Claude Sonnet 4 vs GLM-4.7-Flash
Wins 4 of 6 areas
Coding · Reasoning · Facts · Long documents
Wins 2 of 6 areas
Agents · Following instructions
Claude Sonnet 4 is the stronger all-rounder.GLM-4.7-Flash is cheaper and better at agents.
Scores updated · 24 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 software31Claude Sonnet 43 of 4 tests
- ReasoningHard problems that need careful thinking20Claude Sonnet 42 of 3 tests · 1 tie
- FactsGetting facts right instead of making them up21Claude Sonnet 42 of 3 tests
- Long documentsFinding answers in very long texts10Claude Sonnet 41 of 1 test
- AgentsCarrying out multi-step tasks on its own02GLM-4.7-Flash2 of 2 tests
- Following instructionsDoing exactly what it is asked01GLM-4.7-Flash1 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-4.7-Flash costs 97% 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 Sonnet 4 pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+64.8points ahead
- Reasons across sets of long documentsAA-LCR+28.6points ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+19.6points ahead
Where GLM-4.7-Flash pulls ahead
- Finds hard-to-locate facts by browsing the webBrowseComp+30.6points ahead
- Recent programming contest problemsLiveCodeBench v6+15.5points ahead
- Real work tasks from 44 professionsGDPVal+7.2points ahead
Every test, side by side
All 24 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingClaude Sonnet 4
- LiveCodeBench v6GLM-4.7-Flash by 15.548.564+15.5
- SWE-bench VerifiedClaude Sonnet 4 by 13.572.759.2+13.5
- Terminal-Bench HardClaude Sonnet 4 by 9.131.122+9.1
- SciCodeClaude Sonnet 4 by 6.34033.7+6.3
AgentsGLM-4.7-Flash
- BrowseCompGLM-4.7-Flash by 30.612.242.8+30.6
- GDPValGLM-4.7-Flash by 7.29.716.9+7.2
ReasoningClaude Sonnet 4
- GPQA DiamondClaude Sonnet 4 by 19.677.758.1+19.6
- Humanity's Last ExamClaude Sonnet 4 by 3.110.77.6+3.1
- CritPttie0.30.3tie
FactsClaude Sonnet 4
- AA-Omniscience · Non-hallucinationClaude Sonnet 4 by 64.870.96.1+64.8
- AA-Omniscience · AccuracyClaude Sonnet 4 by 6.522.716.1+6.5
- Vectara HHEM hallucination ratelower is betterGLM-4.7-Flash by 110.39.3+1
Following instructionsGLM-4.7-Flash
- IFBenchGLM-4.7-Flash by 6.154.760.8+6.1
Other results10 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 by 62.80.2-62.6+62.8
- τ²-BenchGLM-4.7-Flash by 34.345.279.5+34.3
- τ²-Bench Telecom (AA run)GLM-4.7-Flash by 34.264.698.8+34.2
- AA Agentic IndexGLM-4.7-Flash by 28.417.646+28.4
- AIME 2025GLM-4.7-Flash by 21.170.591.6+21.1
- Artificial Analysis Coding IndexClaude Sonnet 4 by 11.737.625.9+11.7
- vectara_avg_summary_lengthClaude Sonnet 4 by 74 rating points145.871.8+74 rating
- vectara_answer_rateClaude Sonnet 4 by 798.691.6+7
- AA IntelligenceClaude Sonnet 4 by 418.914.9+4
- vectara_factual_consistencyGLM-4.7-Flash by 189.790.7+1
Questions people ask
Which is better, Claude Sonnet 4 or GLM-4.7-Flash?
Claude Sonnet 4 wins four of the six areas where both have results: coding, reasoning, facts and long documents. GLM-4.7-Flash wins agents and following instructions, and costs 97% less.
Which is better for coding?
Claude Sonnet 4. It wins 3 of the 4 coding tests both models report; GLM-4.7-Flash wins 1.
Which is cheaper?
Claude Sonnet 4 costs $3.00 per million input tokens and $15.00 per million output tokens; GLM-4.7-Flash costs $0.07 and $0.40. That makes GLM-4.7-Flash about 97% cheaper for the same work.
How do you compare the two?
We use the 24 benchmark tests both models have published scores on. The verdict counts the 14 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 10 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.