omniscience · Non-hallucinationQwen3.5 122B A10B by 4.68.312.9+4.6
- Vectara HHEM hallucination ratelower is betterGPT-5.4 by 4.2711.2+4.2
Images and chartsGPT-5.4
- LMArena · VisionGPT-5.4 by 58 rating points13031245+58 rating
- CharXiv (RQ)GPT-5.4 by 5.682.877.2+5.6
- MMMU-ProGPT-5.4 by 3.478.475+3.4
Following instructionsQwen3.5 122B A10B
- IFBenchQwen3.5 122B A10B by 1.873.975.7+1.8
Other results13 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-5.4 by 47.35.8-41.5+47.3
- AA Agentic IndexGPT-5.4 by 34.644.29.6+34.6
- Terminal-Bench 2.0GPT-5.4 by 25.775.149.4+25.7
- Artificial Analysis Coding IndexGPT-5.4 by 25.471.145.7+25.4
- AA IntelligenceGPT-5.4 by 23.43915.6+23.4
- BabyVisionGPT-5.4 by 9.549.740.2+9.5
- τ²-Bench Telecom (AA run)Qwen3.5 122B A10B by 6.587.193.6+6.5
- MATH-VisionGPT-5.4 by 5.89286.2+5.8
- vectara_avg_summary_lengthQwen3.5 122B A10B by 4.781.786.4+4.7
- vectara_factual_consistencyGPT-5.4 by 4.29388.8+4.2
- MMLU-Protie87.586.7tie
- OmniDocBench 1.5tie89.189.8tie
- vectara_answer_ratetie99.999.8tie
Questions people ask
Which is better, GPT-5.4 or Qwen3.5 122B A10B?
GPT-5.4 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 79% less.
Which is better for coding?
GPT-5.4. It wins 6 of the 6 coding tests both models report; Qwen3.5 122B A10B wins none.
Which is cheaper?
GPT-5.4 costs $2.50 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 79% cheaper for the same work.
How do you compare the two?
We use the 34 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 13 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.