Claude Sonnet 4.5 vs GLM-4.7
Wins 3 of 7 areas
Coding · Facts · Long documents
Wins 4 of 7 areas
Agents · Reasoning · Math · Following instructions
GLM-4.7 wins more areas, narrowly.Claude Sonnet 4.5 is better at coding.
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.
- ReasoningHard problems that need careful thinking12GLM-4.72 of 4 tests · 1 tie
- AgentsCarrying out multi-step tasks on its own12GLM-4.72 of 3 tests
- MathCompetition and research-level math01GLM-4.71 of 1 test
- Following instructionsDoing exactly what it is asked01GLM-4.71 of 1 test
- CodingWriting and fixing software32Claude Sonnet 4.53 of 7 tests · 2 ties
- FactsGetting facts right instead of making them up21Claude Sonnet 4.52 of 4 tests · 1 tie
- Long documentsFinding answers in very long texts10Claude Sonnet 4.51 of 1 test
Math, 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-4.7 costs 84% 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-4.7 pulls ahead
- Finds hard-to-locate facts by browsing the webBrowseComp+27.9points ahead
- Recent programming contest problemsLiveCodeBench v6+20.9points ahead
- Olympiad math problems with short answersIMOAnswerBench+16.1points ahead
Where Claude Sonnet 4.5 pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+43.9points ahead
- Customer-service tasks in a simulated bankτ-Bench V3 · Banking+12.3points ahead
- Command-line tasks in a real terminalTerminal-Bench 2.1+10.5points 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 Sonnet 4.5
- LiveCodeBench v6GLM-4.7 by 20.96484.9+20.9
- Terminal-Bench 2.1Claude Sonnet 4.5 by 10.555.845.3+10.5
- LMArena · WebDevGLM-4.7 by 41 rating points13941435+41 rating
- Terminal-Bench HardClaude Sonnet 4.5 by 3.835.631.8+3.8
- SWE-bench VerifiedClaude Sonnet 4.5 by 3.477.273.8+3.4
- SciCodetie45.745.1tie
- SWE-bench Multilingualtie6766.7tie
AgentsGLM-4.7
- BrowseCompGLM-4.7 by 27.924.152+27.9
- τ-Bench V3 · BankingClaude Sonnet 4.5 by 12.324.512.2+12.3
- GDPValGLM-4.7 by 5.320.525.8+5.3
ReasoningGLM-4.7
- Humanity's Last ExamGLM-4.7 by 9.617.827.4+9.6
- SimpleBenchClaude Sonnet 4.5 by 6.654.347.7+6.6
- GPQA DiamondGLM-4.7 by 2.583.485.9+2.5
- CritPttie1.11.7tie
FactsClaude Sonnet 4.5
- AA-Omniscience · Non-hallucinationClaude Sonnet 4.5 by 43.950.97+43.9
- AA-Omniscience · AccuracyClaude Sonnet 4.5 by 3.632.929.3+3.6
- SimpleQA VerifiedGLM-4.7 by 1.530.732.2+1.5
- Vectara HHEM hallucination ratelower is bettertie1211.7tie
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.
- AA-OmniscienceClaude Sonnet 4.5 by 36.3-0.1-36.4+36.3
- HMMT Feb. 2025GLM-4.7 by 29.667.597.1+29.6
- BrowseComp-ZHGLM-4.7 by 24.242.466.6+24.2
- τ²-Bench Telecom (AA run)GLM-4.7 by 17.878.195.9+17.8
- Terminal-BenchClaude Sonnet 4.5 by 16.75033.3+16.7
- xbench-DeepSearchClaude Sonnet 4.5 by 13.76652.3+13.7
- HMMT Nov. 2025GLM-4.7 by 11.881.793.5+11.8
- HLE (with tools)GLM-4.7 by 10.83242.8+10.8
- τ²-BenchClaude Sonnet 4.5 by 10.69887.4+10.6
- Terminal-Bench 2.0Claude Sonnet 4.5 by 95041+9
- AA Agentic IndexGLM-4.7 by 8.717.526.2+8.7
- AIME 2025GLM-4.7 by 8.78795.7+8.7
- Artificial Analysis Coding IndexClaude Sonnet 4.5 by 6.852.145.3+6.8
- vectara_avg_summary_lengthClaude Sonnet 4.5 by 57.2 rating points127.870.6+57.2 rating
- frontiermath_tier_4_v1Claude Sonnet 4.5 by 4.24.20+4.2
- vectara_answer_rateGLM-4.7 by 4.295.699.8+4.2
- MMLU-ProClaude Sonnet 4.5 by 3.287.584.3+3.2
- AA IntelligenceGLM-4.7 by 1.520.722.2+1.5
- vectara_factual_consistencytie8888.3tie
Questions people ask
Which is better, Claude Sonnet 4.5 or GLM-4.7?
GLM-4.7 wins four of the seven areas where both have results: agents, reasoning, math and following instructions. Claude Sonnet 4.5 wins coding, facts and long documents.
Which is better for coding?
Claude Sonnet 4.5. It wins 3 of the 7 coding tests both models report; GLM-4.7 wins 2, and 2 are ties.
Which is cheaper?
Claude Sonnet 4.5 costs $3.00 per million input tokens and $15.00 per million output tokens; GLM-4.7 costs $0.60 and $2.20. That makes GLM-4.7 about 84% 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.