GPT-5.1 vs Qwen3.5 397B A17B
Wins 4 of 7 areas
Coding · Agents · Facts · Long documents
Wins 2 of 7 areas
Images and charts · Following instructions
GPT-5.1 wins more areas, narrowly.Qwen3.5 397B A17B is cheaper and better at images and charts.
Scores updated · 32 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.
- FactsGetting facts right instead of making them up30GPT-5.13 of 3 tests
- CodingWriting and fixing software31GPT-5.13 of 6 tests · 2 ties
- AgentsCarrying out multi-step tasks on its own21GPT-5.12 of 3 tests
- Long documentsFinding answers in very long texts10GPT-5.11 of 1 test
- Images and chartsUnderstanding pictures, charts and video02Qwen3.5 397B A17B2 of 3 tests · 1 tie
- Following instructionsDoing exactly what it is asked02Qwen3.5 397B A17B2 of 2 tests
- ReasoningHard problems that need careful thinking11Even1 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 397B A17B costs 63% 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-5.1 pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+37points ahead
- Short factual questions, answered correctlySimpleQA Verified+22points ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+6.9points ahead
Where Qwen3.5 397B A17B pulls ahead
- Finds hard-to-locate facts by browsing the webBrowseComp+18.2points ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+5.9points ahead
- Keeps track of context across a multi-turn chatMulti-Challenge+4.2points ahead
Every test, side by side
All 32 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingGPT-5.1
- Terminal-Bench HardGPT-5.1 by 4.645.540.9+4.6
- LiveCodeBench v6GPT-5.1 by 3.48783.6+3.4
- SciCodeQwen3.5 397B A17B by 1.543.344.8+1.5
- Terminal-Bench 2.1GPT-5.1 by 1.152.451.3+1.1
- LMArena · WebDevtie13951400tie
- SWE-bench Verifiedtie76.376.4tie
AgentsGPT-5.1
- BrowseCompQwen3.5 397B A17B by 18.250.869+18.2
- τ-Bench V3 · BankingGPT-5.1 by 2.515.913.4+2.5
- GDPValGPT-5.1 by 1.716.514.8+1.7
ReasoningEven
- CritPtGPT-5.1 by 3.24.91.7+3.2
- GPQA DiamondQwen3.5 397B A17B by 287.389.3+2
- Humanity's Last Examtie28.529tie
FactsGPT-5.1
- AA-Omniscience · Non-hallucinationGPT-5.1 by 3748.111.1+37
- SimpleQA VerifiedGPT-5.1 by 224826+22
- AA-Omniscience · AccuracyGPT-5.1 by 6.937.730.8+6.9
Images and chartsQwen3.5 397B A17B
- MMMU-ProQwen3.5 397B A17B by 1.875.577.3+1.8
- LMArena · VisionQwen3.5 397B A17B by 14 rating points12501264+14 rating
- MMMUtie85.485tie
Following instructionsQwen3.5 397B A17B
- IFBenchQwen3.5 397B A17B by 5.972.978.8+5.9
- Multi-ChallengeQwen3.5 397B A17B by 4.263.467.6+4.2
Other results11 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-5.1 by 36.15.4-30.8+36.1
- τ²-Bench Telecom (AA run)Qwen3.5 397B A17B by 13.781.995.6+13.7
- AA Agentic IndexGPT-5.1 by 1121.610.6+11
- AA IntelligenceGPT-5.1 by 6.324.718.4+6.3
- HLE (with tools)Qwen3.5 397B A17B by 5.642.748.3+5.6
- Terminal-Bench 2.0Qwen3.5 397B A17B by 4.947.652.5+4.9
- MMMLUGPT-5.1 by 2.59188.5+2.5
- HMMT Feb. 2025GPT-5.1 by 1.596.394.8+1.5
- Artificial Analysis Coding IndexGPT-5.1 by 1.249.448.2+1.2
- HMMT Nov. 2025Qwen3.5 397B A17B by 191.792.7+1
- MMLU-Protie8787.8tie
Questions people ask
Which is better, GPT-5.1 or Qwen3.5 397B A17B?
GPT-5.1 wins four of the seven areas where both have results: coding, agents, facts and long documents. Qwen3.5 397B A17B wins images and charts and following instructions, and costs 63% less. They are level on reasoning.
Which is better for coding?
GPT-5.1. It wins 3 of the 6 coding tests both models report; Qwen3.5 397B A17B wins 1, and 2 are ties.
Which is cheaper?
GPT-5.1 costs $1.25 per million input tokens and $10.00 per million output tokens; Qwen3.5 397B A17B costs $0.60 and $3.60. That makes Qwen3.5 397B A17B about 63% cheaper for the same work.
How do you compare the two?
We use the 32 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 11 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.