Gemini 2.5 Pro vs GLM-4.6
Wins 3 of 6 areas
Reasoning · Facts · Long documents
Wins 2 of 6 areas
Coding · Agents
Gemini 2.5 Pro wins more areas, narrowly.GLM-4.6 is cheaper and better at agents.
Scores updated · 41 tests both models report · How we compare
Where each one wins
Tests won in each of the six 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 thinking30Gemini 2.5 Pro3 of 3 tests
- FactsGetting facts right instead of making them up30Gemini 2.5 Pro3 of 3 tests
- Long documentsFinding answers in very long texts10Gemini 2.5 Pro1 of 1 test
- AgentsCarrying out multi-step tasks on its own03GLM-4.63 of 3 tests
- CodingWriting and fixing software23GLM-4.63 of 5 tests
- Following instructionsDoing exactly what it is asked11Even1 each
Long documents rests on a single test.
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-4.6 costs 75% 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 2.5 Pro pulls ahead
- Reasons across sets of long documentsAA-LCR+15points ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+12.2points ahead
- Code for real scientific research problemsSciCode+7.9points ahead
Where GLM-4.6 pulls ahead
- Finds hard-to-locate facts by browsing the webBrowseComp+35.2points ahead
- Command-line tasks in a real terminalTerminal-Bench 2.1+20.9points ahead
- Fixes real GitHub issues in Python projectsSWE-bench Verified+4.8points ahead
Every test, side by side
All 41 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingGLM-4.6
- Terminal-Bench 2.1GLM-4.6 by 20.928.549.4+20.9
- LMArena · WebDevGLM-4.6 by 117 rating points12241341+117 rating
- SciCodeGemini 2.5 Pro by 7.946.338.4+7.9
- SWE-bench VerifiedGLM-4.6 by 4.863.268+4.8
- Terminal-Bench HardGemini 2.5 Pro by 1.526.525+1.5
AgentsGLM-4.6
- BrowseCompGLM-4.6 by 35.29.945.1+35.2
- GDPValGLM-4.6 by 13013+13
- τ-Bench V3 · BankingGLM-4.6 by 3.79.713.4+3.7
ReasoningGemini 2.5 Pro
- GPQA DiamondGemini 2.5 Pro by 5.683.678+5.6
- Humanity's Last ExamGemini 2.5 Pro by 3.51814.5+3.5
- CritPtGemini 2.5 Pro by 1.52.61.1+1.5
FactsGemini 2.5 Pro
- AA-Omniscience · AccuracyGemini 2.5 Pro by 12.23926.9+12.2
- AA-Omniscience · Non-hallucinationGemini 2.5 Pro by 3.29.15.9+3.2
- Vectara HHEM hallucination ratelower is betterGemini 2.5 Pro by 2.579.5+2.5
Following instructionsEven
- IFBenchGemini 2.5 Pro by 5.348.743.4+5.3
- Multi-ChallengeGLM-4.6 by 1.353.654.9+1.3
Other results24 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-OmniscienceGemini 2.5 Pro by 25.6-16.4-41.9+25.6
- HMMT 2025GLM-4.6 by 2365.788.7+23
- τ²-BenchGLM-4.6 by 21.25475.2+21.2
- BrowseComp-ZHGLM-4.6 by 17.332.249.5+17.3
- τ²-Bench Telecom (AA run)GLM-4.6 by 16.454.170.5+16.4
- Terminal-BenchGLM-4.6 by 15.225.340.5+15.2
- AA Agentic IndexGLM-4.6 by 15.13.518.6+15.1
- xbench-DeepSearchGLM-4.6 by 145670+14
- FinSearchComp-globalGemini 2.5 Pro by 13.442.629.2+13.4
- GAIA (text only)GLM-4.6 by 11.760.271.9+11.7
- HMMT Nov. 2025GLM-4.6 by 11.78091.7+11.7
- AIME 2025GLM-4.6 by 10.98393.9+10.9
- HMMT Feb. 2025GLM-4.6 by 8.480.889.2+8.4
- LiveCodeBenchGLM-4.6 by 5.374.279.5+5.3
- vectara_answer_rateGemini 2.5 Pro by 4.699.194.5+4.6
- theagentcompanyGemini 2.5 Pro by 4.339.335+4.3
- AA IntelligenceGLM-4.6 by 3.51518.5+3.5
- vectara_avg_summary_lengthGemini 2.5 Pro by 29.2 rating points106.477.2+29.2 rating
- MMLU-ProGemini 2.5 Pro by 2.88683.2+2.8
- vectara_factual_consistencyGemini 2.5 Pro by 2.59390.5+2.5
- ArtifactsBenchGLM-4.6 by 2.157.759.8+2.1
- frontiermath_tier_4_v1Gemini 2.5 Pro by 2.14.22.1+2.1
- HLE (with tools)GLM-4.6 by 228.430.4+2
- Artificial Analysis Coding Indextie46.745.8tie
Questions people ask
Which is better, Gemini 2.5 Pro or GLM-4.6?
Gemini 2.5 Pro wins three of the six areas where both have results: reasoning, facts and long documents. GLM-4.6 wins coding and agents, and costs 75% less. They are level on following instructions.
Which is better for coding?
GLM-4.6. It wins 3 of the 5 coding tests both models report; Gemini 2.5 Pro wins 2.
Which is cheaper?
Gemini 2.5 Pro costs $1.25 per million input tokens and $10.00 per million output tokens; GLM-4.6 costs $0.57 and $2.20. That makes GLM-4.6 about 75% cheaper for the same work.
How do you compare the two?
We use the 41 benchmark tests both models have published scores on. The verdict counts the 17 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 24 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.