Claude Opus 4.8 vs Qwen3.6 Max Preview
Wins 3 of 6 areas
Coding · Reasoning · Facts
Wins 3 of 6 areas
Agents · Long documents · Following instructions
The two are evenly matched.Claude Opus 4.8 is better at reasoning and coding; Qwen3.6 Max Preview at agents and long documents.
Scores updated · 19 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.
- ReasoningHard problems that need careful thinking40Claude Opus 4.84 of 4 tests
- CodingWriting and fixing software30Claude Opus 4.83 of 3 tests
- FactsGetting facts right instead of making them up30Claude Opus 4.83 of 3 tests
- AgentsCarrying out multi-step tasks on its own01Qwen3.6 Max Preview1 of 1 test
- Long documentsFinding answers in very long texts01Qwen3.6 Max Preview1 of 1 test
- Following instructionsDoing exactly what it is asked01Qwen3.6 Max Preview1 of 1 test
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.
Qwen3.6 Max Preview costs 70% 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 4.8 pulls ahead
- Very hard expert questions across many subjectsHumanity's Last Exam+17.9points ahead
- Research-level physics problemsCritPt+17.2points ahead
- Hard command-line tasks in a real terminalTerminal-Bench Hard+14.4points ahead
Every test, side by side
All 19 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingClaude Opus 4.8
- Terminal-Bench HardClaude Opus 4.8 by 14.458.343.9+14.4
- SciCodeClaude Opus 4.8 by 7.554.446.9+7.5
- LMArena · WebDevClaude Opus 4.8 by 74 rating points15561482+74 rating
ReasoningClaude Opus 4.8
- Humanity's Last ExamClaude Opus 4.8 by 17.948.730.8+17.9
- CritPtClaude Opus 4.8 by 17.220.93.7+17.2
- GPQA DiamondClaude Opus 4.8 by 3.29288.8+3.2
- SimpleBenchClaude Opus 4.8 by 1.864.863+1.8
FactsClaude Opus 4.8
- AA-Omniscience · AccuracyClaude Opus 4.8 by 10.948.837.9+10.9
- AA-Omniscience · Non-hallucinationClaude Opus 4.8 by 6.960.753.8+6.9
- SimpleQA VerifiedClaude Opus 4.8 by 15352+1
Long documentsQwen3.6 Max Preview
- AA-LCRQwen3.6 Max Preview by 377.780.7+3
Following instructionsQwen3.6 Max Preview
- IFBenchQwen3.6 Max Preview by 14.462.276.6+14.4
Other results6 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.
- Artificial Analysis Coding IndexClaude Opus 4.8 by 29.474.344.9+29.4
- frontiermath_tier_4_v1Claude Opus 4.8 by 27.131.34.2+27.1
- AA Agentic IndexQwen3.6 Max Preview by 22.242.664.8+22.2
- AA-OmniscienceClaude Opus 4.8 by 19.628.89.2+19.6
- AA IntelligenceClaude Opus 4.8 by 13.441.828.4+13.4
- τ²-Bench Telecom (AA run)Qwen3.6 Max Preview by 1.594.495.9+1.5
Questions people ask
Which is better, Claude Opus 4.8 or Qwen3.6 Max Preview?
Claude Opus 4.8 and Qwen3.6 Max Preview each win three of the six areas where both have results. Claude Opus 4.8 wins coding, reasoning and facts; Qwen3.6 Max Preview wins agents, long documents and following instructions. Qwen3.6 Max Preview costs 70% less.
Which is better for coding?
Claude Opus 4.8. It wins 3 of the 3 coding tests both models report; Qwen3.6 Max Preview wins none.
Which is cheaper?
Claude Opus 4.8 costs $5.00 per million input tokens and $25.00 per million output tokens; Qwen3.6 Max Preview costs $1.30 and $7.80. That makes Qwen3.6 Max Preview about 70% cheaper for the same work.
How do you compare the two?
We use the 19 benchmark tests both models have published scores on. The verdict counts the 13 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 6 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.