GLM-5.1 vs Granite 4.2 8B
Wins 5 of 6 areas
Coding · Agents · Reasoning · Facts · Long documents
Wins 1 of 6 areas
Following instructions
GLM-5.1 is the stronger all-rounder.Granite 4.2 8B is cheaper and better at following instructions.
Scores updated · 23 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.
- CodingWriting and fixing software60GLM-5.16 of 6 tests
- AgentsCarrying out multi-step tasks on its own30GLM-5.13 of 3 tests
- ReasoningHard problems that need careful thinking30GLM-5.13 of 3 tests
- FactsGetting facts right instead of making them up20GLM-5.12 of 2 tests
- Long documentsFinding answers in very long texts10GLM-5.11 of 1 test
- Following instructionsDoing exactly what it is asked01Granite 4.2 8B1 of 1 test
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.
Granite 4.2 8B costs 95% 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-5.1 pulls ahead
- Command-line tasks in a real terminalTerminal-Bench 2.1+43.4points ahead
- Fixes real GitHub issues in many programming languagesSWE-bench Multilingual+42.5points ahead
- Long, multi-file coding tasks in real codebasesSWE-bench Pro+39.3points ahead
Where Granite 4.2 8B pulls ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+3points ahead
Every test, side by side
All 23 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 43.461.818.4+43.4
- SWE-bench MultilingualGLM-5.1 by 42.573.330.8+42.5
- SWE-bench ProGLM-5.1 by 39.358.419.1+39.3
- SWE-bench VerifiedGLM-5.1 by 28.576.247.7+28.5
- SciCodeGLM-5.1 by 13.344.831.5+13.3
- LiveCodeBench v6GLM-5.1 by 12.585.773.2+12.5
AgentsGLM-5.1
- GDPValGLM-5.1 by 30.830.80+30.8
- τ-Bench V3 · BankingGLM-5.1 by 613.67.6+6
- Terminal-Bench 4.0GLM-5.1 by 220+2
ReasoningGLM-5.1
- GPQA DiamondGLM-5.1 by 23.786.863.1+23.7
- Humanity's Last ExamGLM-5.1 by 20.430.19.7+20.4
- CritPtGLM-5.1 by 4.34.60.3+4.3
FactsGLM-5.1
- AA-Omniscience · AccuracyGLM-5.1 by 12.523.711.2+12.5
- AA-Omniscience · Non-hallucinationGLM-5.1 by 2.170.168+2.1
Following instructionsGranite 4.2 8B
- IFBenchGranite 4.2 8B by 376.379.3+3
Other results7 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.
- Artificial Analysis Coding IndexGLM-5.1 by 33.455.822.4+33.4
- AA Agentic IndexGLM-5.1 by 21.525.23.7+21.5
- AA-OmniscienceGLM-5.1 by 18.10.8-17.2+18.1
- HMMT 2025GLM-5.1 by 15.79478.3+15.7
- AA IntelligenceGLM-5.1 by 1526.111.1+15
- τ³-BenchGLM-5.1 by 12.570.658.1+12.5
- MMLU-ProGLM-5.1 by 128674+12
Questions people ask
Which is better, GLM-5.1 or Granite 4.2 8B?
GLM-5.1 wins five of the six areas where both have results: coding, agents, reasoning, facts and long documents. Granite 4.2 8B wins following instructions, and costs 95% less.
Which is better for coding?
GLM-5.1. It wins 6 of the 6 coding tests both models report; Granite 4.2 8B wins none.
Which is cheaper?
GLM-5.1 costs $1.38 per million input tokens and $4.40 per million output tokens; Granite 4.2 8B costs $0.06 and $0.25. That makes Granite 4.2 8B about 95% cheaper for the same work.
How do you compare the two?
We use the 23 benchmark tests both models have published scores on. The verdict counts the 16 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 7 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.