GLM-5.1 vs Qwen3.7 Plus Preview
Wins 0 of 7 areas
—
Wins 4 of 7 areas
Coding · Reasoning · Math · Following instructions
Qwen3.7 Plus Preview wins more areas, narrowly.
Scores updated · 31 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 software05Qwen3.7 Plus Preview5 of 7 tests · 2 ties
- ReasoningHard problems that need careful thinking03Qwen3.7 Plus Preview3 of 3 tests
- MathCompetition and research-level math12Qwen3.7 Plus Preview2 of 3 tests
- Following instructionsDoing exactly what it is asked01Qwen3.7 Plus Preview1 of 1 test
- AgentsCarrying out multi-step tasks on its own22Even2 each
- FactsGetting facts right instead of making them up11Even1 each
- Long documentsFinding answers in very long texts00Even0 each · 1 tie
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.
Qwen3.7 Plus Preview costs 63% less for the same work.
The biggest differences
The three tests each model wins by the widest margin. Scores are out of 100.
Where Qwen3.7 Plus Preview pulls ahead
- Harvard-MIT high-school math contest problemsHMMT Feb. 2026+10.3points ahead
- Very hard expert questions across many subjectsHumanity's Last Exam+5.5points ahead
- Research-level physics problemsCritPt+4.5points ahead
Where GLM-5.1 pulls ahead
- Real work tasks from 44 professionsGDPVal+17.4points ahead
- Unpublished advanced math problemsFrontierMath Tiers 1-3 (v2)+2.4points ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+1.2points ahead
Every test, side by side
All 31 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingQwen3.7 Plus Preview
- LiveCodeBench v6Qwen3.7 Plus Preview by 3.985.789.6+3.9
- Terminal-Bench HardQwen3.7 Plus Preview by 3.843.247+3.8
- SWE-bench MultilingualQwen3.7 Plus Preview by 2.573.375.8+2.5
- SWE-bench VerifiedQwen3.7 Plus Preview by 1.576.277.7+1.5
- SciCodeQwen3.7 Plus Preview by 1.344.846.1+1.3
- SWE-bench Protie58.457.6tie
- Terminal-Bench 2.1tie61.861tie
AgentsEven
- GDPValGLM-5.1 by 17.430.813.4+17.4
- τ-Bench V3 · BankingQwen3.7 Plus Preview by 3.913.617.5+3.9
- MCP AtlasQwen3.7 Plus Preview by 1.471.873.2+1.4
- Terminal-Bench 4.0GLM-5.1 by 121+1
ReasoningQwen3.7 Plus Preview
- Humanity's Last ExamQwen3.7 Plus Preview by 5.530.135.6+5.5
- CritPtQwen3.7 Plus Preview by 4.54.69.1+4.5
- GPQA DiamondQwen3.7 Plus Preview by 3.286.890+3.2
FactsEven
- AA-Omniscience · Non-hallucinationQwen3.7 Plus Preview by 2.270.172.3+2.2
- AA-Omniscience · AccuracyGLM-5.1 by 1.223.722.5+1.2
MathQwen3.7 Plus Preview
- HMMT Feb. 2026Qwen3.7 Plus Preview by 10.382.692.9+10.3
- FrontierMath Tiers 1-3 (v2)GLM-5.1 by 2.436.834.4+2.4
- IMOAnswerBenchQwen3.7 Plus Preview by 2.283.886+2.2
Following instructionsQwen3.7 Plus Preview
- IFBenchQwen3.7 Plus Preview by 1.776.378+1.7
Other results10 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.
- Apex (Pass@1)Qwen3.7 Plus Preview by 11.211.522.7+11.2
- Finance Agent v2GLM-5.1 by 6.644.838.2+6.6
- AA Agentic IndexGLM-5.1 by 5.525.219.7+5.5
- τ²-Bench Telecom (AA run)GLM-5.1 by 4.797.793+4.7
- MMLU-ProQwen3.7 Plus Preview by 2.58688.5+2.5
- NL2RepoGLM-5.1 by 1.642.741.1+1.6
- Terminal-Bench 2.0Qwen3.7 Plus Preview by 1.36970.3+1.3
- AA Intelligencetie26.125.2tie
- AA-Omnisciencetie0.81.1tie
- Artificial Analysis Coding Indextie55.855.9tie
Questions people ask
Which is better, GLM-5.1 or Qwen3.7 Plus Preview?
Qwen3.7 Plus Preview wins four of the seven areas where both have results: coding, reasoning, math and following instructions. GLM-5.1 wins none. They are level on agents, facts and long documents.
Which is better for coding?
Qwen3.7 Plus Preview. It wins 5 of the 7 coding tests both models report; GLM-5.1 wins none, and 2 are ties.
Which is cheaper?
GLM-5.1 costs $1.28 per million input tokens and $4.07 per million output tokens; Qwen3.7 Plus Preview costs $0.40 and $1.60. That makes Qwen3.7 Plus Preview about 63% cheaper for the same work.
How do you compare the two?
We use the 31 benchmark tests both models have published scores on. The verdict counts the 21 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 10 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.