GLM-5.1 vs Kimi K2.5
Wins 3 of 7 areas
Coding · Agents · Following instructions
Wins 1 of 7 areas
Long documents
GLM-5.1 wins more areas, narrowly.Kimi K2.5 is cheaper and better at long documents.
Scores updated · 42 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 software41GLM-5.14 of 8 tests · 3 ties
- AgentsCarrying out multi-step tasks on its own30GLM-5.13 of 4 tests · 1 tie
- Following instructionsDoing exactly what it is asked10GLM-5.11 of 1 test
- Long documentsFinding answers in very long texts01Kimi K2.51 of 1 test
- ReasoningHard problems that need careful thinking11Even1 each · 1 tie
- FactsGetting facts right instead of making them up11Even1 each · 1 tie
- MathCompetition and research-level math11Even1 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 three tests each model wins by the widest margin. Scores are out of 100.
Where GLM-5.1 pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+35.8points ahead
- Command-line tasks in a real terminalTerminal-Bench 2.1+16.1points ahead
- Real work tasks from 44 professionsGDPVal+13.8points ahead
Where Kimi K2.5 pulls ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+11.5points ahead
- Harvard-MIT high-school math contest problemsHMMT Feb. 2026+4.5points ahead
- Reasons across sets of long documentsAA-LCR+4.3points ahead
Every test, side by side
All 42 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingGLM-5.1
- Terminal-Bench 2.1GLM-5.1 by 16.161.845.7+16.1
- Terminal-Bench HardGLM-5.1 by 8.443.234.8+8.4
- SWE-bench ProGLM-5.1 by 7.758.450.7+7.7
- LMArena · WebDevGLM-5.1 by 72 rating points15081436+72 rating
- SciCodeKimi K2.5 by 4.244.849+4.2
- LiveCodeBench v6tie85.785tie
- SWE-bench Verifiedtie76.276.8tie
- SWE-bench Multilingualtie73.373tie
AgentsGLM-5.1
- GDPValGLM-5.1 by 13.83117.2+13.8
- MCP AtlasGLM-5.1 by 871.863.8+8
- BrowseCompGLM-5.1 by 4.479.374.9+4.4
- τ-Bench V3 · Bankingtie13.614.2tie
ReasoningEven
- CritPtGLM-5.1 by 1.54.63.1+1.5
- GPQA DiamondKimi K2.5 by 1.186.887.9+1.1
- Humanity's Last Examtie30.130.7tie
FactsEven
- AA-Omniscience · Non-hallucinationGLM-5.1 by 35.870.134.3+35.8
- AA-Omniscience · AccuracyKimi K2.5 by 11.523.735.2+11.5
- SimpleQA Verifiedtie3434.3tie
MathEven
- HMMT Feb. 2026Kimi K2.5 by 4.582.687.1+4.5
- IMOAnswerBenchGLM-5.1 by 283.881.8+2
- AIME 2026tie95.395.8tie
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.
- Vending-Bench 2GLM-5.1 by 562243 rating points5634411198+562243 rating
- CyberGymGLM-5.1 by 27.468.741.3+27.4
- Terminal-Bench 2.0GLM-5.1 by 18.26950.8+18.2
- Tool-DecathlonGLM-5.1 by 12.940.727.8+12.9
- ToolathlonGLM-5.1 by 12.940.727.8+12.9
- NL2RepoGLM-5.1 by 10.742.732+10.7
- Artificial Analysis Coding IndexGLM-5.1 by 955.846.8+9
- frontiermath_tier_4_v1GLM-5.1 by 8.312.54.2+8.3
- AA-OmniscienceGLM-5.1 by 8.20.8-7.3+8.2
- HMMT Nov. 2025GLM-5.1 by 4.89489.2+4.8
- τ³-BenchGLM-5.1 by 4.670.666+4.6
- browsecomp_with_context_managerGLM-5.1 by 4.479.374.9+4.4
- AA Agentic IndexGLM-5.1 by 3.525.221.7+3.5
- AA IntelligenceGLM-5.1 by 2.626.123.5+2.6
- HLE (with tools)GLM-5.1 by 2.152.350.2+2.1
- τ²-Bench Telecom (AA run)GLM-5.1 by 1.897.795.9+1.8
- HMMT 2025Kimi K2.5 by 1.49495.4+1.4
- LiveBenchGLM-5.1 by 1.170.269.1+1.1
- MMLU-ProKimi K2.5 by 1.18687.1+1.1
Questions people ask
Which is better, GLM-5.1 or Kimi K2.5?
GLM-5.1 wins three of the seven areas where both have results: coding, agents and following instructions. Kimi K2.5 wins long documents, and costs 38% less. They are level on reasoning, facts and math.
Which is better for coding?
GLM-5.1. It wins 4 of the 8 coding tests both models report; Kimi K2.5 wins 1, and 3 are ties.
Which is cheaper?
GLM-5.1 costs $1.38 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 42 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 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.