Model comparison
Claude Sonnet 4.5 vs GLM-5.3-Flash
GLM-5.3-Flash is the stronger model overall, scoring 49.6 to 44.0 on the Noometry Index.
Last verified . 29 shared benchmarks.
Summary
- They share 29 benchmarks with published results for both. Claude Sonnet 4.5 scores higher in 2 categories and GLM-5.3-Flash in 8 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where GLM-5.3-Flash leads 53.1 to 31.9.
- The biggest single-benchmark swing is FrontierMath (Tiers 1-3): 23.9% for Claude Sonnet 4.5 and 55.8% for GLM-5.3-Flash.
- GLM-5.3-Flash is cheaper at $0.15 / $0.50 per million input/output tokens, against $3 / $15 for Claude Sonnet 4.5.
- GLM-5.3-Flash has downloadable open weights; the other is API-only.
Side by side
| Claude Sonnet 4.5 | GLM-5.3-Flash | |
|---|---|---|
| Provider | Anthropic | Z.ai (Zhipu) |
| Noometry Index | 44.0 | 49.6 |
| Released | 2025-09-29 | 2026-08-20 |
| Weights | Proprietary | Open |
| Context window | 1M | 1M |
| Max output | 64K | 131K |
| Input $ / M tokens | $3 | $0.15 |
| Output $ / M tokens | $15 | $0.50 |
| Results tracked | 73 | 36 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-5.3-Flash leads
Claude Sonnet 4.5: 47.8 (#54), GLM-5.3-Flash: 53.7 (#26)
| Benchmark | Claude Sonnet 4.5 | GLM-5.3-Flash |
|---|---|---|
| LMArena WebDev | 1393 | 1614 |
| SciCode | 44.7% | 51.6% |
| LMArena Coding | 1489 | 1506 |
| ALE-Bench | 796.15 | 303.55 |
| SWE-bench Verified | 71.3% | — |
| DeepSWE | — | 63.4% |
| FrontierCode | — | 31.8% |
| SWE-bench Verified (bash only) | 71.4% | — |
| SWE-bench Multilingual | 67% | — |
| GSO | 14.7% | — |
| WeirdML | 47.7% | — |
| AlgoTune | 1.52 | — |
Agentic & Tool Use Claude Sonnet 4.5 leads
Claude Sonnet 4.5: 38.1 (#30), GLM-5.3-Flash: 34.3 (#41)
| Benchmark | Claude Sonnet 4.5 | GLM-5.3-Flash |
|---|---|---|
| Terminal-Bench | 46.5% | — |
| APEX-Agents | — | 52.8% |
| Berkeley Function Calling Leaderboard | 73.2% | — |
| GDPval | 42.5% | — |
| Remote Labor Index | 2.1% | — |
| τ²-bench Airline | 72% | — |
| τ²-bench Banking | 25.3% | — |
| τ²-bench Retail | 72.4% | — |
| τ²-bench Telecom | 84.9% | — |
| Cybench | 60% | — |
| DeepResearch Bench | 52.6% | — |
| OSWorld | 62.9% | — |
| GDP.pdf | — | 14% |
| LMArena Search | 1159 | — |
| METR Time Horizons | 67.4% | — |
| Vending-Bench 2 | 3,839 | — |
Reasoning GLM-5.3-Flash leads
Claude Sonnet 4.5: 26.9 (#113), GLM-5.3-Flash: 31.7 (#69)
| Benchmark | Claude Sonnet 4.5 | GLM-5.3-Flash |
|---|---|---|
| CritPt | 1.1% | 15.4% |
| Chess Puzzles | 12% | 14% |
| LMArena Hard Prompts | 1462 | 1490 |
| Mystery Game Puzzles | 17% | 8% |
| Epoch Capabilities Index | 146.84 | 151.9 |
| ARC-AGI-2 | 13.6% | — |
| SimpleBench | 54.3% | — |
| Kagi LLM Benchmark | 57.9% | — |
| NYT Connections (extended) | 37.3% | — |
| ARC-AGI-1 | 63.7% | — |
| EnigmaEval | 6% | — |
| EBR-Bench | 2.4% | — |
| DTBench | 83.2% | — |
| LMCA | 38.8% | — |
| Surface Evolver Bench | — | 52.5% |
| Bench to the Future 3 | — | 0.15 |
| ForecastBench | 61.9 | — |
Math GLM-5.3-Flash leads
Claude Sonnet 4.5: 31.9 (#190), GLM-5.3-Flash: 53.1 (#38)
| Benchmark | Claude Sonnet 4.5 | GLM-5.3-Flash |
|---|---|---|
| FrontierMath (Tiers 1-3) | 23.9% | 55.8% |
| FrontierMath Tier 4 | 2.4% | 17.1% |
| OTIS Mock AIME 2024-2025 | 77.8% | 93.9% |
| ProofBench | 19% | 21% |
| LMArena Math | 1448 | 1499 |
| Omni-MATH | 55.3% | — |
| MATH Level 5 | 97.7% | — |
| FrontierMath (Feb 2025 set) | 15.2% | — |
| FrontierMath Tier 4 (v1) | 4.2% | — |
Knowledge GLM-5.3-Flash leads
Claude Sonnet 4.5: 48.4 (#70), GLM-5.3-Flash: 58.4 (#33)
| Benchmark | Claude Sonnet 4.5 | GLM-5.3-Flash |
|---|---|---|
| GPQA Diamond | 82.3% | 90.2% |
| LMArena Expert | 1483 | 1512 |
| Humanity's Last Exam | 13.7% | — |
| SimpleQA Verified | 30.7% | — |
| MMLU-Pro | 86.9% | — |
| Vectara Hallucination Rate | 12% | — |
| GPQA (HELM) | 68.6% | — |
Multimodal GLM-5.3-Flash leads
Claude Sonnet 4.5: 34.1 (#84), GLM-5.3-Flash: 42.6 (#25)
| Benchmark | Claude Sonnet 4.5 | GLM-5.3-Flash |
|---|---|---|
| LMArena Vision | — | 1304 |
| VPCT | 39.8% | — |
| LMArena Document | 1450 | — |
Multilingual GLM-5.3-Flash leads
Claude Sonnet 4.5: 53.6 (#65), GLM-5.3-Flash: 56.2 (#24)
| Benchmark | Claude Sonnet 4.5 | GLM-5.3-Flash |
|---|---|---|
| LMArena Non-English | 1425 | 1462 |
| LMArena Chinese | 1459 | 1529 |
| LMArena French | 1459 | 1495 |
| LMArena German | 1427 | 1457 |
| LMArena Japanese | 1390 | 1420 |
| LMArena Korean | 1403 | 1443 |
| LMArena Russian | 1436 | 1472 |
| LMArena Spanish | 1457 | 1471 |
Instruction Following GLM-5.3-Flash leads
Claude Sonnet 4.5: 75.2 (#74), GLM-5.3-Flash: 77.8 (#17)
| Benchmark | Claude Sonnet 4.5 | GLM-5.3-Flash |
|---|---|---|
| LMArena Instruction Following | 1459 | 1480 |
| IFEval | 85% | — |
Long Context Too close to call
Claude Sonnet 4.5: 45.2 (#45), GLM-5.3-Flash: 45.3 (#41)
| Benchmark | Claude Sonnet 4.5 | GLM-5.3-Flash |
|---|---|---|
| LMArena Longer Query | 1476 | 1479 |
Writing & Preference Claude Sonnet 4.5 leads
Claude Sonnet 4.5: 66.7 (#33), GLM-5.3-Flash: 65.4 (#49)
| Benchmark | Claude Sonnet 4.5 | GLM-5.3-Flash |
|---|---|---|
| LMArena Text | 1439 | 1471 |
| LMArena Creative Writing | 1442 | 1440 |
| LMArena Multi-Turn | 1465 | 1471 |
| EQ-Bench Creative Writing | 1678 | — |
| WildBench | 85.4% | — |
Frequently asked questions
Is Claude Sonnet 4.5 better than GLM-5.3-Flash?
GLM-5.3-Flash is the stronger model overall, scoring 49.6 to 44.0 on the Noometry Index.
Which is cheaper, Claude Sonnet 4.5 or GLM-5.3-Flash?
GLM-5.3-Flash is cheaper. It lists at $0.15 per million input tokens and $0.50 per million output tokens; Claude Sonnet 4.5 lists at $3 and $15.
Is Claude Sonnet 4.5 or GLM-5.3-Flash better for coding?
GLM-5.3-Flash scores higher on coding benchmarks: 53.7 versus 47.8 in the Noometry coding category.
Which has the bigger context window?
Both accept 1M tokens.
How many benchmarks do Claude Sonnet 4.5 and GLM-5.3-Flash share?
29 benchmarks have published results for both models. Claude Sonnet 4.5 has 73 scored results on Noometry and GLM-5.3-Flash has 36.