Claude Haiku 4.5 vs Qwen3 Max (Non-Reasoning)
Wins 3 of 6 areas
Coding · Long documents · Following instructions
Wins 2 of 6 areas
Agents · Reasoning
Claude Haiku 4.5 wins more areas, narrowly.Qwen3 Max (Non-Reasoning) is better at reasoning.
Scores updated · 15 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 software20Claude Haiku 4.52 of 2 tests
- Long documentsFinding answers in very long texts10Claude Haiku 4.51 of 1 test
- Following instructionsDoing exactly what it is asked10Claude Haiku 4.51 of 1 test
- ReasoningHard problems that need careful thinking02Qwen3 Max (Non-Reasoning)2 of 3 tests · 1 tie
- AgentsCarrying out multi-step tasks on its own01Qwen3 Max (Non-Reasoning)1 of 1 test
- FactsGetting facts right instead of making them up11Even1 each
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.
Claude Haiku 4.5 costs 17% 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 Haiku 4.5 pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+62.6points ahead
- Reasons across sets of long documentsAA-LCR+24.3points ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+10.2points ahead
Where Qwen3 Max (Non-Reasoning) pulls ahead
- Real work tasks from 44 professionsGDPVal+15.1points ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+9.2points ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+6.4points ahead
Every test, side by side
All 15 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingClaude Haiku 4.5
- Terminal-Bench HardClaude Haiku 4.5 by 6.827.320.5+6.8
- SciCodeClaude Haiku 4.5 by 3.942.238.3+3.9
AgentsQwen3 Max (Non-Reasoning)
- GDPValQwen3 Max (Non-Reasoning) by 15.111.826.9+15.1
ReasoningQwen3 Max (Non-Reasoning)
- GPQA DiamondQwen3 Max (Non-Reasoning) by 9.267.276.4+9.2
- Humanity's Last ExamQwen3 Max (Non-Reasoning) by 1.510.411.9+1.5
- CritPttie00tie
FactsEven
- AA-Omniscience · Non-hallucinationClaude Haiku 4.5 by 62.672.710.1+62.6
- AA-Omniscience · AccuracyQwen3 Max (Non-Reasoning) by 6.41824.4+6.4
Following instructionsClaude Haiku 4.5
- IFBenchClaude Haiku 4.5 by 10.254.344.1+10.2
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 Haiku 4.5 by 39.1-4.4-43.5+39.1
- AA Agentic IndexQwen3 Max (Non-Reasoning) by 32.710.343+32.7
- τ²-Bench Telecom (AA run)Qwen3 Max (Non-Reasoning) by 19.654.774.3+19.6
- Artificial Analysis Coding IndexClaude Haiku 4.5 by 17.543.926.4+17.5
- AA IntelligenceClaude Haiku 4.5 by 1.316.915.6+1.3
Questions people ask
Which is better, Claude Haiku 4.5 or Qwen3 Max (Non-Reasoning)?
Claude Haiku 4.5 wins three of the six areas where both have results: coding, long documents and following instructions. Qwen3 Max (Non-Reasoning) wins agents and reasoning. They are level on facts.
Which is better for coding?
Claude Haiku 4.5. It wins 2 of the 2 coding tests both models report; Qwen3 Max (Non-Reasoning) wins none.
Which is cheaper?
Claude Haiku 4.5 costs $1.00 per million input tokens and $5.00 per million output tokens; Qwen3 Max (Non-Reasoning) costs $1.20 and $6.00. That makes Claude Haiku 4.5 about 17% cheaper for the same work.
How do you compare the two?
We use the 15 benchmark tests both models have published scores on. The verdict counts the 10 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.