GLM-5.1 vs Qwen3.6 Plus
Wins 3 of 7 areas
Coding · Reasoning · Following instructions
Wins 4 of 7 areas
Agents · Facts · Math · Long documents
Qwen3.6 Plus wins more areas, narrowly.GLM-5.1 is better at coding.
Scores updated · 48 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.
- MathCompetition and research-level math02Qwen3.6 Plus2 of 4 tests · 2 ties
- AgentsCarrying out multi-step tasks on its own12Qwen3.6 Plus2 of 3 tests
- FactsGetting facts right instead of making them up12Qwen3.6 Plus2 of 3 tests
- Long documentsFinding answers in very long texts01Qwen3.6 Plus1 of 1 test
- CodingWriting and fixing software32GLM-5.13 of 8 tests · 3 ties
- ReasoningHard problems that need careful thinking21GLM-5.12 of 3 tests
- 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 Plus costs 39% less for the same work.
The biggest differences
The three tests each model wins by the widest margin. Scores are out of 100.
Where Qwen3.6 Plus pulls ahead
- Short factual questions, answered correctlySimpleQA Verified+10.1points ahead
- Customer-service tasks in a simulated bankτ-Bench V3 · Banking+7.2points ahead
- Harvard-MIT high-school math contest problemsHMMT Feb. 2026+5.2points ahead
Where GLM-5.1 pulls ahead
- Real work tasks from 44 professionsGDPVal+6.3points ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+4.7points ahead
- Code for real scientific research problemsSciCode+4.1points ahead
Every test, side by side
All 48 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingGLM-5.1
- LMArena · WebDevGLM-5.1 by 47 rating points15081461+47 rating
- SciCodeGLM-5.1 by 4.144.840.7+4.1
- SWE-bench VerifiedQwen3.6 Plus by 2.676.278.8+2.6
- SWE-bench ProGLM-5.1 by 1.858.456.6+1.8
- LiveCodeBench v6Qwen3.6 Plus by 1.485.787.1+1.4
- Terminal-Bench Hardtie43.243.9tie
- SWE-bench Multilingualtie73.373.8tie
- Terminal-Bench 2.1tie61.861.4tie
AgentsQwen3.6 Plus
- τ-Bench V3 · BankingQwen3.6 Plus by 7.213.620.8+7.2
- GDPValGLM-5.1 by 6.33124.7+6.3
- MCP AtlasQwen3.6 Plus by 2.371.874.1+2.3
ReasoningGLM-5.1
- Humanity's Last ExamGLM-5.1 by 2.330.127.8+2.3
- CritPtGLM-5.1 by 1.74.62.9+1.7
- GPQA DiamondQwen3.6 Plus by 1.486.888.2+1.4
FactsQwen3.6 Plus
- SimpleQA VerifiedQwen3.6 Plus by 10.13444.1+10.1
- AA-Omniscience · Non-hallucinationGLM-5.1 by 4.770.165.4+4.7
- AA-Omniscience · AccuracyQwen3.6 Plus by 2.723.726.4+2.7
MathQwen3.6 Plus
- HMMT Feb. 2026Qwen3.6 Plus by 5.282.687.8+5.2
- FrontierMath Tiers 1-3 (v2)Qwen3.6 Plus by 1.536.838.3+1.5
- AIME 2026tie95.395.3tie
- IMOAnswerBenchtie83.883.8tie
Other results25 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.
- AgentWorldBench - MCPGLM-5.1 by 12.367.655.3+12.3
- Terminal-Bench 2.0GLM-5.1 by 7.46961.6+7.4
- AgentWorldBench - SWEQwen3.6 Plus by 752.159.1+7
- NL2RepoGLM-5.1 by 4.842.737.9+4.8
- frontiermath_tier_4_v1GLM-5.1 by 4.212.58.3+4.2
- Finance Agent v2GLM-5.1 by 3.944.840.9+3.9
- AA Agentic IndexQwen3.6 Plus by 3.825.229+3.8
- AgentWorldBench - TerminalQwen3.6 Plus by 3.347.350.6+3.3
- MMLU-ProQwen3.6 Plus by 2.58688.5+2.5
- HLE (with tools)GLM-5.1 by 1.752.350.6+1.7
- AgentWorldBench - AndroidGLM-5.1 by 1.459.157.6+1.4
- Artificial Analysis Coding IndexGLM-5.1 by 1.355.854.5+1.3
- AgentWorldBench - OSQwen3.6 Plus by 1.259.160.3+1.2
- AA Intelligencetie26.127tie
- Tool-Decathlontie40.739.8tie
- Toolathlontie40.739.8tie
- AgentWorldBench - Webtie51.550.8tie
- LiveBenchtie70.270.8tie
- AgentWorldBench - Searchtie22.521.9tie
- HMMT 2025tie9494.6tie
- HMMT Nov. 2025tie9494.6tie
- AgentWorldBench - Overalltie51.350.8tie
- τ³-Benchtie70.670.7tie
- AA-Omnisciencetie0.80.9tie
- τ²-Bench Telecom (AA run)tie97.797.7tie
Questions people ask
Which is better, GLM-5.1 or Qwen3.6 Plus?
Qwen3.6 Plus wins four of the seven areas where both have results: agents, facts, math and long documents. GLM-5.1 wins coding, reasoning and following instructions.
Which is better for coding?
GLM-5.1. It wins 3 of the 8 coding tests both models report; Qwen3.6 Plus wins 2, and 3 are ties.
Which is cheaper?
GLM-5.1 costs $1.38 per million input tokens and $4.40 per million output tokens; Qwen3.6 Plus costs $0.50 and $3.00. That makes Qwen3.6 Plus about 39% cheaper for the same work.
How do you compare the two?
We use the 48 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 25 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.