Qwen2.5 Instruct 72B vs Qwen3 VL 4B (Reasoning)
Wins 2 of 5 areas
Coding · Facts
Wins 2 of 5 areas
Reasoning · Long documents
The two are evenly matched.Qwen2.5 Instruct 72B is better at coding and facts; Qwen3 VL 4B (Reasoning) at reasoning and long documents.
Scores updated · 18 tests both models report · How we compare
Where each one wins
Tests won in each of the five 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 software20Qwen2.5 Instruct 72B2 of 2 tests
- FactsGetting facts right instead of making them up20Qwen2.5 Instruct 72B2 of 2 tests
- ReasoningHard problems that need careful thinking01Qwen3 VL 4B (Reasoning)1 of 3 tests · 2 ties
- Long documentsFinding answers in very long texts01Qwen3 VL 4B (Reasoning)1 of 1 test
- Following instructionsDoing exactly what it is asked00Even0 each · 1 tie
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 Qwen2.5 Instruct 72B pulls ahead
- Code for real scientific research problemsSciCode+9.6points ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+6.3points ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+5.3points ahead
Where Qwen3 VL 4B (Reasoning) pulls ahead
- Reasons across sets of long documentsAA-LCR+1.3points ahead
- Very hard expert questions across many subjectsHumanity's Last Exam+1points ahead
Every test, side by side
All 18 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingQwen2.5 Instruct 72B
- SciCodeQwen2.5 Instruct 72B by 9.626.717.1+9.6
- Terminal-Bench HardQwen2.5 Instruct 72B by 34.51.5+3
ReasoningQwen3 VL 4B (Reasoning)
- Humanity's Last ExamQwen3 VL 4B (Reasoning) by 13.64.6+1
- GPQA Diamondtie49.149.4tie
- CritPttie00tie
FactsQwen2.5 Instruct 72B
- AA-Omniscience · Non-hallucinationQwen2.5 Instruct 72B by 6.314.58.2+6.3
- AA-Omniscience · AccuracyQwen2.5 Instruct 72B by 5.317.512.2+5.3
Long documentsQwen3 VL 4B (Reasoning)
- AA-LCRQwen3 VL 4B (Reasoning) by 1.32021.3+1.3
Other results9 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.
- AIME 2024Qwen3 VL 4B (Reasoning) by 49.623.372.9+49.6
- τ²-Bench Telecom (AA run)Qwen2.5 Instruct 72B by 1934.515.5+19
- AA-OmniscienceQwen2.5 Instruct 72B by 15.3-53.1-68.4+15.3
- Artificial Analysis Coding IndexQwen2.5 Instruct 72B by 5.211.96.7+5.2
- LiveCodeBenchQwen2.5 Instruct 72B by 4.255.551.3+4.2
- MMLU-ProQwen3 VL 4B (Reasoning) by 2.571.173.6+2.5
- IFEvalQwen2.5 Instruct 72B by 1.584.182.6+1.5
- MMLU-Reduxtie86.886tie
- AA Intelligencetie7.77tie
Questions people ask
Which is better, Qwen2.5 Instruct 72B or Qwen3 VL 4B (Reasoning)?
Qwen2.5 Instruct 72B and Qwen3 VL 4B (Reasoning) each win two of the five areas where both have results. Qwen2.5 Instruct 72B wins coding and facts; Qwen3 VL 4B (Reasoning) wins reasoning and long documents. They are level on following instructions.
Which is better for coding?
Qwen2.5 Instruct 72B. It wins 2 of the 2 coding tests both models report; Qwen3 VL 4B (Reasoning) wins none.
How do you compare the two?
We use the 18 benchmark tests both models have published scores on. The verdict counts the 9 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 9 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.