GLM-4.6 vs Qwen3 Coder 480B A35B Instruct
Wins 4 of 5 areas
Coding · Reasoning · Long documents · Following instructions
Wins 0 of 5 areas
—
GLM-4.6 is the stronger all-rounder.
Scores updated · 20 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.
- ReasoningHard problems that need careful thinking30GLM-4.63 of 3 tests
- CodingWriting and fixing software32GLM-4.63 of 6 tests · 1 tie
- Long documentsFinding answers in very long texts10GLM-4.61 of 1 test
- Following instructionsDoing exactly what it is asked10GLM-4.61 of 1 test
- FactsGetting facts right instead of making them up11Even1 each
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.
GLM-4.6 costs 69% less for the same work.
The biggest differences
The three tests each model wins by the widest margin. Scores are out of 100.
Where GLM-4.6 pulls ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+16.2points ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+11.2points ahead
- Very hard expert questions across many subjectsHumanity's Last Exam+10points ahead
Where Qwen3 Coder 480B A35B Instruct pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+49.2points ahead
- Long, multi-file coding tasks in real codebasesSWE-bench Pro+29points ahead
- Fixes real GitHub issues in Python projectsSWE-bench Verified+1.6points ahead
Every test, side by side
All 20 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingGLM-4.6
- SWE-bench ProQwen3 Coder 480B A35B Instruct by 299.738.7+29
- LMArena · WebDevGLM-4.6 by 68 rating points13411273+68 rating
- Terminal-Bench HardGLM-4.6 by 6.12518.9+6.1
- SciCodeGLM-4.6 by 2.538.435.9+2.5
- SWE-bench VerifiedQwen3 Coder 480B A35B Instruct by 1.66869.6+1.6
- SWE-bench Multilingualtie53.854.7tie
ReasoningGLM-4.6
- GPQA DiamondGLM-4.6 by 16.27861.8+16.2
- Humanity's Last ExamGLM-4.6 by 1014.54.5+10
- CritPtGLM-4.6 by 1.11.10+1.1
FactsEven
- AA-Omniscience · Non-hallucinationQwen3 Coder 480B A35B Instruct by 49.25.955.1+49.2
- AA-Omniscience · AccuracyGLM-4.6 by 11.226.915.7+11.2
Other results7 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.
- τ²-Bench Telecom (AA run)GLM-4.6 by 26.970.543.6+26.9
- Artificial Analysis Coding IndexGLM-4.6 by 21.245.824.6+21.2
- AA-OmniscienceQwen3 Coder 480B A35B Instruct by 19.7-41.9-22.2+19.7
- Terminal-Bench 2.0Qwen3 Coder 480B A35B Instruct by 1324.537.5+13
- AA IntelligenceGLM-4.6 by 6.618.511.9+6.6
- Multi-SWE-BenchGLM-4.6 by 4.23025.8+4.2
- AA Agentic Indextie18.618.3tie
Questions people ask
Which is better, GLM-4.6 or Qwen3 Coder 480B A35B Instruct?
GLM-4.6 wins four of the five areas where both have results: coding, reasoning, long documents and following instructions. Qwen3 Coder 480B A35B Instruct wins none. They are level on facts.
Which is better for coding?
GLM-4.6. It wins 3 of the 6 coding tests both models report; Qwen3 Coder 480B A35B Instruct wins 2, and 1 is a tie.
Which is cheaper?
GLM-4.6 costs $0.57 per million input tokens and $2.20 per million output tokens; Qwen3 Coder 480B A35B Instruct costs $1.50 and $7.50. That makes GLM-4.6 about 69% cheaper for the same work.
How do you compare the two?
We use the 20 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 7 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.