Gemma 4 31B vs GLM-5.1
Wins 0 of 7 areas
—
Wins 6 of 7 areas
Coding · Agents · Reasoning · Facts · Math · Long documents
GLM-5.1 is the stronger all-rounder.Gemma 4 31B is cheaper.
Scores updated · 37 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 software07GLM-5.17 of 8 tests · 1 tie
- AgentsCarrying out multi-step tasks on its own14GLM-5.14 of 5 tests
- ReasoningHard problems that need careful thinking03GLM-5.13 of 3 tests
- FactsGetting facts right instead of making them up03GLM-5.13 of 3 tests
- MathCompetition and research-level math03GLM-5.13 of 3 tests
- Long documentsFinding answers in very long texts01GLM-5.11 of 1 test
- Following instructionsDoing exactly what it is asked00Even0 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.
Gemma 4 31B costs 90% 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
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+55.1points ahead
- Real work tasks from 44 professionsGDPVal+24.9points ahead
- Fixes real GitHub issues in Python projectsSWE-bench Verified+24.2points ahead
Where Gemma 4 31B pulls ahead
- Customer-service tasks in a simulated bankτ-Bench V3 · Banking+1.2points ahead
Every test, side by side
All 37 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingGLM-5.1
- SWE-bench VerifiedGLM-5.1 by 24.25276.2+24.2
- SWE-bench ProGLM-5.1 by 22.735.758.4+22.7
- SWE-bench MultilingualGLM-5.1 by 21.651.773.3+21.6
- Terminal-Bench 2.1GLM-5.1 by 18.443.461.8+18.4
- LMArena · WebDevGLM-5.1 by 143 rating points13651508+143 rating
- Terminal-Bench HardGLM-5.1 by 6.836.443.2+6.8
- LiveCodeBench v6GLM-5.1 by 5.78085.7+5.7
- SciCodetie45.544.8tie
AgentsGLM-5.1
- GDPValGLM-5.1 by 24.96.131+24.9
- MCP AtlasGLM-5.1 by 14.657.271.8+14.6
- AA IT-Bench SREGLM-5.1 by 337.340.3+3
- Terminal-Bench 4.0GLM-5.1 by 202+2
- τ-Bench V3 · BankingGemma 4 31B by 1.214.813.6+1.2
ReasoningGLM-5.1
- Humanity's Last ExamGLM-5.1 by 6.523.630.1+6.5
- CritPtGLM-5.1 by 3.21.44.6+3.2
- GPQA DiamondGLM-5.1 by 1.185.786.8+1.1
FactsGLM-5.1
- AA-Omniscience · Non-hallucinationGLM-5.1 by 55.11570.1+55.1
- SimpleQA VerifiedGLM-5.1 by 23.610.434+23.6
- AA-Omniscience · AccuracyGLM-5.1 by 3.72023.7+3.7
MathGLM-5.1
- IMOAnswerBenchGLM-5.1 by 9.374.583.8+9.3
- AIME 2026GLM-5.1 by 6.189.295.3+6.1
- HMMT Feb. 2026GLM-5.1 by 5.477.282.6+5.4
Other results13 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 48.8-47.90.8+48.8
- τ²-Bench Telecom (AA run)GLM-5.1 by 37.859.997.7+37.8
- NL2RepoGLM-5.1 by 27.215.542.7+27.2
- Terminal-Bench 2.0GLM-5.1 by 26.142.969+26.1
- HLE (with tools)GLM-5.1 by 25.826.552.3+25.8
- Tool-DecathlonGLM-5.1 by 19.521.240.7+19.5
- AA Agentic IndexGLM-5.1 by 18.56.725.2+18.5
- Artificial Analysis Coding IndexGLM-5.1 by 12.443.455.8+12.4
- AA IntelligenceGLM-5.1 by 11.414.726.1+11.4
- HMMT Nov. 2025GLM-5.1 by 6.587.594+6.5
- τ³-BenchGLM-5.1 by 3.167.570.6+3.1
- GPQA (unspecified)GLM-5.1 by 1.884.386.1+1.8
- MMLU-Protie85.286tie
Questions people ask
Which is better, Gemma 4 31B or GLM-5.1?
GLM-5.1 wins six of the seven areas where both have results: coding, agents, reasoning, facts, math and long documents. Gemma 4 31B wins none, but costs 90% less. They are level on following instructions.
Which is better for coding?
GLM-5.1. It wins 7 of the 8 coding tests both models report; Gemma 4 31B wins none, and 1 is a tie.
Which is cheaper?
Gemma 4 31B costs $0.17 per million input tokens and $0.40 per million output tokens; GLM-5.1 costs $1.38 and $4.40. That makes Gemma 4 31B about 90% cheaper for the same work.
How do you compare the two?
We use the 37 benchmark tests both models have published scores on. The verdict counts the 24 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 13 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.