GLM-5.1 vs Qwen3.6 35B A3B
Wins 7 of 7 areas
Coding · Agents · Reasoning · Facts · Math · Long documents · Following instructions
Wins 0 of 7 areas
—
GLM-5.1 is the stronger all-rounder.Qwen3.6 35B A3B is cheaper.
Scores updated · 38 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.
- CodingWriting and fixing software70GLM-5.17 of 7 tests
- AgentsCarrying out multi-step tasks on its own50GLM-5.15 of 5 tests
- ReasoningHard problems that need careful thinking30GLM-5.13 of 3 tests
- MathCompetition and research-level math31GLM-5.13 of 4 tests
- FactsGetting facts right instead of making them up20GLM-5.12 of 2 tests
- Long documentsFinding answers in very long texts10GLM-5.11 of 1 test
- Following instructionsDoing exactly what it is asked10GLM-5.11 of 1 test
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 35B A3B costs 55% less for the same work.
The biggest differences
The tests each model wins by the widest margin, up to three each. Scores are out of 100.
Where GLM-5.1 pulls ahead
- Finds hard-to-locate facts by browsing the webBrowseComp+30.6points ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+20.6points ahead
- Command-line tasks in a real terminalTerminal-Bench 2.1+16.9points ahead
Where Qwen3.6 35B A3B pulls ahead
- Harvard-MIT high-school math contest problemsHMMT Feb. 2026+1points ahead
Every test, side by side
All 38 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingGLM-5.1
- Terminal-Bench 2.1GLM-5.1 by 16.961.844.9+16.9
- SWE-bench ProGLM-5.1 by 8.958.449.5+8.9
- Terminal-Bench HardGLM-5.1 by 8.443.234.8+8.4
- SciCodeGLM-5.1 by 8.244.836.6+8.2
- SWE-bench MultilingualGLM-5.1 by 6.173.367.2+6.1
- LiveCodeBench v6GLM-5.1 by 5.385.780.4+5.3
- SWE-bench VerifiedGLM-5.1 by 2.876.273.4+2.8
AgentsGLM-5.1
- BrowseCompGLM-5.1 by 30.679.348.7+30.6
- GDPValGLM-5.1 by 11.23119.8+11.2
- MCP AtlasGLM-5.1 by 971.862.8+9
- τ-Bench V3 · BankingGLM-5.1 by 4.313.69.3+4.3
- Terminal-Bench 4.0GLM-5.1 by 220+2
ReasoningGLM-5.1
- Humanity's Last ExamGLM-5.1 by 7.930.122.2+7.9
- CritPtGLM-5.1 by 4.34.60.3+4.3
- GPQA DiamondGLM-5.1 by 2.786.884.1+2.7
FactsGLM-5.1
- AA-Omniscience · Non-hallucinationGLM-5.1 by 20.670.149.5+20.6
- AA-Omniscience · AccuracyGLM-5.1 by 4.923.718.8+4.9
MathGLM-5.1
- FrontierMath Tiers 1-3 (v2)GLM-5.1 by 16.436.820.4+16.4
- IMOAnswerBenchGLM-5.1 by 4.983.878.9+4.9
- AIME 2026GLM-5.1 by 2.695.392.7+2.6
- HMMT Feb. 2026Qwen3.6 35B A3B by 182.683.6+1
Other results15 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-OmniscienceGLM-5.1 by 23.10.8-22.2+23.1
- Terminal-Bench 2.0GLM-5.1 by 17.56951.5+17.5
- Artificial Analysis Coding IndexGLM-5.1 by 13.955.841.9+13.9
- Tool-DecathlonGLM-5.1 by 13.840.726.9+13.8
- ToolathlonGLM-5.1 by 13.840.726.9+13.8
- NL2RepoGLM-5.1 by 13.342.729.4+13.3
- AA Agentic IndexGLM-5.1 by 10.225.215+10.2
- AA IntelligenceGLM-5.1 by 7.926.118.2+7.9
- PinchBenchQwen3.6 35B A3B by 6.981.288.1+6.9
- HMMT 2025GLM-5.1 by 4.99489.1+4.9
- HMMT Nov. 2025GLM-5.1 by 4.99489.1+4.9
- τ³-BenchGLM-5.1 by 3.470.667.2+3.4
- τ²-Bench Telecom (AA run)GLM-5.1 by 2.497.795.3+2.4
- MMLU-Protie8685.2tie
- GPQA (unspecified)tie86.186tie
Questions people ask
Which is better, GLM-5.1 or Qwen3.6 35B A3B?
GLM-5.1 wins all seven areas where both have results: coding, agents, reasoning, facts, math, long documents and following instructions. Qwen3.6 35B A3B wins none, but costs 55% less.
Which is better for coding?
GLM-5.1. It wins 7 of the 7 coding tests both models report; Qwen3.6 35B A3B wins none.
Which is cheaper?
GLM-5.1 costs $1.38 per million input tokens and $4.40 per million output tokens; Qwen3.6 35B A3B costs $0.38 and $2.25. That makes Qwen3.6 35B A3B about 55% cheaper for the same work.
How do you compare the two?
We use the 38 benchmark tests both models have published scores on. The verdict counts the 23 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 15 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.