Claude Fable 5.1 vs GLM-5.2
Wins 7 of 7 areas
Coding · Agents · Reasoning · Facts · Math · Long documents · Following instructions
Wins 0 of 7 areas
—
Claude Fable 5.1 is the stronger all-rounder.GLM-5.2 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 software60Claude Fable 5.16 of 6 tests
- ReasoningHard problems that need careful thinking60Claude Fable 5.16 of 6 tests
- AgentsCarrying out multi-step tasks on its own40Claude Fable 5.14 of 4 tests
- MathCompetition and research-level math30Claude Fable 5.13 of 3 tests
- FactsGetting facts right instead of making them up21Claude Fable 5.12 of 3 tests
- Long documentsFinding answers in very long texts10Claude Fable 5.11 of 1 test
- Following instructionsDoing exactly what it is asked10Claude Fable 5.11 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.
GLM-5.2 costs 90% 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 Claude Fable 5.1 pulls ahead
- Abstract visual puzzles that people can solveARC-AGI-2+67.2points ahead
- Extremely hard research-level math problemsFrontierMath Tier 4+58.5points ahead
- Complex command-line tasks across many fieldsTerminal-Bench 4.0+51points ahead
Where GLM-5.2 pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+46.3points 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.
CodingClaude Fable 5.1
- SWE-bench ProClaude Fable 5.1 by 19.181.262.1+19.1
- LiveBench · Agentic CodingClaude Fable 5.1 by 14.366.151.8+14.3
- LMArena · WebDevClaude Fable 5.1 by 138 rating points17421604+138 rating
- Terminal-Bench 2.1Claude Fable 5.1 by 13.591.477.9+13.5
- SciCodeClaude Fable 5.1 by 11.963.151.2+11.9
- LiveBench · CodingClaude Fable 5.1 by 6.786.479.7+6.7
AgentsClaude Fable 5.1
- Terminal-Bench 4.0Claude Fable 5.1 by 51521+51
- GDPValClaude Fable 5.1 by 19.162.743.6+19.1
- τ-Bench V3 · BankingClaude Fable 5.1 by 12.647.234.6+12.6
- AA IT-Bench SREClaude Fable 5.1 by 6.849.542.7+6.8
ReasoningClaude Fable 5.1
- ARC-AGI-2Claude Fable 5.1 by 67.29022.8+67.2
- SimpleBenchClaude Fable 5.1 by 27.886.658.8+27.8
- Humanity's Last ExamClaude Fable 5.1 by 1859.141.1+18
- LiveBench · ReasoningClaude Fable 5.1 by 13.191.778.6+13.1
- CritPtClaude Fable 5.1 by 8.829.720.9+8.8
- GPQA DiamondClaude Fable 5.1 by 4.293.789.5+4.2
FactsClaude Fable 5.1
- AA-Omniscience · Non-hallucinationGLM-5.2 by 46.327.473.7+46.3
- AA-Omniscience · AccuracyClaude Fable 5.1 by 42.967.224.3+42.9
- SimpleQA VerifiedClaude Fable 5.1 by 36.670.834.2+36.6
MathClaude Fable 5.1
- FrontierMath Tier 4Claude Fable 5.1 by 58.587.829.3+58.5
- FrontierMath Tiers 1-3 (v2)Claude Fable 5.1 by 3190.259.2+31
- LiveBench · MathematicsClaude Fable 5.1 by 7.29789.8+7.2
Following instructionsClaude Fable 5.1
- LiveBench · Instruction FollowingClaude Fable 5.1 by 10.77362.3+10.7
Other results16 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-OmniscienceClaude Fable 5.1 by 39.143.54.4+39.1
- GDPval-AA v2Claude Fable 5.1 by 345 rating points18531508+345 rating
- GDPval-AA v2 EloClaude Fable 5.1 by 325 rating points18351510+325 rating
- OfficeQA ProClaude Fable 5.1 by 27.66941.4+27.6
- Program BenchClaude Fable 5.1 by 23.987.663.7+23.9
- DeepSWE 1.1Claude Fable 5.1 by 23.467.444+23.4
- ARC-AGI-1Claude Fable 5.1 by 20.597.577+20.5
- AA IntelligenceClaude Fable 5.1 by 19.753.433.7+19.7
- AA Agentic IndexClaude Fable 5.1 by 18.65839.4+18.6
- Toolathlon VerifiedClaude Fable 5.1 by 17.977.859.9+17.9
- HiL-Bench (Tools-allowed)Claude Fable 5.1 by 17.861.543.7+17.8
- livebench_languageClaude Fable 5.1 by 13.389.576.2+13.3
- Artificial Analysis Coding IndexClaude Fable 5.1 by 12.881.668.8+12.8
- HLE (with tools)Claude Fable 5.1 by 10.965.654.7+10.9
- livebench_data_analysisClaude Fable 5.1 by 6.680.373.7+6.6
- PostTrainBenchClaude Fable 5.1 by 5.940.234.3+5.9
Questions people ask
Which is better, Claude Fable 5.1 or GLM-5.2?
Claude Fable 5.1 wins all seven areas where both have results: coding, agents, reasoning, facts, math, long documents and following instructions. GLM-5.2 wins none, but costs 90% less.
Which is better for coding?
Claude Fable 5.1. It wins 6 of the 6 coding tests both models report; GLM-5.2 wins none.
Which is cheaper?
Claude Fable 5.1 costs $10.00 per million input tokens and $50.00 per million output tokens; GLM-5.2 costs $1.40 and $4.40. That makes GLM-5.2 about 90% 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 24 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 16 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.