Claude 3 Haiku vs Qwen3 30B A3B 2507 Instruct
Wins 3 of 5 areas
Facts · Long documents · Following instructions
Wins 2 of 5 areas
Coding · Reasoning
Claude 3 Haiku is the stronger all-rounder.Qwen3 30B A3B 2507 Instruct is cheaper and better at reasoning.
Scores updated · 11 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.
- 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
- Following instructionsDoing exactly what it is asked10Claude 3 Haiku1 of 1 test
- ReasoningHard problems that need careful thinking02Qwen3 30B A3B 2507 Instruct2 of 3 tests · 1 tie
- CodingWriting and fixing software01Qwen3 30B A3B 2507 Instruct1 of 1 test
Coding, 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 30B A3B 2507 Instruct costs 33% less for the same work.
The biggest differences
The three tests each model wins by the widest margin. Scores are out of 100.
Where Claude 3 Haiku pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+14.9points ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+3points ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+2.6points ahead
Where Qwen3 30B A3B 2507 Instruct pulls ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+28.5points ahead
- Hard command-line tasks in a real terminalTerminal-Bench Hard+5.3points ahead
- Very hard expert questions across many subjectsHumanity's Last Exam+2.8points ahead
Every test, side by side
All 11 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingQwen3 30B A3B 2507 Instruct
- Terminal-Bench HardQwen3 30B A3B 2507 Instruct by 5.30.86.1+5.3
ReasoningQwen3 30B A3B 2507 Instruct
- GPQA DiamondQwen3 30B A3B 2507 Instruct by 28.537.465.9+28.5
- Humanity's Last ExamQwen3 30B A3B 2507 Instruct by 2.84.16.9+2.8
- CritPttie00tie
FactsClaude 3 Haiku
- AA-Omniscience · Non-hallucinationClaude 3 Haiku by 14.919.54.6+14.9
- AA-Omniscience · AccuracyClaude 3 Haiku by 2.617.615+2.6
Following instructionsClaude 3 Haiku
- IFBenchClaude 3 Haiku by 336.133.1+3
Other results3 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 17.5-48.6-66.2+17.5
- τ²-Bench Telecom (AA run)Claude 3 Haiku by 10.921.110.2+10.9
- AA IntelligenceQwen3 30B A3B 2507 Instruct by 1.95.67.5+1.9
Questions people ask
Which is better, Claude 3 Haiku or Qwen3 30B A3B 2507 Instruct?
Claude 3 Haiku wins three of the five areas where both have results: facts, long documents and following instructions. Qwen3 30B A3B 2507 Instruct wins coding and reasoning, and costs 33% less.
Which is better for coding?
Qwen3 30B A3B 2507 Instruct. It wins the one coding test both models report.
Which is cheaper?
Claude 3 Haiku costs $0.25 per million input tokens and $1.25 per million output tokens; Qwen3 30B A3B 2507 Instruct costs $0.20 and $0.80. That makes Qwen3 30B A3B 2507 Instruct about 33% cheaper for the same work.
How do you compare the two?
We use the 11 benchmark tests both models have published scores on. The verdict counts the 8 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 3 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.