Qwen3.7 Max vs Qwen3 VL 4B (Reasoning)
Wins 6 of 6 areas
Coding · Agents · Reasoning · Facts · Long documents · Following instructions
Wins 0 of 6 areas
—
Qwen3.7 Max is the stronger all-rounder.
Scores updated · 22 tests both models report · How we compare
Where each one wins
Tests won in each of the six 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 software30Qwen3.7 Max3 of 3 tests
- ReasoningHard problems that need careful thinking30Qwen3.7 Max3 of 3 tests
- FactsGetting facts right instead of making them up20Qwen3.7 Max2 of 2 tests
- AgentsCarrying out multi-step tasks on its own10Qwen3.7 Max1 of 1 test
- Long documentsFinding answers in very long texts10Qwen3.7 Max1 of 1 test
- Following instructionsDoing exactly what it is asked10Qwen3.7 Max1 of 1 test
Agents, 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.
The biggest differences
The tests each model wins by the widest margin, up to three each. Scores are out of 100.
Where Qwen3.7 Max pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+66.2points ahead
- Reasons across sets of long documentsAA-LCR+57.7points ahead
- Hard command-line tasks in a real terminalTerminal-Bench Hard+49.3points ahead
Where Qwen3 VL 4B (Reasoning) pulls ahead
No clear win on a test scored out of 100.
Every test, side by side
All 22 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingQwen3.7 Max
- Terminal-Bench HardQwen3.7 Max by 49.350.81.5+49.3
- LiveCodeBench v6Qwen3.7 Max by 40.391.651.3+40.3
- SciCodeQwen3.7 Max by 32.449.517.1+32.4
ReasoningQwen3.7 Max
- GPQA DiamondQwen3.7 Max by 42.992.349.4+42.9
- Humanity's Last ExamQwen3.7 Max by 35.940.54.6+35.9
- CritPtQwen3.7 Max by 13.413.40+13.4
FactsQwen3.7 Max
- AA-Omniscience · Non-hallucinationQwen3.7 Max by 66.274.48.2+66.2
- AA-Omniscience · AccuracyQwen3.7 Max by 18.931.112.2+18.9
Following instructionsQwen3.7 Max
- IFBenchQwen3.7 Max by 43.980.536.6+43.9
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-OmniscienceQwen3.7 Max by 81.913.5-68.4+81.9
- τ²-Bench Telecom (AA run)Qwen3.7 Max by 79.294.715.5+79.2
- Artificial Analysis Coding IndexQwen3.7 Max by 59.3666.7+59.3
- SuperGPQAQwen3.7 Max by 26.873.646.8+26.8
- AA IntelligenceQwen3.7 Max by 22.529.57+22.5
- MMLU-ProXQwen3.7 Max by 228765+22
- IncludeQwen3.7 Max by 21.686.264.6+21.6
- MMLU-ProQwen3.7 Max by 1689.673.6+16
- IFEvalQwen3.7 Max by 11.794.382.6+11.7
- AA Agentic IndexQwen3.7 Max by 9.523.914.4+9.5
- MMLU-ReduxQwen3.7 Max by 99586+9
Questions people ask
Which is better, Qwen3.7 Max or Qwen3 VL 4B (Reasoning)?
Qwen3.7 Max wins all six areas where both have results: coding, agents, reasoning, facts, long documents and following instructions. Qwen3 VL 4B (Reasoning) wins none.
Which is better for coding?
Qwen3.7 Max. It wins 3 of the 3 coding tests both models report; Qwen3 VL 4B (Reasoning) wins none.
How do you compare the two?
We use the 22 benchmark tests both models have published scores on. The verdict counts the 11 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.