Claude Opus 4.5 vs Qwen3 Max (Reasoning)
Wins 4 of 7 areas
Reasoning · Facts · Math · Long documents
Wins 2 of 7 areas
Agents · Following instructions
Claude Opus 4.5 wins more areas, narrowly.Qwen3 Max (Reasoning) is cheaper and better at following instructions.
Scores updated · 28 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 thinking20Claude Opus 4.52 of 3 tests · 1 tie
- FactsGetting facts right instead of making them up20Claude Opus 4.52 of 2 tests
- Long documentsFinding answers in very long texts20Claude Opus 4.52 of 2 tests
- MathCompetition and research-level math10Claude Opus 4.51 of 2 tests · 1 tie
- Following instructionsDoing exactly what it is asked02Qwen3 Max (Reasoning)2 of 2 tests
- AgentsCarrying out multi-step tasks on its own01Qwen3 Max (Reasoning)1 of 1 test
- CodingWriting and fixing software22Even2 each
Agents rests on a single test.
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 Max (Reasoning) costs 76% 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 Opus 4.5 pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+33.7points ahead
- Hard command-line tasks in a real terminalTerminal-Bench Hard+22.8points ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+16.8points ahead
Where Qwen3 Max (Reasoning) pulls ahead
- Fixes real GitHub issues in many programming languagesSWE-bench Multilingual+59.7points ahead
- Finds hard-to-locate facts by browsing the webBrowseComp+16.9points ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+12.7points ahead
Every test, side by side
All 28 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingEven
- SWE-bench MultilingualQwen3 Max (Reasoning) by 59.7766.7+59.7
- Terminal-Bench HardClaude Opus 4.5 by 22.84724.2+22.8
- SWE-bench VerifiedClaude Opus 4.5 by 5.680.975.3+5.6
- LiveCodeBench v6Qwen3 Max (Reasoning) by 1.184.885.9+1.1
ReasoningClaude Opus 4.5
- CritPtClaude Opus 4.5 by 2.94.61.7+2.9
- Humanity's Last ExamClaude Opus 4.5 by 2.130.128+2.1
- GPQA Diamondtie86.686.1tie
FactsClaude Opus 4.5
- AA-Omniscience · Non-hallucinationClaude Opus 4.5 by 33.7395.3+33.7
- AA-Omniscience · AccuracyClaude Opus 4.5 by 16.846.629.8+16.8
MathClaude Opus 4.5
- AIME 2026Claude Opus 4.5 by 1.895.193.3+1.8
- IMOAnswerBenchtie8483.9tie
Long documentsClaude Opus 4.5
- LongBench v2Claude Opus 4.5 by 3.864.460.6+3.8
- AA-LCRClaude Opus 4.5 by 377.374.3+3
Following instructionsQwen3 Max (Reasoning)
- IFBenchQwen3 Max (Reasoning) by 12.75870.7+12.7
- Multi-ChallengeQwen3 Max (Reasoning) by 4.35963.3+4.3
Other results12 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 Opus 4.5 by 50.614-36.6+50.6
- Terminal-Bench 2.0Claude Opus 4.5 by 36.859.322.5+36.8
- ToolathlonClaude Opus 4.5 by 24.743.518.8+24.7
- AIME 2025Claude Opus 4.5 by 11.292.881.6+11.2
- AA IntelligenceClaude Opus 4.5 by 7.829.121.3+7.8
- MMMLUClaude Opus 4.5 by 6.490.884.4+6.4
- τ²-Bench Telecom (AA run)Claude Opus 4.5 by 5.989.583.6+5.9
- MMLU-ProClaude Opus 4.5 by 3.889.585.7+3.8
- SuperGPQAClaude Opus 4.5 by 3.370.667.3+3.3
- MMLU-ReduxClaude Opus 4.5 by 2.895.692.8+2.8
- C-EvalQwen3 Max (Reasoning) by 1.592.293.7+1.5
- Seal-0tie47.746.9tie
Questions people ask
Which is better, Claude Opus 4.5 or Qwen3 Max (Reasoning)?
Claude Opus 4.5 wins four of the seven areas where both have results: reasoning, facts, math and long documents. Qwen3 Max (Reasoning) wins agents and following instructions, and costs 76% less. They are level on coding.
Which is better for coding?
Neither. They win 2 coding tests each of the 4 both models report.
Which is cheaper?
Claude Opus 4.5 costs $5.00 per million input tokens and $25.00 per million output tokens; Qwen3 Max (Reasoning) costs $1.20 and $6.00. That makes Qwen3 Max (Reasoning) about 76% cheaper for the same work.
How do you compare the two?
We use the 28 benchmark tests both models have published scores on. The verdict counts the 16 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 12 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.