Claude 3 Haiku vs Qwen3 Omni 30B A3B
Wins 2 of 7 areas
Facts · Long documents
Wins 4 of 7 areas
Coding · Reasoning · Images and charts · Following instructions
Qwen3 Omni 30B A3B wins more areas, narrowly.Claude 3 Haiku is better at facts.
Scores updated · 16 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.
- ReasoningHard problems that need careful thinking02Qwen3 Omni 30B A3B2 of 3 tests · 1 tie
- CodingWriting and fixing software02Qwen3 Omni 30B A3B2 of 2 tests
- Images and chartsUnderstanding pictures, charts and video01Qwen3 Omni 30B A3B1 of 1 test
- Following instructionsDoing exactly what it is asked01Qwen3 Omni 30B A3B1 of 1 test
- FactsGetting facts right instead of making them up20Claude 3 Haiku2 of 2 tests
- Long documentsFinding answers in very long texts10Claude 3 Haiku1 of 1 test
- AgentsCarrying out multi-step tasks on its own00Even0 each · 1 tie
Agents, images and charts, 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 Omni 30B A3B costs 19% 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 Omni 30B A3B pulls ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+35.2points ahead
- Harder college exam questions with imagesMMMU-Pro+29.4points ahead
- Code for real scientific research problemsSciCode+12points ahead
Where Claude 3 Haiku pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+8.5points ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+3points ahead
Every test, side by side
All 16 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingQwen3 Omni 30B A3B
- SciCodeQwen3 Omni 30B A3B by 1218.630.6+12
- Terminal-Bench HardQwen3 Omni 30B A3B by 30.83.8+3
ReasoningQwen3 Omni 30B A3B
- GPQA DiamondQwen3 Omni 30B A3B by 35.237.472.6+35.2
- Humanity's Last ExamQwen3 Omni 30B A3B by 3.44.17.5+3.4
- CritPttie00tie
FactsClaude 3 Haiku
- AA-Omniscience · Non-hallucinationClaude 3 Haiku by 8.519.511+8.5
- AA-Omniscience · AccuracyClaude 3 Haiku by 317.614.6+3
Images and chartsQwen3 Omni 30B A3B
- MMMU-ProQwen3 Omni 30B A3B by 29.430.860.2+29.4
Following instructionsQwen3 Omni 30B A3B
- IFBenchQwen3 Omni 30B A3B by 7.336.143.4+7.3
Other results5 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-OmniscienceClaude 3 Haiku by 12.8-48.6-61.4+12.8
- Artificial Analysis Coding IndexQwen3 Omni 30B A3B by 66.712.7+6
- AA Agentic IndexQwen3 Omni 30B A3B by 3.6710.6+3.6
- AA IntelligenceQwen3 Omni 30B A3B by 2.25.67.8+2.2
- τ²-Bench Telecom (AA run)tie21.121.3tie
Questions people ask
Which is better, Claude 3 Haiku or Qwen3 Omni 30B A3B?
Qwen3 Omni 30B A3B wins four of the seven areas where both have results: coding, reasoning, images and charts and following instructions. Claude 3 Haiku wins facts and long documents. They are level on agents.
Which is better for coding?
Qwen3 Omni 30B A3B. It wins 2 of the 2 coding tests both models report; Claude 3 Haiku wins none.
Which is cheaper?
Claude 3 Haiku costs $0.25 per million input tokens and $1.25 per million output tokens; Qwen3 Omni 30B A3B costs $0.25 and $0.97. That makes Qwen3 Omni 30B A3B about 19% cheaper for the same work.
How do you compare the two?
We use the 16 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 5 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.