Claude Opus 4.5 vs GLM-4.7
Wins 5 of 7 areas
Coding · Reasoning · Facts · Math · Long documents
Wins 1 of 7 areas
Following instructions
Claude Opus 4.5 is the stronger all-rounder.GLM-4.7 is cheaper and better at following instructions.
Scores updated · 36 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 software41Claude Opus 4.54 of 6 tests · 1 tie
- FactsGetting facts right instead of making them up30Claude Opus 4.53 of 4 tests · 1 tie
- ReasoningHard problems that need careful thinking20Claude Opus 4.52 of 3 tests · 1 tie
- MathCompetition and research-level math10Claude Opus 4.51 of 1 test
- Long documentsFinding answers in very long texts10Claude Opus 4.51 of 1 test
- Following instructionsDoing exactly what it is asked01GLM-4.71 of 1 test
- AgentsCarrying out multi-step tasks on its own11Even1 each
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 91% less for the same work.
The biggest differences
The three tests each model wins by the widest margin. Scores are out of 100.
Where Claude Opus 4.5 pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+32points ahead
- Real work tasks from 44 professionsGDPVal+21.5points ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+17.3points ahead
Where GLM-4.7 pulls ahead
- Fixes real GitHub issues in many programming languagesSWE-bench Multilingual+59.7points ahead
- Finds hard-to-locate facts by browsing the webBrowseComp+15points ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+9.9points ahead
Every test, side by side
All 36 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingClaude Opus 4.5
- SWE-bench MultilingualGLM-4.7 by 59.7766.7+59.7
- Terminal-Bench HardClaude Opus 4.5 by 15.24731.8+15.2
- SWE-bench VerifiedClaude Opus 4.5 by 7.180.973.8+7.1
- SciCodeClaude Opus 4.5 by 4.449.545.1+4.4
- LMArena · WebDevClaude Opus 4.5 by 34 rating points14691435+34 rating
- LiveCodeBench v6tie84.884.9tie
AgentsEven
- GDPValClaude Opus 4.5 by 21.547.325.8+21.5
- BrowseCompGLM-4.7 by 153752+15
ReasoningClaude Opus 4.5
- CritPtClaude Opus 4.5 by 2.94.61.7+2.9
- Humanity's Last ExamClaude Opus 4.5 by 2.730.127.4+2.7
- GPQA Diamondtie86.685.9tie
FactsClaude Opus 4.5
- AA-Omniscience · Non-hallucinationClaude Opus 4.5 by 32397+32
- AA-Omniscience · AccuracyClaude Opus 4.5 by 17.346.629.3+17.3
- SimpleQA VerifiedClaude Opus 4.5 by 13.545.732.2+13.5
- Vectara HHEM hallucination ratelower is bettertie10.911.7tie
Other results18 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 Opus 4.5 by 50.414-36.4+50.4
- AA Agentic IndexClaude Opus 4.5 by 33.459.626.2+33.4
- CyberGymClaude Opus 4.5 by 27.150.623.5+27.1
- Terminal-Bench 2.0Claude Opus 4.5 by 18.359.341+18.3
- τ²-BenchClaude Opus 4.5 by 10.898.287.4+10.8
- AA IntelligenceClaude Opus 4.5 by 6.929.122.2+6.9
- τ²-Bench Telecom (AA run)GLM-4.7 by 6.489.595.9+6.4
- MMLU-ProClaude Opus 4.5 by 5.289.584.3+5.2
- vectara_avg_summary_lengthClaude Opus 4.5 by 43.9 rating points114.570.6+43.9 rating
- frontiermath_tier_4_v1Claude Opus 4.5 by 4.24.20+4.2
- HMMT Feb. 2025GLM-4.7 by 4.292.997.1+4.2
- AIME 2025GLM-4.7 by 2.992.895.7+2.9
- Artificial Analysis Coding IndexClaude Opus 4.5 by 2.547.845.3+2.5
- vectara_answer_rateGLM-4.7 by 1.198.799.8+1.1
- vectara_factual_consistencytie89.188.3tie
- AIME 2026 I (Tools-allowed)tie93.392.9tie
- HLE (with tools)tie43.242.8tie
- HMMT Nov. 2025tie93.393.5tie
Questions people ask
Which is better, Claude Opus 4.5 or GLM-4.7?
Claude Opus 4.5 wins five of the seven areas where both have results: coding, reasoning, facts, math and long documents. GLM-4.7 wins following instructions, and costs 91% less. They are level on agents.
Which is better for coding?
Claude Opus 4.5. It wins 4 of the 6 coding tests both models report; GLM-4.7 wins 1, and 1 is a tie.
Which is cheaper?
Claude Opus 4.5 costs $5.00 per million input tokens and $25.00 per million output tokens; GLM-4.7 costs $0.60 and $2.20. That makes GLM-4.7 about 91% cheaper for the same work.
How do you compare the two?
We use the 36 benchmark tests both models have published scores on. The verdict counts the 18 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 18 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.