Gemini 3.1 Pro vs GLM-5
Wins 6 of 7 areas
Coding · Agents · Reasoning · Math · Long documents · Following instructions
Wins 0 of 7 areas
—
Gemini 3.1 Pro is the stronger all-rounder.GLM-5 is cheaper.
Scores updated · 43 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.
- ReasoningHard problems that need careful thinking50Gemini 3.1 Pro5 of 5 tests
- CodingWriting and fixing software40Gemini 3.1 Pro4 of 5 tests · 1 tie
- AgentsCarrying out multi-step tasks on its own31Gemini 3.1 Pro3 of 4 tests
- MathCompetition and research-level math31Gemini 3.1 Pro3 of 4 tests
- Long documentsFinding answers in very long texts10Gemini 3.1 Pro1 of 1 test
- Following instructionsDoing exactly what it is asked10Gemini 3.1 Pro1 of 1 test
- FactsGetting facts right instead of making them up11Even1 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.
GLM-5 costs 70% less for the same work.
The biggest differences
The three tests each model wins by the widest margin. Scores are out of 100.
Where Gemini 3.1 Pro pulls ahead
- Abstract visual puzzles that people can solveARC-AGI-2+72.2points ahead
- Proof problems from the US Math OlympiadUSAMO 2026+39.3points ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+28.6points ahead
Where GLM-5 pulls ahead
- Real work tasks from 44 professionsGDPVal+29.9points ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+15.6points ahead
- Olympiad math problems with short answersIMOAnswerBench+1.5points ahead
Every test, side by side
All 43 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingGemini 3.1 Pro
- SciCodeGemini 3.1 Pro by 12.558.746.2+12.5
- Terminal-Bench HardGemini 3.1 Pro by 10.653.843.2+10.6
- SWE-bench VerifiedGemini 3.1 Pro by 2.880.677.8+2.8
- LMArena · WebDevGemini 3.1 Pro by 13 rating points14471434+13 rating
- SWE-bench Protie54.255.1tie
AgentsGemini 3.1 Pro
- GDPValGLM-5 by 29.914.744.6+29.9
- AA ApexAgentsGemini 3.1 Pro by 17.53214.5+17.5
- BrowseCompGemini 3.1 Pro by 1085.975.9+10
- MCP AtlasGemini 3.1 Pro by 1.469.267.8+1.4
ReasoningGemini 3.1 Pro
- ARC-AGI-2Gemini 3.1 Pro by 72.277.14.9+72.2
- SimpleBenchGemini 3.1 Pro by 26.479.653.2+26.4
- Humanity's Last ExamGemini 3.1 Pro by 17.74729.3+17.7
- CritPtGemini 3.1 Pro by 15.717.72+15.7
- GPQA DiamondGemini 3.1 Pro by 12.194.182+12.1
FactsEven
- AA-Omniscience · AccuracyGemini 3.1 Pro by 28.654.926.3+28.6
- AA-Omniscience · Non-hallucinationGLM-5 by 15.649.164.7+15.6
- Vectara HHEM hallucination ratelower is bettertie10.410.1tie
MathGemini 3.1 Pro
- USAMO 2026Gemini 3.1 Pro by 39.374.435.1+39.3
- HMMT Feb. 2026Gemini 3.1 Pro by 11.994.782.8+11.9
- AIME 2026Gemini 3.1 Pro by 2.998.395.4+2.9
- IMOAnswerBenchGLM-5 by 1.58182.5+1.5
Following instructionsGemini 3.1 Pro
- IFBenchGemini 3.1 Pro by 4.877.172.3+4.8
Other results20 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.
- Vending-Bench 2GLM-5 by 3521 rating points911.24432+3521 rating
- ARC-AGI-1Gemini 3.1 Pro by 53.39844.7+53.3
- AA Agentic IndexGLM-5 by 52.810.363.1+52.8
- AA-OmniscienceGemini 3.1 Pro by 31.631.90.3+31.6
- Artificial Analysis Coding IndexGemini 3.1 Pro by 24.668.844.2+24.6
- frontiermath_tier_4_v1Gemini 3.1 Pro by 14.616.72.1+14.6
- Terminal-Bench 2.0Gemini 3.1 Pro by 12.368.556.2+12.3
- Tool-DecathlonGemini 3.1 Pro by 10.848.838+10.8
- browsecomp_with_context_managerGemini 3.1 Pro by 1085.975.9+10
- t2-benchGemini 3.1 Pro by 9.699.389.7+9.6
- CyberGymGLM-5 by 9.538.848.3+9.5
- vectara_avg_summary_lengthGemini 3.1 Pro by 33.3 rating points107.774.4+33.3 rating
- τ²-Bench Telecom (AA run)GLM-5 by 2.695.698.2+2.6
- NL2RepoGLM-5 by 2.533.435.9+2.5
- HMMT Nov. 2025GLM-5 by 2.194.896.9+2.1
- τ³-BenchGLM-5 by 2.167.169.2+2.1
- AA IntelligenceGemini 3.1 Pro by 1.829.727.9+1.8
- HLE (with tools)Gemini 3.1 Pro by 151.450.4+1
- vectara_answer_ratetie99.499.7tie
- vectara_factual_consistencytie89.689.9tie
Questions people ask
Which is better, Gemini 3.1 Pro or GLM-5?
Gemini 3.1 Pro wins six of the seven areas where both have results: coding, agents, reasoning, math, long documents and following instructions. GLM-5 wins none, but costs 70% less. They are level on facts.
Which is better for coding?
Gemini 3.1 Pro. It wins 4 of the 5 coding tests both models report; GLM-5 wins none, and 1 is a tie.
Which is cheaper?
Gemini 3.1 Pro costs $2.00 per million input tokens and $12.00 per million output tokens; GLM-5 costs $1.00 and $3.20. That makes GLM-5 about 70% cheaper for the same work.
How do you compare the two?
We use the 43 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 20 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.