GPT-4o vs Qwen3.5 397B A17B
Wins 0 of 7 areas
—
Wins 6 of 7 areas
Coding · Agents · Reasoning · Images and charts · Long documents · Following instructions
Qwen3.5 397B A17B is the stronger all-rounder.
Scores updated · 29 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 397B A17B4 of 4 tests
- ReasoningHard problems that need careful thinking03Qwen3.5 397B A17B3 of 3 tests
- Images and chartsUnderstanding pictures, charts and video02Qwen3.5 397B A17B2 of 2 tests
- Long documentsFinding answers in very long texts02Qwen3.5 397B A17B2 of 2 tests
- Following instructionsDoing exactly what it is asked02Qwen3.5 397B A17B2 of 2 tests
- AgentsCarrying out multi-step tasks on its own01Qwen3.5 397B A17B1 of 1 test
- FactsGetting facts right instead of making them up11Even1 each · 1 tie
Agents 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 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 Qwen3.5 397B A17B pulls ahead
- Recent programming contest problemsLiveCodeBench v6+52.7points ahead
- Fixes real GitHub issues in Python projectsSWE-bench Verified+43.2points ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+42.8points ahead
Where GPT-4o pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+51points ahead
Every test, side by side
All 29 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingQwen3.5 397B A17B
- LiveCodeBench v6Qwen3.5 397B A17B by 52.730.983.6+52.7
- SWE-bench VerifiedQwen3.5 397B A17B by 43.233.276.4+43.2
- Terminal-Bench HardQwen3.5 397B A17B by 32.68.340.9+32.6
- SciCodeQwen3.5 397B A17B by 11.533.344.8+11.5
ReasoningQwen3.5 397B A17B
- GPQA DiamondQwen3.5 397B A17B by 36.752.689.3+36.7
- Humanity's Last ExamQwen3.5 397B A17B by 27.21.829+27.2
- CritPtQwen3.5 397B A17B by 1.701.7+1.7
FactsEven
- AA-Omniscience · Non-hallucinationGPT-4o by 5162.111.1+51
- AA-Omniscience · AccuracyQwen3.5 397B A17B by 7.123.730.8+7.1
- SimpleQA Verifiedtie2626tie
Images and chartsQwen3.5 397B A17B
Long documentsQwen3.5 397B A17B
- AA-LCRQwen3.5 397B A17B by 21.35677.3+21.3
- LongBench v2Qwen3.5 397B A17B by 15.148.163.2+15.1
Following instructionsQwen3.5 397B A17B
- IFBenchQwen3.5 397B A17B by 42.83678.8+42.8
- Multi-ChallengeQwen3.5 397B A17B by 27.340.367.6+27.3
Other results12 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.
- τ²-Bench Telecom (AA run)Qwen3.5 397B A17B by 66.728.995.6+66.7
- SuperGPQAQwen3.5 397B A17B by 2842.470.4+28
- Artificial Analysis Coding IndexQwen3.5 397B A17B by 2424.248.2+24
- MMLU-ProXQwen3.5 397B A17B by 23.661.184.7+23.6
- AA-OmniscienceGPT-4o by 20.2-10.5-30.8+20.2
- C-EvalQwen3.5 397B A17B by 177693+17
- MMLU-ProQwen3.5 397B A17B by 13.174.787.8+13.1
- IFEvalQwen3.5 397B A17B by 11.68192.6+11.6
- AA IntelligenceQwen3.5 397B A17B by 11.17.318.4+11.1
- MMMLUQwen3.5 397B A17B by 7.181.488.5+7.1
- MMLU-ReduxQwen3.5 397B A17B by 6.98894.9+6.9
- AA Agentic IndexQwen3.5 397B A17B by 2.28.410.6+2.2
Questions people ask
Which is better, GPT-4o or Qwen3.5 397B A17B?
Qwen3.5 397B A17B wins six of the seven areas where both have results: coding, agents, reasoning, images and charts, long documents and following instructions. GPT-4o wins none. They are level on facts.
Which is better for coding?
Qwen3.5 397B A17B. It wins 4 of the 4 coding tests both models report; GPT-4o wins none.
Which is cheaper?
GPT-4o costs $5.00 per million input tokens and $15.00 per million output tokens; Qwen3.5 397B A17B costs $0.60 and $3.60. That makes Qwen3.5 397B A17B about 79% cheaper for the same work.
How do you compare the two?
We use the 29 benchmark tests both models have published scores on. The verdict counts the 17 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 12 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.