GLM-5.2 vs Kimi K2.5
Wins 5 of 7 areas
Coding · Agents · Reasoning · Math · Following instructions
Wins 0 of 7 areas
—
GLM-5.2 is the stronger all-rounder.Kimi K2.5 is cheaper.
Scores updated · 40 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 software50GLM-5.25 of 5 tests
- AgentsCarrying out multi-step tasks on its own40GLM-5.24 of 4 tests
- ReasoningHard problems that need careful thinking40GLM-5.24 of 4 tests
- MathCompetition and research-level math30GLM-5.23 of 3 tests
- Following instructionsDoing exactly what it is asked10GLM-5.21 of 1 test
- FactsGetting facts right instead of making them up11Even1 each · 1 tie
- 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.
Kimi K2.5 costs 38% 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-5.2 pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+39.4points ahead
- Command-line tasks in a real terminalTerminal-Bench 2.1+32.2points ahead
- Real work tasks from 44 professionsGDPVal+26.5points ahead
Where Kimi K2.5 pulls ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+10.9points ahead
Every test, side by side
All 40 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingGLM-5.2
- Terminal-Bench 2.1GLM-5.2 by 32.277.945.7+32.2
- LMArena · WebDevGLM-5.2 by 169 rating points16051436+169 rating
- Terminal-Bench HardGLM-5.2 by 1650.834.8+16
- SWE-bench ProGLM-5.2 by 11.462.150.7+11.4
- SciCodeGLM-5.2 by 2.251.249+2.2
AgentsGLM-5.2
- GDPValGLM-5.2 by 26.543.717.2+26.5
- AA ApexAgentsGLM-5.2 by 22.233.711.5+22.2
- τ-Bench V3 · BankingGLM-5.2 by 20.434.614.2+20.4
- MCP AtlasGLM-5.2 by 1376.863.8+13
ReasoningGLM-5.2
- CritPtGLM-5.2 by 17.820.93.1+17.8
- ARC-AGI-2GLM-5.2 by 1122.811.8+11
- Humanity's Last ExamGLM-5.2 by 10.441.130.7+10.4
- GPQA DiamondGLM-5.2 by 1.689.587.9+1.6
FactsEven
- AA-Omniscience · Non-hallucinationGLM-5.2 by 39.473.734.3+39.4
- AA-Omniscience · AccuracyKimi K2.5 by 10.924.335.2+10.9
- SimpleQA Verifiedtie34.234.3tie
MathGLM-5.2
- IMOAnswerBenchGLM-5.2 by 9.29181.8+9.2
- HMMT Feb. 2026GLM-5.2 by 5.492.587.1+5.4
- AIME 2026GLM-5.2 by 3.499.295.8+3.4
Other results19 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.
- GDPval-AA v2GLM-5.2 by 499 rating points15081009+499 rating
- CyberGymGLM-5.2 by 35.977.241.3+35.9
- Artificial Analysis Coding IndexGLM-5.2 by 2268.846.8+22
- Tool-DecathlonGLM-5.2 by 20.448.227.8+20.4
- ToolathlonGLM-5.2 by 20.448.227.8+20.4
- AA Agentic IndexGLM-5.2 by 17.739.421.7+17.7
- NL2RepoGLM-5.2 by 16.948.932+16.9
- τ³-Bench BankingGLM-5.2 by 12.626.814.2+12.6
- AA-OmniscienceGLM-5.2 by 11.74.4-7.3+11.7
- ARC-AGI-1GLM-5.2 by 11.77765.3+11.7
- ResearchRubricsGLM-5.2 by 11.671.159.5+11.6
- SWEBench Pro PublicGLM-5.2 by 11.462.150.7+11.4
- AA IntelligenceGLM-5.2 by 10.233.723.5+10.2
- Global-MMLU-LiteGLM-5.2 by 5.289.284+5.2
- HMMT Nov. 2025GLM-5.2 by 5.294.489.2+5.2
- HLE (with tools)GLM-5.2 by 4.554.750.2+4.5
- τ²-Bench Telecom (AA run)GLM-5.2 by 3.299.195.9+3.2
- HMMT 2025Kimi K2.5 by 194.495.4+1
- StrongREJECTKimi K2.5 by 198.599.5+1
Questions people ask
Which is better, GLM-5.2 or Kimi K2.5?
GLM-5.2 wins five of the seven areas where both have results: coding, agents, reasoning, math and following instructions. Kimi K2.5 wins none, but costs 38% less. They are level on facts and long documents.
Which is better for coding?
GLM-5.2. It wins 5 of the 5 coding tests both models report; Kimi K2.5 wins none.
Which is cheaper?
GLM-5.2 costs $1.40 per million input tokens and $4.40 per million output tokens; Kimi K2.5 costs $0.60 and $3.00. That makes Kimi K2.5 about 38% cheaper for the same work.
How do you compare the two?
We use the 40 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 19 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.