Claude Opus 4.5 vs GLM-5
Wins 4 of 7 areas
Coding · Reasoning · Math · Long documents
Wins 2 of 7 areas
Agents · Following instructions
Claude Opus 4.5 wins more areas, narrowly.GLM-5 is cheaper and better at agents.
Scores updated · 39 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 5 tests
- ReasoningHard problems that need careful thinking30Claude Opus 4.53 of 4 tests · 1 tie
- MathCompetition and research-level math20Claude Opus 4.52 of 3 tests · 1 tie
- Long documentsFinding answers in very long texts10Claude Opus 4.51 of 1 test
- AgentsCarrying out multi-step tasks on its own12GLM-52 of 3 tests
- Following instructionsDoing exactly what it is asked01GLM-51 of 1 test
- FactsGetting facts right instead of making them up11Even1 each · 1 tie
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 costs 86% 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
- Abstract visual puzzles that people can solveARC-AGI-2+32.7points ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+20.3points ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+4.6points ahead
Where GLM-5 pulls ahead
- Finds hard-to-locate facts by browsing the webBrowseComp+38.9points ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+25.7points ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+14.3points ahead
Every test, side by side
All 39 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingClaude Opus 4.5
- Terminal-Bench HardClaude Opus 4.5 by 3.84743.2+3.8
- LMArena · WebDevClaude Opus 4.5 by 35 rating points14691434+35 rating
- SciCodeClaude Opus 4.5 by 3.349.546.2+3.3
- SWE-bench ProGLM-5 by 3.15255.1+3.1
- SWE-bench VerifiedClaude Opus 4.5 by 3.180.977.8+3.1
AgentsGLM-5
- BrowseCompGLM-5 by 38.93775.9+38.9
- MCP AtlasGLM-5 by 5.562.367.8+5.5
- GDPValClaude Opus 4.5 by 2.747.344.6+2.7
ReasoningClaude Opus 4.5
- ARC-AGI-2Claude Opus 4.5 by 32.737.64.9+32.7
- GPQA DiamondClaude Opus 4.5 by 4.686.682+4.6
- CritPtClaude Opus 4.5 by 2.64.62+2.6
- Humanity's Last Examtie30.129.3tie
FactsEven
- AA-Omniscience · Non-hallucinationGLM-5 by 25.73964.7+25.7
- AA-Omniscience · AccuracyClaude Opus 4.5 by 20.346.626.3+20.3
- Vectara HHEM hallucination ratelower is bettertie10.910.1tie
MathClaude Opus 4.5
- HMMT Feb. 2026Claude Opus 4.5 by 2.585.382.8+2.5
- IMOAnswerBenchClaude Opus 4.5 by 1.58482.5+1.5
- AIME 2026tie95.195.4tie
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.
- ARC-AGI-1Claude Opus 4.5 by 37.38244.7+37.3
- AA-OmniscienceClaude Opus 4.5 by 13.7140.3+13.7
- τ²-Bench Telecom (AA run)GLM-5 by 8.789.598.2+8.7
- τ²-BenchClaude Opus 4.5 by 8.598.289.7+8.5
- NL2RepoClaude Opus 4.5 by 7.343.235.9+7.3
- HLE (with tools)GLM-5 by 7.243.250.4+7.2
- vectara_avg_summary_lengthClaude Opus 4.5 by 40.1 rating points114.574.4+40.1 rating
- AIME 2025GLM-5 by 3.992.896.7+3.9
- Artificial Analysis Coding IndexClaude Opus 4.5 by 3.647.844.2+3.6
- HMMT Nov. 2025GLM-5 by 3.693.396.9+3.6
- AA Agentic IndexGLM-5 by 3.559.663.1+3.5
- Terminal-Bench 2.0Claude Opus 4.5 by 3.159.356.2+3.1
- CyberGymClaude Opus 4.5 by 2.350.648.3+2.3
- frontiermath_tier_4_v1Claude Opus 4.5 by 2.14.22.1+2.1
- swe_bench_bashClaude Opus 4.5 by 1.674.472.8+1.6
- AA IntelligenceClaude Opus 4.5 by 1.229.127.9+1.2
- vectara_answer_rateGLM-5 by 198.799.7+1
- vectara_factual_consistencytie89.189.9tie
- AIME 2026 I (Tools-allowed)tie93.392.7tie
Questions people ask
Which is better, Claude Opus 4.5 or GLM-5?
Claude Opus 4.5 wins four of the seven areas where both have results: coding, reasoning, math and long documents. GLM-5 wins agents and following instructions, and costs 86% less. They are level on facts.
Which is better for coding?
Claude Opus 4.5. It wins 4 of the 5 coding tests both models report; GLM-5 wins 1.
Which is cheaper?
Claude Opus 4.5 costs $5.00 per million input tokens and $25.00 per million output tokens; GLM-5 costs $1.00 and $3.20. That makes GLM-5 about 86% cheaper for the same work.
How do you compare the two?
We use the 39 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 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.