GLM-5.1 vs Kimi K3
Wins 0 of 6 areas
—
Wins 6 of 6 areas
Coding · Agents · Reasoning · Facts · Math · Long documents
Kimi K3 is the stronger all-rounder.GLM-5.1 is cheaper.
Scores updated · 31 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.
- AgentsCarrying out multi-step tasks on its own06Kimi K36 of 6 tests
- ReasoningHard problems that need careful thinking04Kimi K34 of 4 tests
- CodingWriting and fixing software03Kimi K33 of 3 tests
- MathCompetition and research-level math03Kimi K33 of 3 tests
- FactsGetting facts right instead of making them up12Kimi K32 of 3 tests
- Long documentsFinding answers in very long texts01Kimi K31 of 1 test
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-5.1 costs 68% 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 Kimi K3 pulls ahead
- Unpublished advanced math problemsFrontierMath Tiers 1-3 (v2)+35.4points ahead
- Customer-service tasks in a simulated bankτ-Bench V3 · Banking+32.4points ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+23.9points ahead
Where GLM-5.1 pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+23.3points ahead
Every test, side by side
All 31 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingKimi K3
- Terminal-Bench 2.1Kimi K3 by 23.261.885+23.2
- LMArena · WebDevKimi K3 by 149 rating points15091658+149 rating
- SciCodeKimi K3 by 14.744.859.5+14.7
AgentsKimi K3
- τ-Bench V3 · BankingKimi K3 by 32.413.646+32.4
- GDPValKimi K3 by 20.83151.8+20.8
- MCP AtlasKimi K3 by 12.471.884.2+12.4
- BrowseCompKimi K3 by 11.979.391.2+11.9
- Terminal-Bench 4.0Kimi K3 by 10.6212.6+10.6
- AA IT-Bench SREKimi K3 by 7.440.347.7+7.4
ReasoningKimi K3
- CritPtKimi K3 by 18.84.623.4+18.8
- Humanity's Last ExamKimi K3 by 16.830.146.9+16.8
- GPQA DiamondKimi K3 by 6.786.893.5+6.7
- SimpleBenchKimi K3 by 5.655.160.7+5.6
FactsKimi K3
- AA-Omniscience · AccuracyKimi K3 by 23.923.747.6+23.9
- AA-Omniscience · Non-hallucinationGLM-5.1 by 23.370.146.8+23.3
- SimpleQA VerifiedKimi K3 by 16.63450.6+16.6
MathKimi K3
- FrontierMath Tiers 1-3 (v2)Kimi K3 by 35.436.872.2+35.4
- HMMT Feb. 2026Kimi K3 by 14.482.697+14.4
- AIME 2026Kimi K3 by 1.495.396.7+1.4
Other results11 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.
- DeepSWEKimi K3 by 49.51867.5+49.5
- ToolathlonKimi K3 by 32.540.773.2+32.5
- Program BenchKimi K3 by 26.950.977.8+26.9
- AA Agentic IndexKimi K3 by 25.425.250.6+25.4
- Artificial Analysis Coding IndexKimi K3 by 20.455.876.2+20.4
- AA-OmniscienceKimi K3 by 18.80.819.7+18.8
- AA IntelligenceKimi K3 by 17.526.143.6+17.5
- PostTrainBenchKimi K3 by 16.520.136.6+16.5
- NL2RepoKimi K3 by 15.342.758+15.3
- CyberGymKimi K3 by 11.368.780+11.3
- HLE (with tools)Kimi K3 by 7.552.359.8+7.5
Questions people ask
Which is better, GLM-5.1 or Kimi K3?
Kimi K3 wins all six areas where both have results: coding, agents, reasoning, facts, math and long documents. GLM-5.1 wins none, but costs 68% less.
Which is better for coding?
Kimi K3. It wins 3 of the 3 coding tests both models report; GLM-5.1 wins none.
Which is cheaper?
GLM-5.1 costs $1.38 per million input tokens and $4.40 per million output tokens; Kimi K3 costs $3.00 and $15.00. That makes GLM-5.1 about 68% cheaper for the same work.
How do you compare the two?
We use the 31 benchmark tests both models have published scores on. The verdict counts the 20 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 11 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.