Model comparison
Claude Sonnet 5 vs GLM-5
Claude Sonnet 5 is the stronger model overall, scoring 54.6 to 46.1 on the Noometry Index. GLM-5 costs 2.6× less per token, which makes it the better buy when Claude Sonnet 5's lead doesn't matter for your workload.
Last verified . 29 shared benchmarks.
Summary
- They share 29 benchmarks with published results for both. Claude Sonnet 5 scores higher in 9 categories and GLM-5 in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Claude Sonnet 5 leads 49.1 to 27.6.
- The biggest single-benchmark swing is Chess Puzzles: 35% for Claude Sonnet 5 and 10% for GLM-5.
- GLM-5 is cheaper at $1 / $3.20 per million input/output tokens, against $2 / $10 for Claude Sonnet 5.
- Claude Sonnet 5 accepts more context: 1M tokens versus 205K.
- GLM-5 has downloadable open weights; the other is API-only.
Side by side
| Claude Sonnet 5 | GLM-5 | |
|---|---|---|
| Provider | Anthropic | Z.ai (Zhipu) |
| Noometry Index | 54.6 | 46.1 |
| Released | 2026-06-29 | 2026-02-11 |
| Weights | Proprietary | Open |
| Context window | 1M | 205K |
| Max output | 128K | 131K |
| Input $ / M tokens | $2 | $1 |
| Output $ / M tokens | $10 | $3.20 |
| Results tracked | 51 | 45 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Sonnet 5 leads
Claude Sonnet 5: 55.5 (#26), GLM-5: 49.0 (#52)
| Benchmark | Claude Sonnet 5 | GLM-5 |
|---|---|---|
| LMArena WebDev | 1541 | 1434 |
| WeirdML | 68.8% | 48.2% |
| LMArena Coding | 1483 | 1461 |
| ALE-Bench | 1,463 | 765.62 |
| SWE-bench Verified | — | 72.1% |
| DeepSWE | 53.8% | — |
| FrontierCode | 42.7% | — |
| SWE-bench Verified (bash only) | — | 72.8% |
| CursorBench | 34.1% | — |
| SWE-bench Multilingual | — | 69.7% |
| SciCode | 54.3% | — |
| GSO | 37.3% | — |
Agentic & Tool Use Claude Sonnet 5 leads
Claude Sonnet 5: 42.8 (#18), GLM-5: 31.1 (#71)
| Benchmark | Claude Sonnet 5 | GLM-5 |
|---|---|---|
| Vending-Bench 2 | 6,378 | 4,432 |
| Terminal-Bench | — | 52.4% |
| APEX-Agents | 54.5% | — |
| τ²-bench Airline | — | 82.5% |
| τ²-bench Banking | — | 9.8% |
| τ²-bench Retail | — | 73.7% |
| τ²-bench Telecom | — | 86.8% |
| GBAEval | 65.3% | — |
| LMArena Search | 1194 | — |
Reasoning Claude Sonnet 5 leads
Claude Sonnet 5: 49.1 (#39), GLM-5: 27.6 (#116)
| Benchmark | Claude Sonnet 5 | GLM-5 |
|---|---|---|
| SimpleBench | 60.6% | 53.2% |
| NYT Connections (extended) | 75.1% | 74.8% |
| Chess Puzzles | 35% | 10% |
| LMArena Hard Prompts | 1461 | 1452 |
| Epoch Capabilities Index | 156.21 | 145.83 |
| ForecastBench | 61.1 | 61 |
| ARC-AGI-2 | — | 4.9% |
| Kagi LLM Benchmark | — | 75% |
| ARC-AGI-1 | — | 44.7% |
| CritPt | 16.9% | — |
| Mystery Game Puzzles | 35% | — |
| DTBench | 92.5% | — |
| LMCA | 50% | — |
| Surface Evolver Bench | 60% | — |
| Bench to the Future 3 | 0.14 | — |
Math Claude Sonnet 5 leads
Claude Sonnet 5: 66.2 (#27), GLM-5: 46.4 (#71)
| Benchmark | Claude Sonnet 5 | GLM-5 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 94.7% | 80% |
| LMArena Math | 1467 | 1440 |
| FrontierMath (Tiers 1-3) | 65.6% | — |
| FrontierMath Tier 4 | 29.3% | — |
| MathArena Final-Answer Competitions | — | 65.7% |
| ProofBench | 77% | — |
| FrontierMath (Feb 2025 set) | — | 16.4% |
| FrontierMath Tier 4 (v1) | — | 2.1% |
Knowledge Claude Sonnet 5 leads
Claude Sonnet 5: 55.6 (#47), GLM-5: 52.3 (#64)
| Benchmark | Claude Sonnet 5 | GLM-5 |
|---|---|---|
| GPQA Diamond | 90.5% | 87.8% |
| LMArena Expert | 1490 | 1454 |
| SimpleQA Verified | 33.7% | — |
| Vectara Hallucination Rate | — | 10.1% |
Multimodal Not comparable
Claude Sonnet 5: 42.4 (#31), GLM-5: —
| Benchmark | Claude Sonnet 5 | GLM-5 |
|---|---|---|
| LMArena Vision | 1274 | — |
| Blueprint-Bench 2 | 24.9% | — |
| LMArena Document | 1466 | — |
Multilingual Too close to call
Claude Sonnet 5: 53.8 (#55), GLM-5: 53.7 (#58)
| Benchmark | Claude Sonnet 5 | GLM-5 |
|---|---|---|
| LMArena Non-English | 1431 | 1430 |
| LMArena Chinese | 1477 | 1511 |
| LMArena French | 1460 | 1455 |
| LMArena German | 1440 | 1445 |
| LMArena Japanese | 1422 | 1416 |
| LMArena Korean | 1411 | 1423 |
| LMArena Russian | 1451 | 1436 |
| LMArena Spanish | 1437 | 1454 |
Instruction Following Claude Sonnet 5 leads
Claude Sonnet 5: 76.3 (#41), GLM-5: 75.2 (#67)
| Benchmark | Claude Sonnet 5 | GLM-5 |
|---|---|---|
| LMArena Instruction Following | 1452 | 1428 |
Long Context Too close to call
Claude Sonnet 5: 44.8 (#55), GLM-5: 44.7 (#60)
| Benchmark | Claude Sonnet 5 | GLM-5 |
|---|---|---|
| LMArena Longer Query | 1463 | 1446 |
| CL-bench | — | 18.7% |
Writing & Preference Claude Sonnet 5 leads
Claude Sonnet 5: 69.2 (#25), GLM-5: 66.0 (#38)
| Benchmark | Claude Sonnet 5 | GLM-5 |
|---|---|---|
| LMArena Text | 1442 | 1446 |
| LMArena Creative Writing | 1416 | 1439 |
| EQ-Bench Creative Writing | 1794 | 1601 |
| LMArena Multi-Turn | 1454 | 1456 |
| EQ-Bench 4 | 1236 | — |
Frequently asked questions
Is Claude Sonnet 5 better than GLM-5?
Claude Sonnet 5 is the stronger model overall, scoring 54.6 to 46.1 on the Noometry Index. GLM-5 costs 2.6× less per token, which makes it the better buy when Claude Sonnet 5's lead doesn't matter for your workload.
Which is cheaper, Claude Sonnet 5 or GLM-5?
GLM-5 is cheaper. It lists at $1 per million input tokens and $3.20 per million output tokens; Claude Sonnet 5 lists at $2 and $10.
Is Claude Sonnet 5 or GLM-5 better for coding?
Claude Sonnet 5 scores higher on coding benchmarks: 55.5 versus 49.0 in the Noometry coding category.
Which has the bigger context window?
Claude Sonnet 5 does, with 1M tokens against 205K.
How many benchmarks do Claude Sonnet 5 and GLM-5 share?
29 benchmarks have published results for both models. Claude Sonnet 5 has 51 scored results on Noometry and GLM-5 has 45.